阅读说明：本技术 一种局部遮蔽条件下光伏阵列最大功率点跟踪方法 (Photovoltaic array maximum power point tracking method under local shielding condition ) 是由 雷勇 李云凤 王进武 王小昔 于 2021-07-14 设计创作，主要内容包括：本发明涉及光伏发电技术领域,其目的在于提供一种局部遮蔽条件下光伏阵列最大功率点跟踪方法,包括：启动光伏系统,在光伏阵列指定区域内均匀划分与对应光伏阵列连接的升压电路的占空比,得到占空比矩阵；根据光伏阵列输出的电压和电流,得到每只蚂蚁产生的信息素,并根据所有蚂蚁产生的信息素,得到所有蚂蚁的信息素矩阵；根据每只蚂蚁产生的信息素更新指定路径的信息素；根据信息素矩阵更新当前最大信息素,并根据占空比矩阵更新最大信息素处蚂蚁的位置；设定状态转移因子,并根据状态转移因子和每只蚂蚁产生的信息素得到当前蚂蚁的下一步前进位置,最后输出当前光伏阵列的全局最大功率。本发明可提高最大功率点追踪的准确度和速度。(The invention relates to the technical field of photovoltaic power generation, and aims to provide a photovoltaic array maximum power point tracking method under a local shielding condition, which comprises the following steps: starting a photovoltaic system, and uniformly dividing the duty ratio of a booster circuit connected with a corresponding photovoltaic array in a specified area of the photovoltaic array to obtain a duty ratio matrix; obtaining pheromones generated by each ant according to the voltage and the current output by the photovoltaic array, and obtaining pheromone matrixes of all ants according to the pheromones generated by all ants; updating pheromones of the appointed path according to the pheromones generated by each ant; updating the current maximum pheromone according to the pheromone matrix, and updating the position of ants at the maximum pheromone position according to the duty ratio matrix; and setting a state transfer factor, obtaining the next advancing position of the current ant according to the state transfer factor and the pheromone generated by each ant, and finally outputting the global maximum power of the current photovoltaic array. The invention can improve the accuracy and speed of maximum power point tracking.)

1. A method for tracking the maximum power point of a photovoltaic array under a local shading condition is characterized by comprising the following steps: the method comprises the following steps:

starting a photovoltaic system, uniformly dividing the duty ratio of a booster circuit connected with a corresponding photovoltaic array in a specified area of the photovoltaic array to obtain a duty ratio matrix, wherein the duty ratio matrix comprises a plurality of ants, and the positions of the ants are the duty ratios of the booster circuits connected with the corresponding photovoltaic array;

obtaining pheromones generated by each ant according to the voltage and the current output by the photovoltaic array, and obtaining pheromone matrixes of all ants according to the pheromones generated by all ants;

updating pheromones of the appointed path according to the pheromones generated by each ant;

updating the current maximum pheromone according to the pheromone matrix, and updating the position of ants at the maximum pheromone position according to the duty ratio matrix;

and setting a state transfer factor, obtaining the next advancing position of the current ant according to the state transfer factor and the pheromone generated by each ant, and finally outputting the global maximum power of the current photovoltaic array.

2. The method according to claim 1, wherein the method comprises the following steps: the initial position of the ith ant in the duty ratio matrix isWherein the content of the first and second substances,is the minimum value of the duty cycle of the boost circuit,is the maximum value of the duty ratio of the booster circuit, Ant is the total number of ants, i is [1, Ant]An integer within.

3. The method according to claim 1, wherein the method comprises the following steps: updating the pheromone of the designated path according to the pheromone generated by each ant, comprising the following steps:

establishing an pheromone diffusion model according to the pheromone generated by each ant;

and updating the pheromone of the specified path according to the pheromone diffusion model.

4. The method of claim 3, wherein the method comprises the following steps: the pheromone diffusion model isWherein x is any position in the designated path, b represents the current ant position, c is standard deviation representing pheromone diffusion capacity, and f (x) represents the pheromone concentration of the ants at the position b diffusing to the position x.

5. The method of claim 4, wherein the method comprises the following steps: the pheromone of the specified path is y_k+1＝y_k-ρ*f₁+ρ*f₂Wherein f is₂Is the pheromone diffusion model of the current ant, f₁For the pheromone diffusion model of the current ant after the last pheromone update, y_kIndicating the amount of information, y, of all paths after the k-th update of the pheromone_k+1Representing the information content of all paths after the (k +1) th pheromone updating, wherein the k value range is [1, Ant × Iter _ max]Iter _ max is the maximum iteration number, rho is the pheromone volatility coefficient, and rho belongs to [0,1 ]]。

6. The method according to claim 1, wherein the method comprises the following steps: setting a state transfer factor, obtaining the next advancing position of the current ant according to the state transfer factor and the pheromone generated by each ant, and finally outputting the global maximum power of the current photovoltaic array, wherein the state transfer factor comprises the following steps:

setting a state transition factor P₀；

Judging whether pheromone p generated by any ant meets condition p<P₀If yes, determining the next forward position of the current ant based on a chemotaxis operation formula, and then entering the next step; if not, searching the next step forward position of the current ant in the global scope according to the pheromone of the specified path and the position of the ant at the maximum pheromone, and then entering the next step;

judging whether the current iteration times are smaller than a preset maximum iteration time or not; if yes, recording the pheromone generated by each ant again; if not, generating a PWM waveform required by the booster circuit by the ant position at the maximum pheromone position, and outputting the global maximum power of the current photovoltaic array.

7. The method of claim 6, wherein the method comprises the following steps: pheromone p generated by any ant satisfies condition p<P₀When the chemotaxis operation formula isWherein j is iteration frequency, theta (j) is the current position of the ant, theta (j +1) is the next position of the ant, and S_maxFor the initial step size, Iter _ max is the maximum number of iterations, λ_jIs in the swimming direction.

8. The method of claim 6, wherein the method comprises the following steps: pheromone p generated by any ant does not satisfy condition p<P₀Then, the next step advance position of the current ant is theta (j +1) ═ theta (j) +0.1 ·x_maxRand (1), where j is the iteration number, θ (j) is the current position of the ant, θ (j +1) is the next position of the ant, and x_maxRand (1) is a random function from 0 to 1, which is the position of the ant at the maximum pheromone.

Technical Field

The invention relates to the technical field of photovoltaic power generation, in particular to a method for tracking a maximum power point of a photovoltaic array under a local shielding condition.

Background

In practical application, a photovoltaic array in a photovoltaic system is shielded by cloud cover, dust and buildings, and is exposed to uneven illumination intensity, so that a local shielding problem is generated, and at the moment, as shown in fig. 1, an output power-voltage curve of the photovoltaic array has a multimodal characteristic, and a plurality of local peaks occur. In order to exert the maximum efficacy of the photovoltaic system, an MPPT (maximum Power Point Tracking) method is usually adopted to track the maximum Power Point in the photovoltaic array in real time. Conventional MPPT methods such as a perturbation and observation method, a conductance increment method, and the like are prone to fall into a problem of a local maximum power point, so that a photovoltaic system has high power loss, and therefore the MPPT methods need to be optimized.

Aiming at the problem of local shading, the optimization of the MPPT method at present is divided into two modes of a topological structure and an algorithm. The photovoltaic module which is shielded needs to be compensated or array reconstructed according to the shadow condition by adopting the array topological structure optimization, but an additional hardware circuit needs to be added for realizing the compensation or the array reconstruction, so that the system cost is high, and the control is more complex. The optimization of the control algorithm is divided into a composite algorithm, a fuzzy control algorithm, a prediction algorithm, a bionic algorithm and the like, wherein the composite algorithm based on the traditional MPPT method has longer optimization time, and the optimization precision is greatly influenced by the step length; the fuzzy control algorithm has higher requirements on the controller and less practical application; based on a prediction algorithm of big data, an objective function of the prediction algorithm possibly falls into a local extreme point due to insufficient training data, the consideration on sudden shadow shielding is less, and the calculation amount is larger; the bionic algorithm based on the biological behaviors in the nature is the most popular algorithm at present due to the good optimizing performance of the bionic algorithm.

However, the biomimetic algorithm risks getting stuck in local peak points and converges slowly. The global development and the local exploration are crucial to the speed and the accuracy of the bionic algorithm, the global development capability is too strong, the bionic algorithm is not easy to fall into a local peak point, and the algorithm is too slow in convergence; the strong local exploration capability enables the algorithm to be rapidly converged, but the problem of increased risk of local peak points is easily caused. Therefore, how to reasonably enhance the global development capability and the local exploration capability to realize the purpose of quickly and accurately tracking the global maximum power point under the local shielding so as to improve the power generation efficiency is a technical problem to be solved at present.

Disclosure of Invention

The invention aims to solve the technical problems to a certain extent, and provides a photovoltaic array maximum power point tracking method under a local shielding condition.

The technical scheme adopted by the invention is as follows:

a method for tracking the maximum power point of a photovoltaic array under a local shading condition is characterized by comprising the following steps: the method comprises the following steps:

starting a photovoltaic system, uniformly dividing the duty ratio of a booster circuit connected with a corresponding photovoltaic array in a specified area of the photovoltaic array to obtain a duty ratio matrix, wherein the duty ratio matrix comprises a plurality of ants, and the positions of the ants are the duty ratios of the booster circuits connected with the corresponding photovoltaic array;

obtaining pheromones generated by each ant according to the voltage and the current output by the photovoltaic array, and obtaining pheromone matrixes of all ants according to the pheromones generated by all ants;

updating pheromones of the appointed path according to the pheromones generated by each ant;

updating the current maximum pheromone according to the pheromone matrix, and updating the position of ants at the maximum pheromone position according to the duty ratio matrix;

and setting a state transfer factor, obtaining the next advancing position of the current ant according to the state transfer factor and the pheromone generated by each ant, and finally outputting the global maximum power of the current photovoltaic array.

Preferably, the initial position of the ith ant in the duty ratio matrix isWherein the content of the first and second substances,is the minimum value of the duty cycle of the boost circuit,is the maximum value of the duty ratio of the booster circuit, Ant is the total number of ants, iIs [1, Ant]An integer within.

Preferably, the updating of the pheromone of the designated path according to the pheromone generated by each ant comprises:

establishing an pheromone diffusion model according to the pheromone generated by each ant;

and updating the pheromone of the specified path according to the pheromone diffusion model.

Further, the pheromone diffusion model isWherein x is any position in the designated path, b represents the current ant position, c is standard deviation representing pheromone diffusion capacity, and f (x) represents the pheromone concentration of the ants at the position b diffusing to the position x.

Further, the pheromone of the specified path is y_k+1＝y_k-ρ*f₁+ρ*f₂Wherein f is₂Is the pheromone diffusion model of the current ant, f₁For the pheromone diffusion model of the current ant after the last pheromone update, y_kIndicating the amount of information, y, of all paths after the k-th update of the pheromone_k+1Representing the information content of all paths after the (k +1) th pheromone updating, wherein the k value range is [1, Ant × Iter _ max]Iter _ max is the maximum iteration number, rho is the pheromone volatility coefficient, and rho belongs to [0,1 ]]。

Preferably, the setting of the state transition factor, obtaining a next advancing position of the current ant according to the state transition factor and the pheromone generated by each ant, and finally outputting the global maximum power of the current photovoltaic array comprises:

setting a state transition factor P₀；

Judging whether pheromone p generated by any ant meets condition p<P₀If yes, determining the next forward position of the current ant based on a chemotaxis operation formula, and then entering the next step; if not, searching the next step forward position of the current ant in the global scope according to the pheromone of the specified path and the position of the ant at the maximum pheromone, and then entering the next step;

judging whether the current iteration times are smaller than a preset maximum iteration time or not; if yes, recording the pheromone generated by each ant again; if not, generating a PWM waveform required by the booster circuit by the ant position at the maximum pheromone position, and outputting the global maximum power of the current photovoltaic array.

Further, pheromone p generated by any ant meets condition p<P₀When the chemotaxis operation formula isWherein j is iteration frequency, theta (j) is the current position of the ant, theta (j +1) is the next position of the ant, and S_maxFor the initial step size, Iter _ max is the maximum number of iterations, λ_jIs in the swimming direction.

Further, pheromone p generated by any ant does not satisfy condition p<P₀When the current ant has a next carry position of θ (j +1) ═ θ (j) +0.1 · x_maxRand (1), where j is the iteration number, θ (j) is the current position of the ant, θ (j +1) is the next position of the ant, and x_maxRand (1) is a random function from 0 to 1, which is the position of the ant at the maximum pheromone.

The invention has the beneficial effects that: the accuracy and speed of maximum power point tracking can be improved. Specifically, an pheromone mechanism of the ant colony algorithm enables the ant colony algorithm to have strong global capability, but mutual influence among ant colonies is ignored, an pheromone diffusion model is introduced on the basis of the ant colony algorithm, ants at the current position can influence pheromones generated by other ants from near to far, so that the global development capability of the bionic algorithm is enhanced, and the maximum power point tracking method in the invention is not easy to fall into a local peak point; in the local exploration stage, the ant is endowed with self-adaptive chemotaxis operation, so that the maximum power point tracking method has stronger local exploration capability, and the invention introduces global development and local exploration of a polymorphic ant colony concept balance algorithm, thereby reducing the risk of trapping into a local peak point and simultaneously improving the convergence rate. The maximum power point tracking method provided by the invention realizes the fusion of an ant colony algorithm and a bacterial foraging algorithm, achieves the effect of advantage complementation, improves the tracking accuracy through the pheromone diffusion model, increases the tracking speed of the maximum power point tracking method, reduces the optimization time, improves the tracking precision, and finally realizes the fast and accurate tracking of the global maximum power point under the partial shielding condition, improves the impact of photovoltaic output current on the system, is beneficial to reducing the loss of a photovoltaic system, and improves the photovoltaic power generation efficiency.

Drawings

FIG. 1 is a graph of output power versus voltage for a photovoltaic array under partial shading;

FIG. 2 is a schematic flow diagram of PACO-BFOA;

FIG. 3 is a detailed flow chart of PACO-BFOA;

FIG. 4 is a structural diagram of a method for realizing MPPT of a photovoltaic system by using PACO-BFOA;

FIG. 5 is a detail of FIG. 4;

FIG. 6 is a graph showing the output power curves of the photovoltaic array under the condition of constant illumination, PACO-BFOA, ACO, BFOA and disturbance observation methods;

FIG. 7 is a diagram of the output power curves of the photovoltaic array by PACO-BFOA, ACO, BFOA and disturbance observation under the condition of sudden illumination change;

FIG. 8 is a graph showing the output power curves of the photovoltaic array under the condition of slow change of illumination, PACO-BFOA, ACO, BFOA and disturbance observation methods;

fig. 9 is a block diagram of an electronic device according to the present invention.

Detailed Description

The invention is further described with reference to the following figures and specific embodiments.

It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.

Example 1:

the present embodiment provides a method for tracking a maximum power point of a photovoltaic array under a local shading condition, that is, PACO-BFOA (Polymorphic Ant Colony-Bacterial forming Algorithm), as shown in fig. 2 to 3, the method for tracking a maximum power point of a photovoltaic array in the present embodiment includes the following steps:

s1, starting a photovoltaic system, in order to improve the searching speed of a maximum power point tracking method, needing to know the distribution of pheromones more comprehensively, and uniformly dividing the duty ratio of a booster circuit connected with a corresponding photovoltaic array in a specified area of the photovoltaic array to obtain a duty ratio matrix X, wherein the duty ratio matrix X comprises a plurality of ants, and the positions of the ants are the duty ratios of the booster circuits connected with the corresponding photovoltaic array; wherein the initial position of the ith ant in the duty ratio matrix X is Is the minimum value of the duty cycle of the boost circuit,is the maximum value of the duty ratio of the booster circuit, Ant is the total number of ants, i is [1, Ant]An integer within;

specifically, if the number of ants is set to be 5, duty ratio division is carried out on the specified area (0,1) of the photovoltaic array, and the obtained duty ratio matrix X is [0.9950,0.7475,0.5000,0.2525,0.0050 ];

s2, obtaining pheromone P generated by each ant according to the voltage and the current output by the photovoltaic array, and obtaining pheromone matrixes P of all ants according to the pheromone P generated by all the ants; wherein, the output power corresponding to the position of each ant is pheromone p generated by the ant at the current position;

s3, updating pheromones of the appointed path according to the pheromone p generated by each ant;

the specific steps of step S3 are as follows:

s301, establishing an pheromone diffusion model according to pheromone p generated by each antWherein x is any position in the designated path, b represents the current ant position, c is a standard deviation representing pheromone diffusion capacity, and f (x) represents the pheromone concentration of the ants at the position b diffusing to the position x;

s302, updating pheromone y of the designated path according to the pheromone diffusion model_k+1＝y_k-ρ*f₁+ρ*f₂Wherein f is₂Is the pheromone diffusion model of the current ant, f₁For the pheromone diffusion model of the current ant after the last pheromone update, y_kIndicating the amount of information, y, of all paths after the k-th update of the pheromone_k+1Representing the information content of all paths after the (k +1) th pheromone updating, wherein the k value range is [1, Ant × Iter _ max]Iter _ max is the maximum iteration number, rho is the pheromone volatility coefficient, and rho belongs to [0,1 ]]；

S4, updating the current maximum pheromone P according to the pheromone matrix P_max＝p_i＝max[p₁,p₂,…,p_Ant]And updating the position X of the ant at the maximum pheromone position according to the duty ratio matrix X_max＝x_i；

S5, setting a state transfer factor P₀And according to the state transition factor P₀And pheromone p generated by each ant obtains the next advancing position of the current ant, and finally the global maximum power of the current photovoltaic array is output;

the specific steps of step S5 are as follows:

s501, setting a state transfer factor P₀；

S502, judging whether pheromone p generated by any ant meets condition p<P₀If yes, judging the current ant as a scout ant, needing to assist local search through chemotaxis behavior and based on chemotaxis operation formulaDetermining the next step forward position of the current ant, wherein j is the iteration number, theta (j) is the current position of the ant, theta (j +1) is the next step position of the ant, and S_maxFor the initial step size, Iter _ max is the maximum number of iterations, maxThe large number of iterations Iter _ max is empirically derived, λ_jThe direction of the swimming is the direction of the swimming, and then the next step is carried out; if not, judging that the current ant is a search ant, carrying out global development, and according to the pheromone of the specified path and the position x of the ant at the maximum pheromone position_max＝x_iSearching the next step forward position theta (j +1) of the current ant in the global scope, wherein theta (j) +0.1 x_maxRand (1), where rand (1) is a random function from 0 to 1, and then going to the next step;

s503, judging whether the current iteration number is smaller than a preset maximum iteration number, namely judging whether the current iteration number Iter meets the condition Iter is smaller than Iter _ max; if yes, recording the pheromone p generated by each ant again, and continuing iteration; if not, the ant position x at the maximum pheromone is determined_maxAnd generating a PWM waveform required by the booster circuit, and outputting the current global maximum power of the photovoltaic array, namely outputting the optimal output duty ratio of the global maximum power point of the photovoltaic system.

The point tracking method in this embodiment is implemented based on the circuit structure shown in fig. 4, and fig. 5 is a specific structure shown in fig. 4, and mainly includes a photovoltaic module, a boost circuit, and a MPPT controller PACO-BFOA, where the PACO-BFOA inputs a voltage and a current of the photovoltaic module, the output is a duty ratio instruction, and a pulse width modulation module obtains a switching signal to control on/off of an insulated gate bipolar transistor, thereby changing the load size, changing the output power of the photovoltaic module, and finally finding the maximum output power.

The embodiment can improve the accuracy and speed of maximum power point tracking. Specifically, an pheromone mechanism of the ant colony algorithm enables the ant colony algorithm to have strong global capability, but mutual influence among ant colonies is ignored, and an pheromone diffusion model is introduced on the basis of the ant colony algorithm, so that the ants at the current position can influence pheromones generated by other ants from near to far, the global development capability of the bionic algorithm is enhanced, and the maximum power point tracking method in the embodiment is not easy to fall into a local peak point; in the local exploration stage, the ant is endowed with self-adaptive chemotaxis operation, so that the maximum power point tracking method has stronger local exploration capability, and the embodiment introduces global development and local exploration of a polymorphic ant colony concept balance algorithm, thereby reducing the risk of sinking into a local peak point and improving the convergence rate. The maximum power point tracking method provided by the invention realizes the fusion of an ant colony algorithm and a bacterial foraging algorithm, achieves the effect of advantage complementation, improves the tracking accuracy through the pheromone diffusion model, increases the tracking speed of the maximum power point tracking method, reduces the optimization time, improves the tracking precision, and finally realizes the fast and accurate tracking of the global maximum power point under the partial shielding condition, improves the impact of photovoltaic output current on the system, is beneficial to reducing the loss of a photovoltaic system, and improves the photovoltaic power generation efficiency.

The effectiveness and excellent performance of the maximum power tracking method of this embodiment are further illustrated by the simulation results of ACO (Ant Colony Optimization), BFOA (Bacterial Foraging Algorithm) and PACO-BFOA (Polymorphic Ant Colony-Bacterial Foraging Algorithm) under 3 conditions of constant, abrupt, and slow change of illumination as follows:

TABLE 13 bionic algorithm convergence time comparison (optimum bolder) (unit: s)

TABLE 23 bionic algorithm Power oscillation conditions (optimum value bolded)

It should be noted that ACO simulates natural ant foraging behavior to generate pheromone to form a positive feedback mechanism, so as to realize optimal path foraging; BFOA simulates the behavior of escherichia coli, and the optimal behavior is found through three basic behaviors of chemotaxis, propagation and migration; in the embodiment, the PACO-BFOA carries out algorithm fusion on the ACO and the BFOA to realize advantage complementation, and a pheromone diffusion mechanism is added to further improve the global development capability of the algorithm.

Tables 1 and 2 show simulation data of time scales and power oscillation angles of different MPPT methods under the same test platform, wherein power indexesRepresenting the mean oscillation of the power curve, power indexMaximum oscillation of the characteristic power curve, t is the current running time, P_out(T) is the system output power at time T, T is the total system running time,and the average value of the power output by the photovoltaic array in the iterative process of the algorithm is shown.

Under the condition of constant illumination, the photovoltaic modules are respectively at 1000W/m²、800W/m²、600W/m²And 400W/m²The illumination amplitude of the light source is unchanged;

under the condition of illumination mutation, the illumination intensity of 0s-0.5s is 1000W/m²、800W/m²、600W/m²And 400W/m²At 0.5s, the irradiance jump is 900W/m²、620W/m²、620W/m²And 400W/m²；

Under the condition of slow change of illumination, the simulation time is from initial t to t being 0.5s to t being 1.5s, and the solar irradiance is from 1000W/m²、800W/m²、600W/m²And 400W/m²Is gradually changed into 980W/m²、780W/m²、580W/m²And 380W/m²。

Specifically, as shown in fig. 6 to 8, the curves of the output power of the photovoltaic array are respectively PACO-BFOA, ACO, BFOA and disturbance observation (P & O) under the condition of constant illumination, sudden illumination and slow illumination change.

It can be seen from the data in Table 1 that the time required for the PACO-BFOA to converge to the optimum value is relatively minimal when the illumination is varied. As can be seen from Table 2, compared with other bionic algorithms, the power oscillation of the PACO-BFOA is small, and the system impact is small.

Example 2:

on the basis of embodiment 1, this embodiment discloses an electronic device, and this device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like. The electronic device may be referred to as a device for a terminal, a portable terminal, a desktop terminal, or the like, and as shown in fig. 9, the electronic device includes:

a memory for storing computer program instructions; and the number of the first and second groups,

a processor for executing the computer program instructions to perform the operations of the photovoltaic array maximum power point tracking method under partial shading conditions as described in any of embodiment 1.

In particular, the processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 301 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor, where the main processor is a processor for processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. The processor 301 may further include an AI (Artificial Intelligence) processor for processing computational operations related to machine learning such that the node coding model of the graph neural network can be trained autonomously for learning, improving efficiency and accuracy.

Memory 302 may include one or more computer-readable storage media, which may be non-transitory. Memory 302 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 302 is used to store at least one instruction for execution by the processor 801 to implement the node encoding method of the graph neural network provided by the method embodiments herein.

In some embodiments, the terminal may further include: a communication interface 303 and at least one peripheral device. The processor 301, the memory 302 and the communication interface 303 may be connected by a bus or signal lines. Various peripheral devices may be connected to communication interface 303 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 304, a display screen 305, and a power source 306.

The communication interface 303 may be used to connect at least one peripheral device related to I/O (Input/Output) to the processor 301 and the memory 302. In some embodiments, processor 301, memory 302, and communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302 and the communication interface 303 may be implemented on a single chip or circuit board, which is not limited in this embodiment.

The Radio Frequency circuit 304 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 304 communicates with communication networks and other communication devices via electromagnetic signals.

The display screen 305 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof.

The power supply 306 is used to power various components in the electronic device.

Example 3:

on the basis of any embodiment of embodiments 1 to 2, the present embodiment discloses a computer-readable storage medium for storing computer-readable computer program instructions, where the computer program instructions are configured to, when executed, perform the operation of the photovoltaic array maximum power point tracking method under the local shading condition according to embodiment 1.

It should be noted that the functions described herein, if implemented in software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.

The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: modifications of the technical solutions described in the embodiments or equivalent replacements of some technical features may still be made. And such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Finally, it should be noted that the present invention is not limited to the above alternative embodiments, and that various other forms of products can be obtained by anyone in light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.