阅读说明：本技术 一种基于深度学习的非侵入式能耗监测系统及方法 (Non-invasive energy consumption monitoring system and method based on deep learning ) 是由 白易元 李远翼 周林路 刘长乐 于 2020-06-05 设计创作，主要内容包括：本发明实施例提供一种基于深度学习的非侵入式能耗监测系统及方法,该系统包括：非侵入式传感器、边缘计算设备、云端管理平台；所述非侵入式传感器用于实时采集负载电器的电参数,所述电参数包括电压数据、电流数据,并将所述电参数传输至所述边缘计算设备；所述边缘计算设备用于通过预设分析模型根据对所述电参数整体分析得到所述负载电器的能耗分析结果,将所述能耗分析结果发送至云端管理平台；所述云端管理平台用于对边缘计算设备上传数据进行集成,实现能耗统计、能源审计,并支持对所述边缘计算设备进行管理、升级,本方案能够有效地对能耗进行监测的同时,方便部署,并且能够进行深入分析。(The embodiment of the invention provides a non-invasive energy consumption monitoring system and a non-invasive energy consumption monitoring method based on deep learning, wherein the system comprises the following steps: the system comprises a non-invasive sensor, edge computing equipment and a cloud management platform; the non-invasive sensor is used for collecting the electrical parameters of the load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment; the edge computing equipment is used for obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model and sending the energy consumption analysis result to a cloud management platform; the cloud management platform is used for integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment.)

1. A deep learning based non-intrusive energy consumption monitoring system, comprising: the system comprises a non-invasive sensor, edge computing equipment and a cloud management platform;

the non-invasive sensor is used for collecting the electrical parameters of the load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment;

the edge computing equipment is used for obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model and sending the energy consumption analysis result to a cloud management platform;

the cloud management platform is used for integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment.

2. The non-intrusive energy consumption monitoring system of claim 1,

when the electric parameters which cannot be analyzed by the edge computing device exist, the electric parameters are sent to the cloud management platform;

the cloud management platform is further configured to: carrying out supervised feature labeling on the electrical parameters; and carrying out neural network training based on the labeling result to obtain a training model, and updating the training model to the edge computing equipment for remote upgrading.

3. The non-intrusive energy consumption monitoring system of claim 1,

the cloud management platform comprises: the system comprises a data interface module, a data center module, a business module and a training module;

the data interface module is used for being in communication connection with the edge computing equipment and receiving data sent by the edge computing equipment;

the data center is used for storing the data sent by the edge computing equipment;

the training module is used for marking and training the electrical parameters which cannot be identified by the edge computing equipment so as to obtain a new model to update a preset analysis model in the edge computing equipment.

4. The non-intrusive energy consumption monitoring system of claim 3,

the business module comprises a user management unit, a data statistics unit, an audit management unit and an alarm management unit;

the user management unit is used for performing user management operation of increasing, decreasing and updating on the user;

the data statistical unit is used for carrying out real-time energy consumption overall statistics and load individual statistics;

the audit management unit manages audit rules and checks audit results;

and the alarm management unit is used for setting and checking the energy consumption alarm.

5. The non-intrusive energy consumption monitoring system of claim 1,

a first WiFi module is arranged on the non-invasive sensor;

a second WiFi module is arranged on the edge computing equipment;

the first WiFi module is in communication connection with the second WiFi module.

6. The non-intrusive energy consumption monitoring system of any of claims 1 to 5,

the edge computing equipment is provided with a first mobile communication module;

the cloud management platform is provided with a second mobile communication module;

the first mobile communication module is in communication connection with the second mobile communication module.

7. The deep learning based non-invasive energy consumption monitoring method is applied to the deep learning based non-invasive energy consumption monitoring system according to any one of claims 1 to 6, and is characterized by comprising the following steps:

collecting electrical parameters of a load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment;

obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model, and sending the energy consumption analysis result to a cloud management platform;

and integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment.

Technical Field

The embodiment of the invention relates to the technical field of power grids, in particular to a non-invasive energy consumption monitoring system and method based on deep learning.

Background

Currently, an energy consumption monitoring system can be used for monitoring the power use conditions of enterprises, factories, schools, public buildings and the like in real time, and promoting units or individuals to improve the energy-saving operation management level through energy consumption statistics, energy audit, energy efficiency publicity and other means. There are generally two methods for monitoring power consumption: invasive and non-invasive. The intrusive method is characterized in that the energy consumption data are directly read by installing equipment such as an intelligent electric meter and the like in the power network. For non-invasive methods, prior art solutions include: 1. meter reading equipment: by installing additional equipment on the non-intelligent equipment (traditional electric meter), reading the electric meter reading by using a camera, and transmitting back to the server for analysis and monitoring. 2. Sensor pattern matching: and a non-invasive sensor is arranged on a line, data is read and then transmitted back to the server, and analysis is performed by methods such as pattern matching. The method supports the decomposition of energy consumption loads and identifies energy consumption details.

However, the prior art solutions have their drawbacks, 1. invasive: the method is suitable for newly-built projects, and the problems of high transformation difficulty, high cost, influence on normal operation and the like exist in the built building projects, so that the method is difficult to apply. 2. Meter reading equipment: the information of the traditional equipment is read through equipment such as a camera and the like, on one hand, the overall energy consumption condition of the coarse granularity can only be obtained, and deep analysis cannot be carried out; on the other hand, continuous monitoring and alarming are difficult to carry out. 3. The pattern matching method comprises the following steps: on one hand, the traditional sensor needs wired connection and is complex to deploy; on the other hand, the method needs to acquire a large amount of equipment electrical characteristic data in advance as a support, the identification accuracy is limited, and the implementation cost is high.

Therefore, how to provide an energy consumption monitoring method, which can effectively monitor the energy consumption, is convenient to deploy, and can perform deep analysis, is a technical problem to be solved urgently by technical personnel in the field.

Disclosure of Invention

Therefore, the embodiment of the invention provides a non-intrusive energy consumption monitoring system and method based on deep learning, which can effectively monitor energy consumption, facilitate deployment and perform deep analysis.

In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:

in one aspect, an embodiment of the present invention provides a deep learning-based non-intrusive energy consumption monitoring system, including: the system comprises a non-invasive sensor, edge computing equipment and a cloud management platform;

the non-invasive sensor is used for collecting the electrical parameters of the load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment;

the edge computing equipment is used for obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model and sending the energy consumption analysis result to a cloud management platform;

the cloud management platform is used for integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment.

Preferably, when the electrical parameters which cannot be analyzed by the edge computing device exist, the electrical parameters are sent to the cloud management platform;

the cloud management platform is further configured to: carrying out supervised feature labeling on the electrical parameters; and carrying out neural network training based on the labeling result to obtain a training model, and updating the training model to the edge computing equipment for remote upgrading.

Preferably, the cloud management platform includes: the system comprises a data interface module, a data center module, a business module and a training module;

the data interface module is used for being in communication connection with the edge computing equipment and receiving data sent by the edge computing equipment;

the data center is used for storing the data sent by the edge computing equipment;

the training module is used for marking and training the electrical parameters which cannot be identified by the edge computing equipment so as to obtain a new model to update a preset analysis model in the edge computing equipment.

Preferably, the service module comprises a user management unit, a data statistics unit, an audit management unit and an alarm management unit;

the user management unit is used for performing user management operation of increasing, decreasing and updating on the user;

the data statistical unit is used for carrying out real-time energy consumption overall statistics and load individual statistics;

the audit management unit manages audit rules and checks audit results;

and the alarm management unit is used for setting and checking the energy consumption alarm.

Preferably, a first WiFi module is disposed on the non-invasive sensor;

a second WiFi module is arranged on the edge computing equipment;

the first WiFi module is in communication connection with the second WiFi module.

Preferably, a first mobile communication module is arranged on the edge computing device;

the cloud management platform is provided with a second mobile communication module;

the first mobile communication module is in communication connection with the second mobile communication module.

On the other hand, an embodiment of the present invention provides a deep learning-based non-intrusive energy consumption monitoring method, which is applied to the deep learning-based non-intrusive energy consumption monitoring system, and includes:

collecting electrical parameters of a load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment;

obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model, and sending the energy consumption analysis result to a cloud management platform;

and integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment.

The embodiment of the invention provides a non-invasive energy consumption monitoring system and a non-invasive energy consumption monitoring method based on deep learning, wherein the system comprises the following steps: the system comprises a non-invasive sensor, edge computing equipment and a cloud management platform; the non-invasive sensor is used for collecting the electrical parameters of the load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment; the edge computing equipment is used for obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model and sending the energy consumption analysis result to a cloud management platform; the cloud management platform is used for integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment. The scheme has the characteristics of high precision and fine-grained energy consumption monitoring, and can identify the individual load energy consumption condition with high precision based on deep learning. Convenience and adaptability are improved. The non-invasive sensor does not need to modify the original power system, is convenient to install and is suitable for various scenes. The overall cost-to-price ratio is improved. The equipment is not required to be changed and installed, the line is not required to be laid, the energy consumption can be effectively monitored, the arrangement is convenient, and deep analysis can be carried out.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.

The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.

Fig. 1 is a schematic structural diagram of a deep learning-based non-intrusive energy consumption monitoring system according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a cloud management platform of a deep learning-based non-intrusive energy consumption monitoring system according to an embodiment of the present invention;

fig. 3 is a flowchart of a deep learning-based non-intrusive energy consumption monitoring method according to an embodiment of the present invention.

Detailed Description

The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1 and fig. 2, fig. 1 is a schematic structural diagram of a deep learning based non-intrusive energy consumption monitoring system according to an embodiment of the present invention; fig. 2 is a schematic structural diagram of a cloud management platform of a deep learning-based non-intrusive energy consumption monitoring system according to an embodiment of the present invention.

In a specific implementation manner of the present invention, an embodiment of the present invention provides a deep learning-based non-intrusive energy consumption monitoring system, including: the system comprises a non-invasive sensor, edge computing equipment and a cloud management platform; the non-invasive sensor is used for collecting the electrical parameters of the load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment; the edge computing equipment is used for obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model and sending the energy consumption analysis result to a cloud management platform; the cloud management platform is used for integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment.

Further, in practice, there may be electrical parameters that cannot be identified by the edge computing device, when a new type of load appliance is detected, and when there are electrical parameters that cannot be analyzed by the edge computing device, the electrical parameters are sent to the cloud management platform; the cloud management platform is further configured to: carrying out supervised feature labeling on the electrical parameters; and carrying out neural network training based on the labeling result to obtain a training model, and updating the training model to the edge computing equipment for remote upgrading. That is to say, when the edge computing device can not recognize, the electrical parameter data which can not be recognized are uploaded to the cloud management platform, and the cloud management platform carries out supervised feature labeling and training, so that a new recognition model of the load device is obtained, and the preset analysis model in the edge computing device can be updated.

Further, the cloud management platform comprises: the system comprises a data interface module, a data center module, a business module and a training module; the data interface module is used for being in communication connection with the edge computing equipment and receiving data sent by the edge computing equipment; the data center is used for storing the data sent by the edge computing equipment; the training module is used for marking and training the electrical parameters which cannot be identified by the edge computing equipment so as to obtain a new model to update a preset analysis model in the edge computing equipment.

Specifically, the service module comprises a user management unit, a data statistics unit, an audit management unit and an alarm management unit; the user management unit is used for performing user management operation of increasing, decreasing and updating on the user; the data statistical unit is used for carrying out real-time energy consumption overall statistics and load individual statistics; the audit management unit manages audit rules and checks audit results; and the alarm management unit is used for setting and checking the energy consumption alarm.

It should be noted that the non-invasive sensor is provided with a first WiFi module; a second WiFi module is arranged on the edge computing equipment; the first WiFi module is in communication connection with the second WiFi module. That is, the non-invasive sensor and the edge computing device communicate information via WiFi signals, but other wireless communication modules, such as bluetooth modules, may be used in practice.

The edge computing device and the cloud management platform are far away from each other, so that the edge computing device can communicate by using a mobile communication module, and particularly, the edge computing device is provided with a first mobile communication module; the cloud management platform is provided with a second mobile communication module; the first mobile communication module is in communication connection with the second mobile communication module. Specifically, mobile communication modules such as 2G \3G \4G \5G and the like can be used, and of course, other wired or wireless communication modes can be used for information transmission.

The embodiment of the invention provides a non-invasive energy consumption monitoring system and method based on deep learning. The non-invasive sensor does not need to reform transform original electric power system, and the installation is convenient, is applicable to various scenes, and wholeness price ratio improves, need not equipment and changes outfit, need not the circuit and lays, when can monitor the energy consumption effectively, convenient the deployment to can go on deep analysis.

Referring to fig. 3, fig. 3 is a flowchart of a deep learning based non-intrusive energy consumption monitoring method according to an embodiment of the present invention.

The embodiment of the invention provides a non-invasive energy consumption monitoring method based on deep learning, which is applied to the non-invasive energy consumption monitoring system based on deep learning and comprises the following steps:

step S31: collecting electrical parameters of a load electrical appliance in real time, wherein the electrical parameters comprise voltage data and current data, and transmitting the electrical parameters to the edge computing equipment;

step S32: obtaining an energy consumption analysis result of the load electric appliance according to the integral analysis of the electric parameters through a preset analysis model, and sending the energy consumption analysis result to a cloud management platform;

step S33: and integrating data uploaded by the edge computing equipment, realizing energy consumption statistics and energy audit, and supporting management and upgrading of the edge computing equipment.

The method in the embodiment of the present invention has been described in the above-mentioned non-intrusive energy consumption monitoring system based on deep learning, and will not be described herein again.

Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.