阅读说明：本技术 判定装置、太阳光发电系统、判定方法及判定程序 (Determination device, photovoltaic power generation system, determination method, and determination program ) 是由 后藤勋 下口刚史 谷村晃太郎 池上洋行 于 2018-10-10 设计创作，主要内容包括：判定装置(101)是在具备包括太阳能单电池的发电部的太阳光发电系统中使用的判定装置,具备：获取部(86),获取参照期间的输出数据及对象期间的输出数据,所述输出数据为所述发电部的输出的计测结果的时间序列的输出数据：及判定部(81),基于由所述获取部(86)获取到的所述参照期间的所述输出数据,判定所述对象期间的所述输出数据的异常。(A determination device (101) is used in a solar power generation system provided with a power generation unit including a solar cell, and is provided with: an acquisition unit (86) that acquires output data for a reference period and output data for a target period, the output data being time-series output data of a measurement result of the output of the power generation unit: and a determination unit (81) that determines an abnormality in the output data of the target period based on the output data of the reference period acquired by the acquisition unit (86).)

1. A determination device for a solar photovoltaic power generation system, which comprises a power generation unit including a solar cell,

the determination device includes:

an acquisition unit that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit; and

and a determination unit configured to determine an abnormality in the output data of the target period based on the output data of the reference period acquired by the acquisition unit.

2. The determination device according to claim 1,

the target period is a period subsequent to the reference period.

3. The determination device according to claim 1 or 2,

the decision section decides an anomaly of the output data using any one or more of an autoregressive model, statistical analysis, bayesian statistics, sparse structure learning, neural networks, support vector machines, naive bayes, k-nearest neighbor algorithms, decision trees, C4.5, classification and regression trees, random forests, adaptive boosting, bagging, hierarchical clustering, k-means, maximum expectation algorithms, latent semantic analysis, probabilistic latent semantic analysis, linear discriminant analysis, hierarchical dirichlet processes, latent dirichlet distribution, k-center point method, generalized linear models, hierarchical bayes, and autoregressive mapping.

4. The determination device according to any one of claims 1 to 3,

the solar power generation system is provided with:

1 or a plurality of junction boxes, each junction box collecting output lines from 1 or a plurality of the power generation units;

1 or more header tanks, each header tank collecting a collection line from 1 or more of the junction tanks;

1 or a plurality of power conversion devices each of which collects a collection line from 1 or a plurality of the collection boxes; and

and a distribution cabinet for collecting the collection lines from 1 or more of the power conversion devices.

5. A solar power generation system is provided with:

1 or more power generation sections including solar cells;

1 or a plurality of junction boxes, each junction box collecting output lines from 1 or a plurality of the power generation units;

1 or more header tanks, each header tank collecting a collection line from 1 or more of the junction tanks;

1 or a plurality of power conversion devices each of which collects a collection line from 1 or a plurality of the collection boxes;

a power distribution cabinet that collects collection lines from 1 or a plurality of the power conversion devices; and

and a determination device that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit, and that determines an abnormality in the output data of the target period based on the acquired output data of the reference period.

6. A determination method in a determination device, the determination method comprising:

acquiring output data of a reference period and output data of a target period, wherein the output data is time-series output data including a measurement result of the output of the power generation unit of the solar cell; and

determining abnormality of the output data in the target period based on the acquired output data in the reference period.

7. A judgment program used in a judgment device,

the determination program is configured to cause a computer to function as an acquisition unit that acquires output data of a reference period and output data of a target period, the output data being time-series output data including a measurement result of an output of a power generation unit of a solar cell, and a determination unit that determines an abnormality in the output data of the target period based on the output data of the reference period acquired by the acquisition unit.

Technical Field

The invention relates to a determination device, a solar photovoltaic power generation system, a determination method, and a determination program.

The present application claims priority based on japanese application patent application No. 2017-253407, filed on 12/28/2017, the disclosure of which is incorporated herein in its entirety.

Background

Japanese patent laying-open No. 2012 and 205078 (patent document 1) discloses the following monitoring system for solar photovoltaic power generation. That is, the monitoring system for solar power generation is a monitoring system for solar power generation that monitors the power generation status of a solar cell panel for a solar power generation system that collects outputs from a plurality of solar cell panels and sends the collected outputs to a power conversion device, and includes: a measuring device which is provided at a location where the output circuits from the plurality of solar panels are collected, and measures the amount of power generated by each solar panel; a lower communication device connected to the measurement device and having a function of transmitting measurement data of the amount of power generated by the measurement device; an upper communication device having a function of receiving the measurement data transmitted from the lower communication device; and a management device having a function of collecting the measurement data for each solar cell panel via the upper communication device. The management device determines the presence or absence of an abnormality based on a difference in power generation amounts at the same time point for the respective solar panels, or determines the presence or absence of an abnormality based on a maximum value or an integrated value of the power generation amounts for a predetermined period for the respective solar panels.

Disclosure of Invention

(1) The disclosed determination device is used in a solar photovoltaic power generation system that includes a power generation unit including a solar cell, and includes: an acquisition unit that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit; and a determination unit configured to determine an abnormality in the output data in the target period based on the output data in the reference period acquired by the acquisition unit.

(5) The disclosed solar power generation system is provided with: 1 or more power generation sections including solar cells; 1 or a plurality of junction boxes, each junction box collecting output lines from 1 or a plurality of the power generation units; 1 or more header tanks, each header tank collecting a collection line from 1 or more of the junction tanks; 1 or a plurality of power conversion devices each of which collects a collection line from 1 or a plurality of the collection boxes; a power distribution cabinet that collects collection lines from 1 or a plurality of the power conversion devices; and a determination device that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit, and determines an abnormality in the output data of the target period based on the acquired output data of the reference period.

(6) The determination method of the present disclosure is a determination method in a determination device, including the steps of: acquiring output data of a reference period and output data of a target period, wherein the output data is time-series output data including a measurement result of the output of the power generation unit of the solar cell; and determining abnormality of the output data in the target period based on the acquired output data in the reference period.

(7) The determination program of the present disclosure is a determination program used in a determination device for causing a computer to function as an acquisition unit that acquires output data of a reference period and output data of a target period, the output data being time-series output data including a measurement result of an output of a power generation unit of a solar cell, and a determination unit that determines an abnormality of the output data of the target period based on the output data of the reference period acquired by the acquisition unit.

An aspect of the present disclosure can be realized not only as a determination device having a processing unit with such a feature, but also as a semiconductor integrated circuit that realizes part or all of the determination device.

In addition, one aspect of the present disclosure can be realized not only as a solar photovoltaic power generation system including a processing unit having such a characteristic, but also as a method including the processing unit having the characteristic as a step. In addition, an aspect of the present disclosure can be implemented as a semiconductor integrated circuit that realizes part or all of a solar photovoltaic power generation system.

Drawings

Fig. 1 is a diagram showing a configuration of a solar photovoltaic power generation system according to an embodiment of the present invention.

Fig. 2 is a diagram showing the configuration of a PCS unit of the embodiment of the present invention.

Fig. 3 is a diagram showing the structure of a current collecting unit according to the embodiment of the present invention.

Fig. 4 is a diagram showing the structure of a solar battery cell according to an embodiment of the present invention.

Fig. 5 is a diagram showing the configuration of a power generation state determination system according to an embodiment of the present invention.

Fig. 6 is a diagram showing a configuration of a monitoring device in the power generation state determination system according to the embodiment of the present invention.

Fig. 7 is a diagram showing the configuration of a determination device in the power generation state determination system according to the embodiment of the present invention.

Fig. 8 is a diagram showing an example of monitoring information held by a determination device in the power generation state determination system according to the embodiment of the present invention.

Fig. 9 is a diagram showing an example of the generated power data acquired by the acquisition unit in the determination device according to the embodiment of the present invention.

Fig. 10 is a diagram showing an example of 5 clusters for classifying reference data and target data in the determination device according to the embodiment of the present invention.

Fig. 11 is a diagram showing an example of 7 clusters that classify reference data in the determination device according to the embodiment of the present invention.

Fig. 12 is a diagram showing an example of 9 clusters that classify reference data in the determination device according to the embodiment of the present invention.

Fig. 13 is a diagram showing an example of 11 clusters that classify reference data in the determination device according to the embodiment of the present invention.

Fig. 14 is a flowchart for determining an operation procedure when the determination device of the embodiment of the present invention determines an abnormality of the power generation unit.

Detailed Description

In recent years, techniques for monitoring a photovoltaic power generation system to determine an abnormality have been developed.

[ problems to be solved by the present disclosure ]

A technique capable of improving the accuracy of abnormality determination of a photovoltaic power generation system beyond the technique described in patent document 1 is desired.

The present disclosure has been made to solve the above-described problems, and an object thereof is to provide a determination device, a photovoltaic power generation system, a determination method, and a determination program that can improve the accuracy of abnormality determination of a photovoltaic power generation system.

[ Effect of the present disclosure ]

According to the present disclosure, the accuracy of abnormality determination of the solar power generation system can be improved.

[ description of embodiments of the invention of the present application ]

First, the description of the embodiments of the present invention is given.

(1) A determination device according to an embodiment of the present invention is a determination device used in a photovoltaic power generation system including a power generation unit including a solar cell, and includes: an acquisition unit that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit; and a determination unit configured to determine an abnormality in the output data in the target period based on the output data in the reference period acquired by the acquisition unit.

In this way, for example, by configuring to determine an abnormality based on time-series output data, which is a measurement result of the output of the power generation unit, without setting parameters of the natural environment such as air temperature, weather, and solar radiation amount as conditions, it is possible to detect an abnormality without providing a panel thermometer and a solar radiation amount. In addition, since the number of times of visual confirmation can be reduced by reducing the number of devices to be installed, the possibility of erroneous confirmation can be reduced. Therefore, the accuracy of the abnormality determination of the solar power generation system can be improved.

(2) Preferably, the target period is a period subsequent to the reference period.

With this configuration, it is possible to more accurately determine an abnormality by using output data accumulated in the past.

(3) Preferably, the determination section uses an autoregressive model, statistical Analysis, Bayesian statistics, sparse structure learning, neural networks, support vector machines, naive Bayes, k-nearest neighbor algorithm (kNN: k-nearest neighbor algorithm), decision trees, C4.5, CART (Classification and Regression Trees: Classification and Regression trees), stochastic forests, adoost (adaptive enhancement), bagging, hierarchical clustering, k-means (k-means), EM algorithm (expectation maximization algorithm), Latent Semantic Analysis (LSA: late Semantic Analysis), probabilistic Latent Semantic Analysis (PLSA: Latent Semantic Analysis), Linear Discriminant Analysis (LDA: Linear Discriminant Analysis), hierarchical Leide Process (HDP: high probability distribution), Latent Linear Discriminant Analysis (LDA: Latent Linear Discriminant Analysis), and Latent Linear Discriminant Analysis (LDA: hierarchical Lee-weighted Analysis), and hierarchical Lee-weighted Analysis (HDP: high probability distribution-weighted distribution) models, And determining the abnormality of the output data by any one or more of a linear model, hierarchical Bayes and self-organizing map (SOM).

According to such a configuration, it is possible to detect an abnormality more favorably by using an autoregressive model, machine learning, statistical analysis, bayesian statistics, sparse structure learning, or other methods.

(4) Preferably, the solar power generation system includes: 1 or a plurality of junction boxes, each junction box collecting output lines from 1 or a plurality of the power generation units; 1 or more header tanks, each header tank collecting a collection line from 1 or more of the junction tanks; 1 or a plurality of power conversion devices each of which collects a collection line from 1 or a plurality of the collection boxes; and a power distribution cabinet for collecting the collection lines from 1 or more of the power conversion devices.

According to such a configuration, since output data can be collected at a desired location, it is possible to detect an abnormality for each power generation unit, each junction box, each collector box, each power conversion device, or each distribution box, and to improve the estimation of the cause of the abnormality.

(5) A solar power generation system according to an embodiment of the present invention includes: 1 or more power generation sections including solar cells; 1 or a plurality of junction boxes, each junction box collecting output lines from 1 or a plurality of the power generation units; 1 or more header tanks, each header tank collecting a collection line from 1 or more of the junction tanks; 1 or a plurality of power conversion devices each of which collects a collection line from 1 or a plurality of the collection boxes; a power distribution cabinet that collects collection lines from 1 or a plurality of the power conversion devices; and a determination device that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit, and determines an abnormality in the output data of the target period based on the acquired output data of the reference period.

In this way, for example, by a configuration in which the abnormality is determined based on the time-series output data that is the measurement result of the output of the power generation unit without setting the parameters of the natural environment such as the temperature, the weather, and the solar radiation amount as conditions, the abnormality can be detected without providing the panel thermometer and the solar radiation amount. In addition, since the number of times of visual confirmation can be reduced by reducing the number of devices to be installed, the possibility of erroneous confirmation can be reduced. Therefore, the accuracy of the abnormality determination of the solar power generation system can be improved.

(6) A determination method according to an embodiment of the present invention is a determination method in a determination device, the determination method including: acquiring output data of a reference period and output data of a target period, wherein the output data is time-series output data including a measurement result of the output of the power generation unit of the solar cell; and determining abnormality of the output data in the target period based on the acquired output data in the reference period.

In this way, for example, by configuring to determine an abnormality based on time-series output data, which is a measurement result of the output of the power generation unit, without setting parameters of the natural environment such as air temperature, weather, and solar radiation amount as conditions, it is possible to detect an abnormality without providing a panel thermometer and a solar radiation amount. In addition, since the number of times of visual confirmation can be reduced by reducing the number of devices to be installed, the possibility of erroneous confirmation can be reduced. Therefore, the accuracy of the abnormality determination of the solar power generation system can be improved.

(7) A determination program according to an embodiment of the present invention is a determination program used in a determination device for causing a computer to function as an acquisition unit that acquires output data of a reference period and output data of a target period, the output data being time-series output data including a measurement result of an output of a power generation unit of a solar cell, and a determination unit that determines an abnormality of the output data of the target period based on the output data of the reference period acquired by the acquisition unit.

In this way, for example, by configuring to determine an abnormality based on time-series output data, which is a measurement result of the output of the power generation unit, without setting parameters of the natural environment such as air temperature, weather, and solar radiation amount as conditions, it is possible to detect an abnormality without providing a panel thermometer and a solar radiation amount. In addition, since the number of times of visual confirmation can be reduced by reducing the number of devices to be installed, the possibility of erroneous confirmation can be reduced. Therefore, the accuracy of the abnormality determination of the solar power generation system can be improved.

Embodiments of the present invention will be described below with reference to the drawings. In the drawings, the same or corresponding portions are denoted by the same reference numerals, and description thereof will not be repeated. At least some of the embodiments described below may be arbitrarily combined.

[ constitution of solar Power Generation System ]

Fig. 1 is a diagram showing a configuration of a solar photovoltaic power generation system according to an embodiment of the present invention.

Referring to fig. 1, a photovoltaic Power generation system 401 includes 4 PCS (Power Conditioning Subsystem) units 80 and a Power distribution cabinet 6. The switch cabinet 6 comprises a copper bar 73.

In fig. 1, 4 PCS units 80 are representatively illustrated, but a plurality of or a small number of PCS units 80 may be provided.

Fig. 2 is a diagram showing the configuration of a PCS unit of the embodiment of the present invention.

Referring to fig. 2, the PCS unit 80 includes 4 current collecting units 60 and a PCS (power conversion device) 8. PCS8 includes copper bar 7 and power conversion unit 9.

In fig. 2, 4 current collecting units 60 are representatively illustrated, but a plurality of or a small number of current collecting units 60 may be provided.

Fig. 3 is a diagram showing the structure of a current collecting unit according to the embodiment of the present invention.

Referring to fig. 3, the current collecting unit 60 includes 4 solar cells 74 and a current collecting box 71. The collector box 71 has copper bars 72.

In fig. 3, 4 solar cells 74 are representatively illustrated, but a plurality or a small number of solar cells 74 may also be provided.

Fig. 4 is a diagram showing the structure of a solar battery cell according to an embodiment of the present invention.

Referring to fig. 4, the solar cell 74 includes 4 power generation sections 78 and a connection box 76. The power generation unit 78 includes a solar panel. The connecting box 76 has a copper bar 77.

In fig. 4, 4 power generation sections 78 are representatively illustrated, but a plurality of or a small number of power generation sections 78 may also be provided.

In this example, the power generation unit 78 is a solar cell panel string in which a plurality of solar cell panels are connected in series.

In the photovoltaic power generation system 401, power lines, which are output lines and collective lines from the plurality of power generation units 78, are electrically connected to the power distribution box 6.

In the solar photovoltaic power generation system 401, each of the 1 or more junction boxes 76 collects the output lines 1 from the 1 or more power generation units 78 as the collective line 5. Each of the 1 or more collector boxes 71 collects the collected lines 5 from the 1 or more junction boxes 76 as collected lines 2. Each PCS of the 1 or more PCS8 collects the collection lines 2 from the 1 or more collection boxes 71 into a collection line 4. The switch boards 6 collect the collection lines 4 from 1 or more PCS 8.

More specifically, the output line 1 of the power generation unit 78 has a 1 st end connected to the power generation unit 78 and a 2 nd end connected to the copper bar 77. The output lines 1 are collected as a collection line 5 via a copper bar 77. The copper bar 77 is disposed inside the connection box 76, for example.

Upon receiving the sunlight, power generation unit 78 converts the energy of the received sunlight into dc power and outputs the converted dc power to output line 1.

Referring to fig. 3 and 4, the collector 5 has a 1 st end connected to the copper bar 77 and a 2 nd end connected to the copper bar 72 of the corresponding solar cell 74. The collection lines 5 are collected as collection lines 2 via copper bars 72. The copper bar 72 is disposed inside the header box 71, for example.

Referring to fig. 1 to 4, in the photovoltaic power generation system 401, as described above, the output lines 1 from the plurality of power generation units 78 are collected as the collection line 5, the collection lines 5 are collected as the collection line 2, the collection lines 2 are collected as the collection line 4, and the collection lines 4 are electrically connected to the distribution box 6.

More specifically, each collector line 2 has a 1 st end connected to the copper bar 72 of the corresponding collector unit 60 and a 2 nd end connected to the copper bar 7. In PCS8, internal wire 3 has the 1 st end connected to copper bar 7 and the 2 nd end connected to power conversion unit 9.

In the PCS8, for example, when the power conversion unit 9 receives dc power generated in each power generation unit 78 via the output line 1, the copper bar 77, the collector line 5, the copper bar 72, the collector line 2, the copper bar 7, and the internal line 3, the received dc power is converted into ac power and output to the collector line 4.

The collecting line 4 has a 1 st end connected to the power conversion unit 9 and a 2 nd end connected to the copper bar 73.

In the distribution box 6, the ac power output from the power conversion unit 9 in each PCS8 to each collector line 4 is output to the system via the copper bar 73.

[ problem ]

In order to detect an abnormality in photovoltaic power generation, the photovoltaic power generation system 401 includes a method of measuring the amount of power generation of the solar cell panel while observing the solar conditions and comparing the measured amount of power generation with the estimated amount of power generation, a method of normalizing the amount of power generation in the junction box 76 for the power generation unit 78 having the largest amount of power generation and comparing the normalized amount of power generation with a value published by the manufacturer, a method of visually confirming the data of the amount of power generation, and the like.

However, in such a method, it is necessary to add a device such as a sunshine meter, which is costly, and the device is visually confirmed, so that many false confirmations are made. In addition, a decrease in the amount of power generation can only be found as an abnormality.

Therefore, in the solar photovoltaic power generation system according to the embodiment of the present invention, such a problem is solved by the following configuration and operation.

[ configuration of Power Generation State determination System 301 ]

Fig. 5 is a diagram showing the configuration of a power generation state determination system according to an embodiment of the present invention.

Referring to fig. 5, a photovoltaic power generation system 401 includes a power generation state determination system 301. The power generation state determination system 301 includes a determination device 101, a plurality of monitoring devices 111, and a collection device 151.

Fig. 5 representatively shows 4 monitoring devices 111 provided corresponding to 1 power collecting means 60, and a plurality of or a small number of monitoring devices 111 may be provided. Further, the power generation state determination system 301 includes 1 collection device 151, but may include a plurality of collection devices 151.

In the power generation state determination system 301, information of the sensor in the monitoring device 111 as the slave unit is transmitted to the collection device 151 periodically or aperiodically.

The monitoring device 111 is provided in the current collecting means 60, for example. More specifically, 4 monitoring devices 111 are provided corresponding to the 4 solar cells 74, respectively. Each monitoring device 111 is electrically connected to, for example, the corresponding output line 1 and the corresponding bus line 5.

The monitoring device 111 measures the current of each output line 1 in the corresponding solar cell 74 using a sensor. The monitoring device 111 measures the voltage of each output line 1 in the corresponding solar cell 74 by using a sensor.

The collection device 151 is disposed, for example, in the vicinity of the PCS 8. More specifically, the collection device 151 is provided corresponding to the PCS8, and is electrically connected to the copper bar 7 via the signal line 46.

The monitoring device 111 and the collection device 151 perform Power Line Communication (PLC) via the collection lines 2 and 5, and thereby transmit and receive information.

More specifically, each monitoring device 111 transmits monitoring information indicating the measurement results of the current and voltage of the corresponding output line. The collecting device 151 collects the measurement results of the monitoring devices 111.

[ constitution of monitoring device 111 ]

Fig. 6 is a diagram showing a configuration of a monitoring device in the power generation state determination system according to the embodiment of the present invention. In fig. 6, the output lines 1, the collector lines 5 and the copper bars 77 are shown in more detail.

Referring to fig. 6, the output line 1 includes a positive side output line 1p and a negative side output line 1 n. The collection line 5 includes a positive electrode side collection line 5p and a negative electrode side collection line 5 n. The copper bar 77 includes a positive-side copper bar 77p and a negative-side copper bar 77 n.

Although not shown, the copper bar 72 in the collector box 71 shown in fig. 3 includes a positive-side copper bar 72p and a negative-side copper bar 72n corresponding to the positive-side collector line 5p and the negative-side collector line 5n, respectively.

The positive-side output line 1p has a 1 st end connected to the corresponding power generation unit 78 and a 2 nd end connected to the positive-side copper bar 77 p. The negative-side output line 1n has a 1 st end connected to the corresponding power generating section 78 and a 2 nd end connected to the negative-side copper bar 77 n.

The positive side collector line 5p has a 1 st end connected to the positive side copper bar 77p and a 2 nd end connected to the positive side copper bar 72p in the collector box 71. The negative side collector line 5n has a 1 st end connected to the negative side copper bar 77n and a 2 nd end connected to the negative side copper bar 72n in the collector box 71.

The monitoring device 111 includes a detection processing unit 11, 4 current sensors 16, a voltage sensor 17, and a communication unit 14. The monitoring device 111 may include a plurality of or a small number of current sensors 16 depending on the number of output lines 1.

The monitoring device 111 is provided in the vicinity of the power generation unit 78, for example. Specifically, the monitor 111 is installed inside the connection box 76 provided with, for example, a copper bar 77, and the copper bar 77 is connected to the output line 1 to be measured. Further, the monitoring device 111 may be provided outside the connection box 76.

The monitoring device 111 is electrically connected to the positive-side bus line 5p and the negative-side bus line 5n via, for example, a positive-side power supply line 26p and a negative-side power supply line 26n, respectively. Hereinafter, each of the positive power supply line 26p and the negative power supply line 26n is also referred to as a power supply line 26.

Each monitoring device 111 transmits monitoring information indicating a measurement result of the corresponding power generation unit 78 via the power line connected to itself and the collection device 151.

Specifically, the communication unit 14 of the monitoring device 111 can perform power line communication via a collection line with the collection device 151 that collects measurement results of the plurality of monitoring devices 111. More specifically, the communication unit 14 can receive the transmission information via the aggregation lines 2 and 5. Specifically, the communication unit 14 performs power line communication with the collection device 151 via the power line 26 and the trunk lines 2 and 5.

The detection processing unit 11 is set to generate monitoring information indicating the measurement results of the current and voltage of the corresponding output line 1, for example, every predetermined time.

The current sensor 16 measures the current of the output line 1. In more detail, the current sensor 16 is, for example, a current probe of a hall element type. The current sensor 16 measures the current flowing through the corresponding negative electrode side output line 1n using the electric power received from the power supply circuit, not shown, of the monitoring device 111, and outputs a signal indicating the measurement result to the detection processing unit 11. The current sensor 16 may measure a current flowing through the positive electrode side output line 1 p.

The voltage sensor 17 measures the voltage of the output line 1. More specifically, the voltage sensor 17 measures the voltage between the positive-side copper bar 77p and the negative-side copper bar 77n, and outputs a signal indicating the measurement result to the detection processing unit 11.

The detection processing unit 11 converts, for example, signals obtained by averaging and filtering the measurement signals received from the current sensors 16 and the voltage sensor 17 into digital signals every predetermined time.

The detection processing unit 11 generates monitoring information including the measurement value indicated by each generated digital signal, the ID of the corresponding current sensor 16 (hereinafter also referred to as a current sensor ID), the ID of the voltage sensor 17 (hereinafter also referred to as a voltage sensor ID), and the ID of the own monitoring device 111 (hereinafter also referred to as a monitoring device ID).

The detection processing unit 11 generates a monitoring packet in which the transmission source ID is the own monitoring apparatus ID, the transmission destination ID is the ID of the collection apparatus 151, and the data portion is the monitoring information. Then, the detection processing unit 11 outputs the generated monitoring packet to the communication unit 14. The detection processing unit 11 may include a sequence number in the monitoring packet.

The communication unit 14 transmits the monitoring packet received from the detection processing unit 11 to the collection device 151.

Referring again to fig. 5, the collection device 151 can receive transmission information via the collection lines 2, 5. Specifically, the collection device 151 performs power line communication with the monitoring devices 111 via the signal lines 46 and the trunk lines 2 and 5, for example, and receives monitoring packets from the plurality of monitoring devices 111.

The collecting device 151 includes a counter and a storage unit, and when receiving a monitoring packet from the monitoring device 111, acquires monitoring information from the received monitoring packet and acquires the count value in the counter as the reception time. The collection device 151 stores the monitoring information in a storage unit, not shown, after the monitoring information includes the reception time.

[ constitution and operation of judging device ]

Fig. 7 is a diagram showing the configuration of a determination device in the power generation state determination system according to the embodiment of the present invention.

Referring to fig. 7, the determination device 101 includes a determination unit 81, a communication processing unit 84, a storage unit 85, and an acquisition unit 86. The determination unit 81 includes an evaluation unit 82 and a generation unit 83.

The storage unit 85 of the determination device 101 stores, for example, a monitoring device ID that is an ID of the monitoring device 111 to be managed. In addition, the storage unit 85 registers a correspondence R1 between the monitoring device ID and the current sensor ID and the voltage sensor ID, which are IDs of the sensors included in the monitoring device 111 having the monitoring device ID.

The determination device 101 is, for example, a server, periodically acquires monitoring information from the collection device 151, and processes the acquired monitoring information. The determination device 101 may be, for example, a configuration built in the collection device 151.

More specifically, the communication processing unit 84 in the determination device 101 transmits and receives information to and from other devices such as the collection device 151 via a network.

The communication processing unit 84 performs monitoring information collection processing at a predetermined daily processing timing, for example, 0 am of each day. Further, if the determination device 101 is built in the collection device 151, the monitoring information can be easily collected at shorter intervals.

More specifically, when the daily processing timing is reached, the communication processing unit 84 refers to each monitoring device ID registered in the storage unit 85, and transmits, to the collection device 151, a monitoring information request including monitoring information pertaining to a reception time from 24 hours before the daily processing timing to the daily processing timing (hereinafter, also referred to as a processing day), in association with each of the referred monitoring device IDs.

Upon receiving the monitoring information request from the determination device 101, the collection device 151 transmits 1 or more pieces of monitoring information satisfying the content of the monitoring information request to the determination device 101 in accordance with the received monitoring information request.

Fig. 8 is a diagram showing an example of monitoring information held by a determination device in the power generation state determination system according to the embodiment of the present invention.

Referring to fig. 8, when receiving 1 or more pieces of monitoring information from the collection device 151 as a response to the monitoring information request, the communication processing unit 84 calculates the generated power of each of the power generation units 78 based on the received monitoring information.

Specifically, the communication processing section 84 calculates the generated power for each current sensor ID by, for example, multiplying the current value for each power generation section 78, which is the current value for each current sensor ID included in the monitoring information including the calculated generated power for each current sensor ID, by the voltage value for 1 included in the monitoring information.

The communication processing unit 84 stores each piece of monitoring information after processing in the storage unit 85, and outputs a processing completion notification to the acquisition unit 86.

The acquisition unit 86 acquires time-series output data that is a measurement result of the output of the power generation unit 78.

More specifically, upon receiving the process completion notification from the communication processing unit 84, the acquisition unit 86 acquires time-series output data of the generated power (hereinafter also referred to as generated power data) from the storage unit 85 for each current sensor ID with reference to the correspondence relationship R1 registered in the storage unit 85.

Further, the acquisition section 86 may acquire time-series output data of the current value or the voltage value from the storage section 85 for each current sensor ID.

Fig. 9 is a diagram showing an example of the generated power data acquired by the acquisition unit in the determination device according to the embodiment of the present invention. In fig. 9, the horizontal axis represents time, and the vertical axis represents generated power.

The acquisition unit 86 acquires generated power data (hereinafter, also referred to as target data) of a period (hereinafter, also referred to as a target period) including a reception time belonging to a processing day and generated power data (hereinafter, also referred to as reference data) of a period (hereinafter, also referred to as a reference period) preceding the target period. The acquisition unit 86 outputs the acquired target data and reference data to the generation unit 83 in the determination unit 81. The target period and the reference period may partially overlap each other.

The determination unit 81 performs a determination process for determining an abnormality in the target data based on the reference data received from the acquisition unit 86.

For example, the determination section 81 uses an autoregressive model, statistical Analysis, Bayesian statistics, sparse structure learning, neural network, support vector machine, naive Bayes, k-nearest neighbor algorithm (kNN: k-nearest neighbor algorithm), decision Tree, C4.5, CART (Classification and Regression Tree: Classification and Regression Tree), stochastic forest, adaptive boosting (adaptive), bagging, hierarchical clustering, k-means (k-means), EM algorithm (expectation maximization algorithm), Latent Semantic Analysis (LSA: late Semantic Analysis), probabilistic Latent Semantic Analysis (PLSA: Latent Semantic Analysis), Linear Discriminant Analysis (LDA: Linear Discriminant Analysis), hierarchical Latent Lee Process (HDB: high probability Semantic Analysis), Linear Discriminant Analysis (LDA: Linear Discriminant Analysis), Latent Linear Discriminant Analysis (LDA: Latent Lei-Analysis), hierarchical Linear Discriminant Analysis (Linear Discriminant-Analysis), and Latent Linear Discriminant-Analysis (LDN: high probability Discriminant-probability Analysis), and Linear Discriminant model (LDC-Linear Discriminant-Analysis), and Linear Discriminant Analysis (LDN-Linear Discriminant-Analysis (L-mean) as), and Linear Discriminant Analysis, Hierarchical Bayes or self-organizing map (SOM) is used for the determination process.

[ example 1]

The determination device 101 performs determination processing using an autoregressive model.

More specifically, the generation unit 83 in the determination unit 81 predicts the generated power in the target period using the autoregressive model with respect to the reference data received from the acquisition unit 86, generates prediction data indicating the predicted generated power, and outputs the prediction data to the evaluation unit 82. The generation unit 83 also outputs the target data received from the acquisition unit 86 to the evaluation unit 82.

The evaluation unit 82 compares the prediction data received from the generation unit 83 with the target data, and evaluates an error of the target data with respect to the prediction data according to a predetermined method, thereby determining whether the target data is normal or abnormal.

More specifically, the evaluation unit 82 determines that the target data is normal when the error is smaller than a predetermined threshold value, and determines that the target data is abnormal when the error is equal to or larger than the threshold value.

[ example 2]

The determination device 101 performs determination processing using a neural network.

More specifically, the generation unit 83 of the determination unit 81 generates, for example, a learning data set including a plurality of normal generated power data for learning and a plurality of abnormal generated power data provided by a user.

Next, the generation unit 83 generates a classification model using the generated learning dataset.

Specifically, the generation unit 83 inputs the Learning data set to the neural network, for example, according to a Deep Learning (Deep Learning) method.

The generation unit 83 performs machine learning so that the neural network can be classified into normal generated power data or abnormal generated power data, thereby generating a classification model.

The generating unit 83 inputs the target data to the classification model having completed the machine learning, and obtains data with a classification result of whether the target data is normal generated power data or abnormal generated power data. The generation unit 83 then outputs the obtained data to the evaluation unit 82.

The evaluation unit 82 determines whether or not the target data is normal based on the data received from the generation unit 83.

[ example 3]

The determination device 101 performs determination processing using a support vector machine.

More specifically, the generation unit 83 in the determination unit 81 provides normal generated power data by a user, for example, and generates a group of normal generated power data (hereinafter, also referred to as a normal group) from reference data based on the provided generated power data.

The generation unit 83 provides abnormal generated power data by a user, for example, and generates a group of abnormal generated power data (hereinafter, also referred to as an abnormal group) from the reference data based on the provided generated power data.

The generating unit 83 sets, for example, generated power data close to the abnormal group among generated power data included in the normal group as normal feature data, and sets generated power data close to the normal group among generated power data included in the abnormal group as abnormal feature data.

The generation unit 83 calculates a determination condition indicating a boundary between the normal group and the abnormal group based on the normal feature data and the abnormal feature data, and outputs the calculated determination condition to the evaluation unit 82. The generation unit 83 also outputs the target data received from the acquisition unit 86 to the evaluation unit 82.

The evaluation unit 82 determines which of the normal group and the abnormal group the target data should belong to based on the determination condition received from the generation unit 83.

The evaluation unit 82 determines that the target data is normal when determining that the target data should belong to the normal group, and determines that the target data is abnormal when determining that the target data should belong to the abnormal group.

The generation unit 83 is configured to use a neural network or a support vector machine as supervised learning, but is not limited thereto. The generation unit 83 may be configured using a method of supervised learning such as C4.5, CART, a decision tree such as a random forest and a bag method, na iotave bayes, adaptive boosting, kNN, and the like.

[ example 4]

The determination device 101 performs determination processing using the k-means.

More specifically, the generating unit 83 in the determining unit 81 performs clustering using the waveform of the reference data and the waveform of the target data received from the acquiring unit 86, thereby generating N (N is an integer equal to or greater than 2) clusters into which the reference data and the target data are classified.

The generator 83 generates N, for example, 5, 7, 9, or 11 clusters using the k-means.

Fig. 10 is a diagram showing an example of 5 clusters for classifying reference data and target data in the determination device according to the embodiment of the present invention.

Fig. 10 shows the average values of the reference data and the target data classified into the respective clusters.

Referring to fig. 10, the generator 83 generates 5 clusters C51 to C55.

Fig. 11 is a diagram showing an example of 7 clusters that classify reference data in the determination device according to the embodiment of the present invention.

Referring to fig. 11, the generator 83 generates 7 clusters C71 to C77.

Fig. 12 is a diagram showing an example of 9 clusters that classify reference data in the determination device according to the embodiment of the present invention.

Referring to fig. 12, the generator 83 generates 9 clusters C91 to C99.

Fig. 13 is a diagram showing an example of 11 clusters that classify reference data in the determination device according to the embodiment of the present invention.

Referring to fig. 13, the generation unit 83 generates 11 clusters C101 to C111.

The generating unit 83 outputs cluster information indicating into which cluster the generated plurality of clusters and the target data are classified, to the evaluating unit 82.

The evaluation unit 82 identifies some of the received clusters as normal clusters, and identifies the remaining clusters as abnormal clusters.

The evaluation unit 82 identifies the cluster into which the target data is classified based on the received cluster information, determines the target data as normal if the target data is classified as a normal cluster, and determines the target data as abnormal if the target data is classified as an abnormal cluster.

For example, C53 is split into C73 and C75 for the 7 clusters shown in fig. 11 as compared to the 5 clusters shown in fig. 10.

In this way, by increasing the number of clusters classified, it is possible to detect an abnormality more finely, and it is possible to easily follow the cause of the abnormality.

The generator 83 is configured to use a k-average value as unsupervised learning, but is not limited thereto. The generating unit 83 may be configured to use an unsupervised learning method such as hierarchical clustering, EM algorithm, latent semantic analysis, probabilistic latent semantic analysis, linear discriminant analysis, hierarchical dirichlet process, latent dirichlet distribution method, k-center point method, and self-organizing map, for example.

The generation unit 83 may be configured to generate the determination condition using statistical analysis, bayesian statistics, or sparse structure learning. The generation unit 83 may use a method other than the above-described methods.

In addition, the determination device 101 may combine any of multiple methods of an autoregressive model, statistical analysis, bayesian statistics, sparse structure learning, a neural network, a support vector machine, naive bayes, a k-nearest neighbor algorithm, a decision tree, C4.5, CART, random forest, adaptive boosting, a bagging method, hierarchical clustering, k-means, an EM algorithm, probabilistic latent semantic analysis, linear discriminant analysis, HDP, latent dirichlet distribution, k-centroid method, generalized linear model, hierarchical bayes, and self-organizing map.

Specifically, for example, the generation unit 83 in the determination unit 81 performs clustering using the waveforms of the reference data and the target data received from the acquisition unit 86 to generate, for example, 5 clusters into which the reference data and the target data are classified, and generates a learning data set in which the generated clusters are used as normal generated power data and abnormal generated power data for learning.

[ flow of actions ]

Each device in the power generation state determination system 301 includes a computer, and an arithmetic processing unit such as a CPU in the computer reads and executes a program including a part or all of each step in the sequence diagram or flowchart described below from a memory not shown. The programs of these plural devices can be installed from the outside, respectively. The programs of these devices are distributed in a state of being stored in a recording medium.

Fig. 14 is a flowchart for determining the operation procedure when the determination device of the embodiment of the present invention determines an abnormality in the power generation unit.

Referring to fig. 14, the determination device 101 waits until the daily processing timing is reached (no in step S101).

When the daily processing timing is reached (yes in step S101), the determination device 101 receives the current value and the voltage value of each power generation unit 78 for the processing day from the collection device 151 (step S102).

Next, the determination device 101 calculates the generated power of the power generation unit 78 for each processing day based on the received current value and voltage value (step S103).

Next, the determination device 101 stores the target data, which is the time-series data of the generated power for each power generation unit 78 on the processing day, in the storage unit 85 with the date of the processing day (step S104).

Next, the determination device 101 acquires the reference data and the target data, which are past time-series data, from the storage unit 85 (step S105).

Next, the determination device 101 determines an abnormality of the target data by using an autoregressive model, machine learning, statistical analysis, bayesian statistics, sparse structure learning, or another method (step S106).

Next, the determination device 101 waits until a new daily processing timing is reached (step S101).

In the solar photovoltaic power generation system according to the embodiment of the present invention, the collection device 151 is connected to the PCS8 and configured to receive and transmit information from and to the monitoring device 111 and the determination device 101, but the present invention is not limited to this. The collection device 151 may be connected to the distribution box 6, the power collection unit 60, or the solar battery cell 74, and configured to transmit and receive information to and from the monitoring device 111 and the determination device 101.

In the solar photovoltaic power generation system according to the embodiment of the present invention, the determination device 101 may be a server alone, but is not limited thereto. The determination device 101 may be a cloud server.

In the solar photovoltaic power generation system according to the embodiment of the present invention, the target period is a period after the reference period, but the present invention is not limited thereto. The target period may be the same period as the reference period. In this case, the determination device 101 clusters a plurality of object data in an object period using, for example, hierarchical clustering, a k-center method, a k-means, a self-organization map, or the like, generates a plurality of clusters into which the plurality of object data are classified, and performs determination processing for determining an abnormality in the object data based on cluster information included in the generated clusters.

In the photovoltaic power generation system according to the embodiment of the present invention, the determination device 101 is used in the photovoltaic power generation system 401 including 1 or more junction boxes 76, 1 or more collector boxes 71, 1 or more power conversion devices 8, and the distribution box 6, but is not limited thereto. The determination device 101 may be used in a solar power generation system having a different configuration from the solar power generation system 401.

However, a technique that can improve the accuracy of abnormality determination of the photovoltaic power generation system over the technique described in patent document 1 is desired.

In the determination device according to the embodiment of the present invention, the acquisition unit 86 acquires the output data of the reference period and the output data of the target period, which are time-series output data of the measurement result of the output of the power generation unit 78. The determination unit 81 determines an abnormality of the output data in the target period based on the output data in the reference period acquired by the acquisition unit 86.

In this way, for example, by configuring to determine an abnormality based on time-series output data, which is a measurement result of the output of the power generation unit 78, without setting parameters of the natural environment such as air temperature, weather, and solar radiation amount as conditions, it is possible to detect an abnormality without providing a panel thermometer and a solar radiation amount. In addition, since the number of installed devices can be reduced and the number of times of visual confirmation can be reduced, the possibility of erroneous confirmation can be reduced.

Therefore, in the determination device according to the embodiment of the present invention, the accuracy of the abnormality determination of the photovoltaic power generation system can be improved.

In the determination device according to the embodiment of the present invention, the target period is a period after the reference period.

With this configuration, it is possible to more accurately determine an abnormality using output data accumulated in the past.

In the determination device according to the embodiment of the present invention, the determination unit 81 determines the abnormality of the output data using one or more of an autoregressive model, statistical analysis, bayesian statistics, sparse structure learning, a neural network, a support vector machine, naive bayes, a k nearest neighbor algorithm, a decision tree, C4.5, CART, a random forest, adaptive boosting, a bagging method, hierarchical clustering, k-means, an EM algorithm, latent semantic analysis, probabilistic latent semantic analysis, linear discriminant analysis, a hierarchical dirichlet process, a latent dirichlet distribution method, a k-centroid method, a generalized linear model, a linear model, hierarchical bayes, and self-organizing map.

According to such a configuration, it is possible to detect an abnormality more favorably using an autoregressive model, machine learning, statistical analysis, bayesian statistics, sparse structure learning, a generalized linear model, a linear model, hierarchical bayes, or other methods.

In the solar photovoltaic system 401 including the determination device according to the embodiment of the present invention, each of the 1 or more junction boxes 76 collects the output lines from the 1 or more power generation units 78. Each of the 1 or more header tanks 71 collects the collection lines from the 1 or more junction tanks 76. Each of the 1 or more power conversion devices 8 collects the collection lines from the 1 or more collection boxes 71. The distribution box 6 collects a collection line from 1 or more power conversion devices 8.

With such a configuration, since the output data can be collected at a desired location, it is possible to detect an abnormality for each power generation unit 78, each junction box 76, each power collection box 71, each power conversion device 8, or each power distribution box 6, and to improve the estimation of the cause of the abnormality.

In the solar photovoltaic power generation system according to the embodiment of the present invention, each of the 1 or more junction boxes 76 collects the output lines from the 1 or more power generation units 78. Each of the 1 or more header tanks 71 collects the collection lines from the 1 or more junction tanks 76. Each of the 1 or more power conversion devices 8 collects the collection lines from the 1 or more collection boxes 71. The distribution box 6 collects the collection lines from 1 or a plurality of the power conversion devices 8. The determination device 101 acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of the output of the power generation unit 78, and the determination device 101 determines an abnormality of the output data of the target period based on the acquired output data of the reference period.

In this way, for example, by configuring to determine an abnormality based on time-series output data, which is a measurement result of the output of the power generation unit 78, without setting parameters of the natural environment such as air temperature, weather, and solar radiation amount as conditions, it is possible to detect an abnormality without providing a panel thermometer and a solar radiation amount. In addition, since the number of installed devices can be reduced and the number of times of visual confirmation can be reduced, the possibility of erroneous confirmation can be reduced.

Therefore, in the solar photovoltaic power generation system according to the embodiment of the present invention, the accuracy of the abnormality determination of the solar photovoltaic power generation system can be improved.

In the determination method in the determination device according to the embodiment of the present invention, first, output data of a reference period and output data of a target period, which are time-series output data of a measurement result of the output of the power generation unit 78, are acquired. Then, based on the acquired output data of the reference period, an abnormality of the output data of the target period is determined.

In this way, for example, by configuring to determine an abnormality based on time-series output data, which is a measurement result of the output of the power generation unit 78, without setting parameters of the natural environment such as air temperature, weather, and solar radiation amount as conditions, it is possible to detect an abnormality without providing a panel thermometer and a solar radiation amount. In addition, since the number of times of visual confirmation can be reduced by reducing the number of devices to be installed, the possibility of erroneous confirmation can be reduced.

Therefore, in the determination method according to the embodiment of the present invention, the accuracy of the abnormality determination of the photovoltaic power generation system can be improved.

The above-described embodiments are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined not by the above description but by the appended claims, and is intended to include all changes which come within the meaning and range of equivalency of the claims.

The above description includes the features noted below.

[ additional notes 1]

A determination device used in a solar power generation system including a power generation unit including a solar cell, the determination device comprising: an acquisition unit that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit; and a determination unit configured to determine an abnormality of the output data in the target period based on the output data of the reference period acquired by the acquisition unit, wherein the power generation unit is a solar cell panel string in which a plurality of solar cell panels are connected in series, an output of the power generation unit is a generated power, a current, or a voltage of the power generation unit, the target period is 1 day, and the reference period is a period up to the day before the target period.

[ appendix 2]

A solar power generation system is provided with: 1 or more power generation sections including solar cells; 1 or a plurality of junction boxes, each junction box collecting output lines from 1 or a plurality of the power generation units; 1 or more header tanks, each header tank collecting a collection line from 1 or more of the junction tanks; 1 or a plurality of power conversion devices each of which collects a collection line from 1 or a plurality of the collection boxes; a power distribution cabinet that collects collection lines from 1 or a plurality of the power conversion devices; and a determination device that acquires output data of a reference period and output data of a target period, the output data being time-series output data of a measurement result of an output of the power generation unit, and determines an abnormality of the output data of the target period based on the acquired output data of the reference period, wherein the power generation unit is a solar cell panel string in which a plurality of solar cell panels are connected in series, the output of the power generation unit is generated power, current, or voltage of the power generation unit, the target period is 1 day, and the reference period is a period until the day before the target period.

Description of the reference numerals

1 output line

2. 4, 5 collecting line

3 inner wire

6 switch board

7 copper bar

8PCS

9 Power conversion unit

14 communication unit

16 current sensor

17 Voltage sensor

26 power cord

60 current collecting unit

71 current collecting box

72. 73, 77 copper bar

74 solar cell unit 76 junction box

78 Power generation part

80PCS unit 81 decision section

82 evaluation section

83 generating part

84 communication processing section 85 storage section

86 acquisition part

The 101 determining device 111 monitors the 151 collecting device 301 power generation state determining system 401 of the photovoltaic power generation system.