Method for Evaluating the Power Supply Adequacy of a Solar Power Supply System for Cloudy and Rainy Days

Abstract

The present invention discloses a method for evaluating the power supply adequacy of a solar power supply system for rainy days, belonging to the field of power supply technology. It can monitor the operation status of the solar power supply system in real time and predict the electricity load in the solar power supply area at the same time, so as to accurately evaluate the power supply adequacy under rainy weather conditions, facilitate users to adjust their electricity demands according to the power supply adequacy results, and realize the optimal allocation of energy. It has the advantages of simple operation, strong practicability, wide application range, etc.

Description

Technical Field

[0001] The present invention belongs to the technical field of power supply, and particularly relates to a method for evaluating the power supply adequacy of a solar power supply system for rainy days. Background Art

[0002] A solar power supply system is a power generation system that converts solar energy into electrical energy using solar panels. The solar panels generate direct current under sunlight irradiation. The direct current is regulated by a controller. Part of it is used to directly supply power to DC loads, and the other part is used to charge a battery. When the electrical energy generated by the solar panels is insufficient to meet the load demand, the battery will discharge and supply power to the load through the controller. If the system is equipped with an inverter, the direct current can be converted into alternating current for use by AC loads or fed into the public power grid for grid connection. With the popularization of solar power generation technology, more and more solar power supply systems are applied in daily life. However, solar power generation is greatly affected by weather conditions. Especially in rainy weather, the power generation capacity of the solar power supply system drops significantly, resulting in unstable power supply. In the prior art, there is a lack of a method for evaluating the power supply adequacy of a solar power supply system under rainy weather conditions, making it impossible for users to accurately grasp the power supply situation on rainy days and affecting normal power consumption. Summary of the Invention

[0003] The present invention provides a method for evaluating the power supply adequacy of a solar power supply system for rainy days to solve the problem in the prior art that it is difficult to evaluate the power supply adequacy of a solar power supply system on rainy days.

[0004] A method for evaluating the power supply adequacy of a solar power supply system for rainy days includes:

[0005] Collecting the solar power supply impact factors and daily power supply under rainy day conditions, and using the GISA-BP algorithm to learn the solar power supply impact factors and daily power supply to determine the first prediction rule;

[0006] Collecting the regional power consumption characteristics and daily power consumption corresponding to the solar power supply area, and using the GISA-BP algorithm to learn the regional power consumption characteristics and daily power consumption to determine the second prediction rule;

[0007] Collecting the real-time solar power supply impact factors on rainy days, and using the first prediction rule to analyze the real-time solar power supply factors to determine the predicted solar power supply;

[0008] Collecting the real-time regional power consumption characteristics corresponding to the solar power supply area, and using the second prediction rule to analyze the real-time regional power consumption characteristics to determine the predicted regional power consumption;

[0009] According to the predicted solar power supply and the predicted power consumption in the area, evaluate the power supply adequacy of the solar power supply system on rainy and cloudy days to obtain the power supply adequacy evaluation result.

[0010] In a possible implementation manner, collect the solar power supply impact factors and the daily power supply under rainy and cloudy day conditions, including:

[0011] Collect the average temperature, daily temperature range, average relative humidity, average wind speed, sunshine duration, visibility, global horizontal radiation, global tilted radiation, diffuse horizontal radiation, and diffuse tilted radiation under rainy and cloudy day conditions to obtain the solar power supply impact factors;

[0012] Collect the daily power supply under rainy and cloudy day conditions.

[0013] In a possible implementation manner, use the GISA-BP algorithm to learn the solar power supply impact factors and the daily power supply to determine the first prediction rule, including:

[0014] Use the BP algorithm to create the first initial rule and initialize the parameters of the first initial rule to obtain the first parameter individual, and repeat to obtain multiple different first parameter individuals;

[0015] Form a vector of the solar power supply impact factors and use it as the input data of the first initial rule, and use the daily power supply corresponding to the solar power supply impact factors as the expected label to obtain the loss function value corresponding to each first parameter individual;

[0016] Determine the optimal first parameter individual according to the loss function value corresponding to each first parameter individual;

[0017] Based on the optimal first parameter individual, use the adaptive vibration-guided search strategy to update each first parameter individual to obtain the first parameter individual after vibration-guided search;

[0018] For the first parameter individual after vibration-guided search, use the adaptive local area search strategy to update each first parameter individual to obtain the first parameter individual after local area search;

[0019] For the first parameter individual after local area search, use the adaptive population cooperation search strategy to update each first parameter individual to obtain the first parameter individual after population cooperation search;

[0020] Repeat the above vibration-guided search, local area search, and population cooperation search until the number of training times reaches the maximum number of training times, re-obtain the optimal first parameter individual, and apply the parameters included in the optimal first parameter individual to the first initial rule to obtain the first prediction rule.

[0021] In a possible implementation manner, based on the optimal first-parameter individual, an adaptive vibration-guided search strategy is adopted to update each first-parameter individual, and the first-parameter individual after vibration-guided search is obtained, including:

[0022] Based on the current training times, the adaptive decay factor is determined as:

[0023]

[0024] where z t represents the adaptive decay factor in the t-th training process, z max represents the maximum value corresponding to the adaptive decay factor, z min represents the minimum value corresponding to the adaptive decay factor, e represents the natural constant, and T represents the maximum number of training times;

[0025] According to the adaptive decay factor, the first adaptive vibration-guided coefficient and the second adaptive vibration-guided coefficient are obtained as:

[0026] α1 = 2z t r1 - z t

[0027] α2 = kz t r2 + 1

[0028] where α1 represents the first adaptive vibration-guided coefficient, r1 represents the first random number between (0, 1), α2 represents the second adaptive vibration-guided coefficient, k represents the natural constant quantity, and r2 represents the second random number between (0, 1);

[0029] Generate a third random number r3 between (0, 1), and determine whether the third random number r3 is less than the first decision probability. If so, based on the optimal first-parameter individual, and according to the first adaptive vibration-guided coefficient and the second adaptive vibration guidance, perform the first vibration-guided search on the first-parameter individual to obtain the first-parameter individual after vibration-guided search. Otherwise, based on the optimal first-parameter individual, and according to the first adaptive vibration-guided coefficient and the second adaptive vibration guidance, perform the second vibration-guided search on the first-parameter individual;

[0030] Performing the first vibration-guided search on the first-parameter individual based on the optimal first-parameter individual and according to the first adaptive vibration-guided coefficient and the second adaptive vibration guidance is:

[0031]

[0032] where represents the i-th first-parameter individual in the t-th training process, i = 1, 2,..., I, and I represents the total number of first-parameter individuals, Denote the optimal first-parameter individual, Denote the first-parameter individual after vibration-guided search

[0033] Based on the optimal first-parameter individual, and according to the first adaptive vibration-guided coefficient and the second adaptive vibration guidance, the second vibration-guided search for the first-parameter individual is as follows:

[0034]

[0035] where, π represents the pi, cos represents the cosine function, and sin represents the sine function.

[0036] In a possible implementation, for the first-parameter individual after vibration-guided search, an adaptive local region search strategy is adopted to update each first-parameter individual, and the first-parameter individual after local region search is obtained, including:

[0037] Based on the current training times, determine the adaptive local exploitation factor as:

[0038] p = (1 - t / T) t / T

[0039] where, p represents the adaptive local exploitation factor;

[0040] For the first-parameter individual after vibration-guided search, generate a fourth random number r4 between (0, 1), and determine whether the fourth random number r4 is less than the second decision probability. If so, perform the first local region search on the first-parameter individual to obtain the first-parameter individual after local region search; otherwise, perform the second local region search on the first-parameter individual to obtain the first-parameter individual after local region search;

[0041] The first local region search for the first-parameter individual is as follows:

[0042]

[0043] where, Denote the first-parameter individual after the nth vibration-guided search, n = 1, 2,..., I, r5 represents a fifth random number between (0, 1), and F represents a random quantity between [-1, 1];

[0044] The second local region search for the first-parameter individual is as follows:

[0045]

[0046] where, Denote the first-parameter individual after local region search

[0047] In a possible implementation, for the first parameter individuals after local region search, an adaptive population cooperation search strategy is adopted to update each first parameter individual to obtain the first parameter individuals after population cooperation search, including:

[0048] Based on the current training times, determine the adaptive cooperation factor as:

[0049]

[0050] where, represents the adaptive cooperation factor corresponding to the m-th first parameter individual after local region search in the t-th training process, β0 represents the first preset constant, represents the intermediate coefficient corresponding to the m-th first parameter individual after local region search, m = 1, 2, …, I, ξ max represents the maximum value corresponding to the intermediate coefficient, ξ max represents the minimum value corresponding to the intermediate coefficient, represents the fitness value corresponding to the m-th first parameter individual after local region search, represents the minimum fitness value among the first parameter individuals after local region search, represents the average fitness value among the first parameter individuals after local region search; the fitness value is obtained by taking the reciprocal after adding the loss function value and the second preset constant;

[0051] For the m-th first parameter individual after local region search, according to the adaptive cooperation factor, determine the cooperation influence of all other first parameter individuals on the first parameter individual as:

[0052]

[0053] where, represents the cooperation influence, r6 represents the sixth random number between (0, 1), represents the first parameter individual after the k-th local region search and the first parameter individual after the m-th local region search regarding the influence on the d-th dimension parameter, d = 1, 2, …, D, D represents the total dimension of the parameters of the first parameter individual, ε represents the second preset constant, and ε = 0.0001; represents the weight corresponding to the first parameter individual corresponding to, represents the weight corresponding to the first parameter individual corresponding to, and are obtained in the same way; represents the first parameter individual The d-th dimensional parameter of represents the first parameter individual The d-th dimensional parameter of represents the first parameter individual corresponding position superiority degree, represents the first parameter individual corresponding position superiority degree, f m represents the fitness value corresponding to the first parameter individual after the m-th local area search, f w represents the minimum fitness value in the first parameter individual after the local area search, f best represents the maximum fitness value in the first parameter individual after the local area search;

[0054] According to the collaborative influence and the weight determine the first parameter individual The collaborative influence term corresponding to the d-th dimensional parameter of is:

[0055] According to the first parameter individual The collaborative influence term corresponding to the d-th dimensional parameter of determine the first parameter individual The increment term corresponding to the d-th dimensional parameter of is:

[0056]

[0057] where represents the increment term corresponding to the d-th dimensional parameter of the first parameter individual during the t-th training process The increment term corresponding to the d-th dimensional parameter of represents the increment term corresponding to the d-th dimensional parameter of the first parameter individual during the (t + 1)-th training process, r7 represents the seventh random number between (0, 1), A1 represents the first constant between (0, 1), r8 represents the eighth random number between (-1, 1), represents the d-th dimensional parameter of the optimal first parameter individual, A2 represents the second constant between (0, 1), r9 represents the ninth random number between (-1, 1);

[0058] According to the increment term corresponding to the d-th dimensional parameter of the first parameter individual, update the first parameter individual to:

[0059]

[0060] where represents the d-th dimensional parameter of the first parameter individual after the population collaborative search

[0061] In a possible implementation manner, collecting the regional power consumption characteristics and daily power consumption corresponding to the solar power supply area, including:

[0062] Collecting the seasonal data, weather data, temperature data, and date type data of the power supply area to obtain the regional power consumption characteristics corresponding to the solar power supply area;

[0063] Collecting the daily power consumption corresponding to the regional power consumption characteristics;

[0064] Among them, the seasonal data includes spring, summer, autumn, or winter, the weather data includes rainy, sunny, cloudy, or snowy days, and the date type data includes weekdays or non-weekdays.

[0065] In a possible implementation manner, using the GISA-BP algorithm to learn the regional power consumption characteristics and daily power consumption to determine the second prediction rule, including:

[0066] Using the BP algorithm to create a second initial rule and initialize the parameters of the second initial rule to obtain a second parameter individual, and repeating to obtain multiple different second parameter individuals;

[0067] Forming the regional power consumption characteristics into a vector and using it as the input data of the second initial rule, and using the daily power consumption corresponding to the regional power consumption characteristics as the expected label to obtain the loss function value corresponding to each second parameter individual;

[0068] Determining the optimal second parameter individual according to the loss function value corresponding to each second parameter individual;

[0069] Based on the optimal second parameter individual, using an adaptive vibration-guided search strategy to update each second parameter individual to obtain the second parameter individual after vibration-guided search;

[0070] For the second parameter individual after vibration-guided search, using an adaptive local area search strategy to update each second parameter individual to obtain the second parameter individual after local area search;

[0071] For the second parameter individual after local area search, using an adaptive population cooperation search strategy to update each second parameter individual to obtain the second parameter individual after population cooperation search;

[0072] Repeatedly execute the above vibration-guided search, local area search, and population cooperation search until the number of training times reaches the maximum number of training times, re-obtain the optimal second parameter individual, and apply the parameters included in the optimal second parameter individual to the second initial rule to obtain the second prediction rule.

[0073] In a possible implementation manner, according to the predicted solar power supply amount and the predicted regional power consumption amount, the power supply adequacy of the solar power supply system on rainy and cloudy days is evaluated to obtain a power supply adequacy evaluation result, including:

[0074] Determine whether the difference obtained by subtracting the predicted regional power consumption amount from the predicted solar power supply amount is greater than a preset power supply adequacy threshold. If so, determine that the power supply adequacy evaluation result is sufficient power supply; otherwise, determine that the power supply adequacy evaluation result is insufficient power supply.

[0075] In a possible implementation manner, after evaluating the power supply adequacy of the solar power supply system on rainy and cloudy days, it further includes:

[0076] Determine whether the power supply adequacy evaluation result is of the insufficient type. If so, generate a warning of insufficient power supply and transmit the warning of insufficient power supply to the device or system designated by the staff; otherwise, repeatedly execute the method for evaluating the power supply adequacy of the solar power supply system.

[0077] A method for evaluating the power supply adequacy of a solar power supply system for rainy and cloudy days provided by the present invention can monitor the operating state of the solar power supply system in real time, and at the same time predict the power consumption load of the solar power supply area, so as to accurately evaluate the power supply adequacy under rainy and cloudy weather conditions, facilitate users to adjust their power consumption demands according to the power supply adequacy result, and achieve optimal energy allocation; it has the advantages of simple operation, strong practicability, wide application range, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0079] Figure 1 It is a flowchart of a method for evaluating the power supply adequacy of a solar power supply system for rainy and cloudy days provided by an embodiment of the present invention.

[0080] Figure 2 It is a flowchart of obtaining a first prediction rule provided by an embodiment of the present invention.

[0081] Figure 3 It is a flowchart of obtaining a second prediction rule provided by an embodiment of the present invention.

[0082] Through the above accompanying drawings, specific embodiments of the present invention have been shown, and there will be more detailed descriptions hereinafter. These drawings and written descriptions are not intended to limit the scope of the inventive concept in any way, but to illustrate the concept of the present invention to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0083] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of apparatuses and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0084] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0085] As Figure 1 shown, an embodiment of the present invention provides a method for evaluating the power supply adequacy of a solar power supply system for rainy and cloudy days, including:

[0086] S101. Collect the solar power supply impact factors and daily power supply under rainy and cloudy day conditions, and use the GISA-BP algorithm to learn the solar power supply impact factors and daily power supply to determine a first prediction rule;

[0087] In a possible implementation manner, collecting the solar power supply impact factors and daily power supply under rainy and cloudy day conditions includes: collecting the average temperature, daily temperature range, average relative humidity, average wind speed, sunshine duration, visibility, global horizontal radiation, global tilted radiation, diffuse horizontal radiation, and diffuse tilted radiation under rainy and cloudy day conditions to obtain the solar power supply impact factors; collecting the daily power supply under rainy and cloudy day conditions.

[0088] It should be noted that in addition to the above solar power supply impact factors, other impact factors can also be used for solar power generation prediction to make the solar power generation prediction more accurate.

[0089] The embodiment of the present invention constructs a prediction rule using the BP neural network algorithm, and after updating the parameters of the prediction rule using the GISA algorithm (Global Information Sharing Algorithm) provided by the embodiment of the present invention, a first prediction rule that can predict the solar power supply is obtained.

[0090] Optionally, in addition to predicting the solar power supply, the solar power generation power can also be predicted, and the power supply amount can be converted through the solar power generation power, so as to realize the prediction of the solar power supply amount.

[0091] S102. Collect the regional power consumption characteristics and daily power consumption corresponding to the solar power supply area, and use the GISA-BP algorithm to learn the regional power consumption characteristics and daily power consumption to determine a second prediction rule;

[0092] In a possible implementation, the regional electricity consumption characteristics and daily electricity consumption corresponding to the solar power supply area are collected, including: collecting seasonal data, weather data, temperature data, and date type data of the power supply area to obtain the regional electricity consumption characteristics corresponding to the solar power supply area; collecting the daily electricity consumption corresponding to the regional electricity consumption characteristics; wherein, the seasonal data includes spring, summer, autumn, or winter, the weather data includes rainy, sunny, cloudy, or snowy days, and the date type data includes weekdays or non-working days.

[0093] It should be noted that in addition to the above regional electricity consumption characteristics, other electricity consumption characteristics can also be adopted to make the prediction of regional electricity consumption more accurate.

[0094] To enable the technical personnel of the present invention to better understand the technical solutions described in the embodiments of the present invention, a simple description of using the GISA-BP algorithm to learn the regional electricity consumption characteristics and daily electricity consumption is as follows. It can include: assuming that the regional electricity consumption characteristics and daily electricity consumption for B days are collected, a vector can be constructed using the daily electricity consumption for C (C < B) days and the regional electricity consumption characteristics on the (C + 1)-th day to obtain input data, and the daily electricity consumption on the (C + 1)-th day is used as the expected input, and the GISA-BP algorithm is used for learning, thereby a second prediction rule can be obtained.

[0095] S103. Collect the real-time solar power supply impact factor on rainy and cloudy days, and analyze the real-time solar power supply factor using the first prediction rule to determine the predicted solar power supply;

[0096] Collect the real-time solar power supply impact factor on rainy and cloudy days, and construct the real-time solar power supply impact factor as the input of the first prediction rule, so as to predict the solar power supply.

[0097] S104. Collect the real-time regional electricity consumption characteristics corresponding to the solar power supply area, and analyze the real-time regional electricity consumption characteristics using the second prediction rule to determine the predicted regional electricity consumption;

[0098] Collect the real-time regional electricity consumption characteristics corresponding to the solar power supply area. The input data of the second prediction rule can be constructed in a training manner, and the input data of the second prediction rule is input into the second prediction rule, so as to predict the regional electricity consumption.

[0099] S105. According to the predicted solar power supply and the predicted regional electricity consumption, evaluate the power supply adequacy of the solar power supply system on rainy and cloudy days to obtain the power supply adequacy evaluation result.

[0100] When the predicted solar power supply is approximately equal to the general power consumption in the predicted area, it can be considered that the power supply is basically sufficient. However, the power consumption fluctuates. Therefore, a preset power supply adequacy threshold can be set. When the difference between the predicted solar power supply and the general power consumption in the predicted area is greater than the preset power supply adequacy threshold, it can be considered that the power supply demand is met.

[0101] Optionally, since a general solar power supply system is also provided with a storage battery, the power supply of the storage battery can also be considered to make the evaluation of power supply adequacy more accurate.

[0102] It should be noted that in order to ensure that the method for evaluating the power supply adequacy of a solar power supply system for rainy days provided by the embodiments of the present invention can achieve accurate evaluation of power supply adequacy, a large number of samples need to be used for data learning, and after the method is deployed, continuous learning of historical data can be carried out to correct the evaluation effect, so that the evaluation becomes more and more accurate.

[0103] The method for evaluating the power supply adequacy of a solar power supply system for rainy days provided by the present invention can monitor the operating state of the solar power supply system in real time, and at the same time predict the power load of the solar power supply area, so as to accurately evaluate the power supply adequacy under rainy weather conditions, facilitate users to adjust power consumption requirements according to the power supply adequacy results, and achieve optimal energy allocation; it has the advantages of simple operation, strong practicability, wide application range, etc.

[0104] In the existing deep learning process, in order to realize the learning of data relationships, intelligent optimization algorithms such as particle swarm optimization algorithms and genetic algorithms are often used to optimize the parameters of neural network algorithms, so as to realize data relationship learning. However, the intelligent optimization algorithms in the prior art often have problems such as poor training accuracy, slow training speed, and easy to fall into local optimum, usually resulting in poor data relationship learning ability, and finally it is difficult to achieve accurate evaluation of power supply adequacy. Therefore, the embodiments of the present invention provide a GISA-BP algorithm to solve the technical problems existing in the prior art, so as to achieve accurate evaluation of power supply adequacy.

[0105] As Figure 2 shown, and the GISA-BP (Global Information Sharing - Back Propagation) algorithm is used to learn the solar power supply influencing factors and the daily power supply, and a first prediction rule is determined, including:

[0106] S201. Use the BP algorithm to create a first initial rule and initialize the parameters of the first initial rule to obtain a first parameter individual, and repeat to obtain multiple different first parameter individuals;

[0107] In addition to constructing the first initial rule using the BP algorithm, other neural networks can also be used to construct the first initial rule. The parameters of the first initial rule can be initialized using a random initialization method or a chaotic mapping initialization method. In the embodiments of the present invention, the chaotic mapping initialization method is preferably used for initialization to make the initial solution more evenly distributed in the solution space, thereby improving the training speed of the algorithm.

[0108] The parameters of the first initial rule can be connection weights and / or thresholds, so that the first initial rule can perform data analysis and prediction.

[0109] S202. Combine the solar power supply impact factors into a vector and use it as the input data of the first initial rule. Use the daily power supply corresponding to the solar power supply impact factor as the expected label, and obtain the loss function value corresponding to each first parameter individual.

[0110] Obtaining the loss function value corresponding to each first parameter individual may include: using the root mean square error loss function or the cross-entropy error loss function to obtain the loss function value.

[0111] S203. Determine the optimal first parameter individual according to the loss function value corresponding to each first parameter individual.

[0112] That is, determine the first parameter individual with the smallest loss function value as the optimal first parameter individual.

[0113] S204. Based on the optimal first parameter individual, use the adaptive vibration-guided search strategy to update each first parameter individual to obtain the first parameter individual after vibration-guided search.

[0114] S205. For the first parameter individual after vibration-guided search, use the adaptive local area search strategy to update each first parameter individual to obtain the first parameter individual after local area search.

[0115] S206. For the first parameter individual after local area search, use the adaptive population cooperation search strategy to update each first parameter individual to obtain the first parameter individual after population cooperation search.

[0116] S207. Repeat the above vibration-guided search, local area search, and population cooperation search until the number of training times reaches the maximum number of training times. Re-obtain the optimal first parameter individual and apply the parameters included in the optimal first parameter individual to the first initial rule to obtain the first prediction rule.

[0117] Optionally, in addition to ending the training when the number of training times reaches the maximum number of training times, other conditions can also be used to end the training. For example, when the minimum value of the loss function is less than a preset threshold, it can be determined that the training can be ended.

[0118] In a possible implementation manner, based on the optimal first parameter individual, an adaptive vibration-guided search strategy is used to update each first parameter individual to obtain the first parameter individual after vibration-guided search, including:

[0119] Based on the current number of training times, determine the adaptive attenuation factor as:

[0120]

[0121] where z t represents the adaptive attenuation factor in the t-th training process, z max represents the maximum value corresponding to the adaptive attenuation factor, z min represents the minimum value corresponding to the adaptive attenuation factor, e represents the natural constant, and T represents the maximum number of training times;

[0122] According to the adaptive attenuation factor, obtain the first adaptive vibration-guided coefficient and the second adaptive vibration-guided coefficient as:

[0123] α1 = 2z t r1 - z t

[0124] α2 = kz t r2 + 1

[0125] where α1 represents the first adaptive vibration-guided coefficient, r1 represents the first random number between (0, 1), α2 represents the second adaptive vibration-guided coefficient, k represents the natural constant quantity, and r2 represents the second random number between (0, 1);

[0126] Generate a third random number r3 between (0, 1), and determine whether the third random number r3 is less than the first decision probability (which can be set to 0.5). If so, based on the optimal first parameter individual, and according to the first adaptive vibration-guided coefficient and the second adaptive vibration-guided, perform the first vibration-guided search on the first parameter individual to obtain the first parameter individual after vibration-guided search. Otherwise, based on the optimal first parameter individual, and according to the first adaptive vibration-guided coefficient and the second adaptive vibration-guided, perform the second vibration-guided search on the first parameter individual;

[0127] Performing the first vibration-guided search on the first parameter individual based on the optimal first parameter individual and according to the first adaptive vibration-guided coefficient and the second adaptive vibration-guided is:

[0128]

[0129] Among them, represents the i-th first parameter individual in the t-th training process, where i = 1, 2, …, I, and I represents the total number of first parameter individuals, represents the optimal first parameter individual, represents the first parameter individual after vibration-guided search

[0130] Based on the optimal first parameter individual and according to the first adaptive vibration-guided coefficient and the second adaptive vibration guidance, the second vibration-guided search for the first parameter individual is as follows:

[0131]

[0132] Among them, π represents pi, cos represents the cosine function, and sin represents the sine function.

[0133] The first vibration-guided search and the second vibration-guided search provided by the embodiments of the present invention can enable all the first parameter individuals to perform spiral search in the solution space in different ways and vibrate during the spiral search, thereby forming a mesh search path, which can not only effectively improve the search efficiency but also enhance the global search ability of the algorithm, and thus can effectively avoid falling into local optima.

[0134] In a possible implementation manner, for the first parameter individual after vibration-guided search, an adaptive local area search strategy is adopted to update each first parameter individual to obtain the first parameter individual after local area search, including:

[0135] Based on the current training times, determine the adaptive local exploitation factor as:

[0136] p = (1 - t / T) t / T

[0137] Among them, p represents the adaptive local exploitation factor;

[0138] For the first parameter individual after vibration-guided search, generate a fourth random number r4 between (0, 1), and determine whether the fourth random number r4 is less than the second decision probability (which can be set to 0.5). If so, perform the first local area search on the first parameter individual to obtain the first parameter individual after local area search; otherwise, perform the second local area search on the first parameter individual to obtain the first parameter individual after local area search;

[0139] The first local area search for the first parameter individual is as follows:

[0140]

[0141] Among them, represents the first parameter individual after the nth vibration-guided search, where n = 1, 2, …, I, r5 represents the fifth random number between (0, 1), and F represents a random quantity between [-1, 1];

[0142] The second local area search for the first parameter individual is as follows:

[0143]

[0144] Among them, represents the first parameter individual after the local area search

[0145] The first local area search and the second local area search provided by the embodiments of the present invention can enable the first parameter individual to perform local search in an irregular route and in different ways, thereby effectively improving the search accuracy of the algorithm.

[0146] In a possible implementation manner, for the first parameter individual after the local area search, an adaptive population cooperation search strategy is used to update each first parameter individual to obtain the first parameter individual after the population cooperation search, including:

[0147] Based on the current training times, the adaptive cooperation factor is determined as:

[0148]

[0149] Among them, represents the adaptive cooperation factor corresponding to the first parameter individual after the mth local area search in the tth training process, β0 represents the first preset constant, represents the intermediate coefficient corresponding to the first parameter individual after the mth local area search, where m = 1, 2, …, I, ξ max represents the maximum value corresponding to the intermediate coefficient, ξ max represents the minimum value corresponding to the intermediate coefficient, represents the fitness value corresponding to the first parameter individual after the mth local area search, represents the minimum fitness value among the first parameter individuals after the local area search, represents the average fitness value among the first parameter individuals after the local area search; the fitness value is obtained by taking the reciprocal after adding the loss function value and the second preset constant;

[0150] For the first parameter individual after the mth local area search, according to the adaptive cooperation factor, the cooperation influence of all other first parameter individuals on the first parameter individual is determined as:

[0151]

[0152] Among them, represents the collaborative influence, and r6 represents the sixth random number between (0, 1). represents the first parameter individual after the k-th local area search and the first parameter individual after the m-th local area search with respect to the influence on the d-th dimensional parameter, d = 1, 2, …, D, where D represents the total dimension of the parameters of the first parameter individual, and ε represents the second preset constant, and ε = 0.0001; represents the first parameter individual corresponding weight represents the first parameter individual corresponding weight and is obtained in the same way; represents the d-th dimensional parameter of the first parameter individual represents the d-th dimensional parameter of the first parameter individual represents the degree of position superiority or inferiority corresponding to the first parameter individual represents the degree of position superiority or inferiority corresponding to the first parameter individual, f m represents the fitness value corresponding to the first parameter individual after the m-th local area search, f w represents the minimum fitness value among the first parameter individuals after the local area search, f best represents the maximum fitness value among the first parameter individuals after the local area search;

[0153] According to the collaborative influence and the weight determine that the collaborative influence term corresponding to the d-th dimensional parameter of the first parameter individual is:

[0154] According to the collaborative influence term corresponding to the d-th dimensional parameter of the first parameter individual determine that the increment term corresponding to the d-th dimensional parameter of the first parameter individual is:

[0155]

[0156] Among them, represents the increment term corresponding to the d-th dimensional parameter of the first parameter individual during the t-th training process,​​​​ Denote the increment term corresponding to the d-th dimension parameter of the first parameter individual during the (t + 1)-th training process where r7 represents the seventh random number between (0, 1), A1 represents the first constant between (0, 1), and r8 represents the eighth random number between (-1, 1). Denote the d-th dimension parameter of the optimal first parameter individual, A2 represents the second constant between (0, 1), and r9 represents the ninth random number between (-1, 1);

[0157] Herein Denote the d-th dimension parameter of a random first parameter individual other than the first parameter individual Update the first parameter individual according to the increment term corresponding to the d-th dimension parameter of the first parameter individual as follows:

[0158] According to the first parameter individual Update the first parameter individual according to the increment term corresponding to the d-th dimension parameter of the first parameter individual as:

[0159]

[0160] wherein Denote the d-th dimension parameter of the first parameter individual after population collaborative search of the first parameter individual

[0161] The adaptive local region search strategy provided by the embodiments of the present invention can not only integrate the information of all first parameter individuals, but also learn the parameter information of the optimal first parameter individual and a random first parameter individual, and at the same time adopts a memory strategy, thereby being more conducive to exploring the unknown regions of the entire solution space by using the information of the entire population and improving the possibility of finding the global optimal solution.

[0162] Optionally, after updating the first parameter individual, out-of-bounds processing can be performed on it to ensure that the parameters are always valid.

[0163] As Figure 3 shown, the GISA-BP algorithm is used to learn the regional electricity consumption characteristics and daily electricity consumption, and determine the second prediction rule, including:

[0164] S301. Create a second initial rule using the BP algorithm and initialize the parameters of the second initial rule to obtain a second parameter individual, and repeatedly obtain multiple different second parameter individuals;

[0165] S302. Combine the regional electricity consumption characteristics into a vector and use it as the input data of the second initial rule, and use the daily electricity consumption corresponding to the regional electricity consumption characteristics as the expected label to obtain the loss function value corresponding to each second parameter individual;

[0166] S303. Determine the optimal second parameter individual according to the loss function value corresponding to each second parameter individual;

[0167] S304. Based on the optimal second-parameter individual, use an adaptive vibration-guided search strategy to update each second-parameter individual to obtain the second-parameter individual after vibration-guided search;

[0168] S305. For the second-parameter individual after vibration-guided search, use an adaptive local-region search strategy to update each second-parameter individual to obtain the second-parameter individual after local-region search;

[0169] S306. For the second-parameter individual after local-region search, use an adaptive population cooperation search strategy to update each second-parameter individual to obtain the second-parameter individual after population cooperation search;

[0170] S307. Repeat the above vibration-guided search, local-region search, and population cooperation search until the number of training times reaches the maximum number of training times, re-obtain the optimal second-parameter individual, and apply the parameters included in the optimal second-parameter individual to the second initial rule to obtain the second prediction rule.

[0171] The specific method for determining the second prediction rule is similar to the principle and beneficial effects of determining the first prediction rule, and will not be elaborated here.

[0172] In a possible implementation manner, according to the predicted solar power supply and the predicted regional power consumption, evaluate the power supply adequacy of the solar power supply system on rainy days to obtain a power supply adequacy evaluation result, including:

[0173] Judge whether the difference obtained by subtracting the predicted regional power consumption from the predicted solar power supply is greater than a preset power supply adequacy threshold. If so, determine that the power supply adequacy evaluation result is power supply sufficient; otherwise, determine that the power supply adequacy evaluation result is power supply insufficient.

[0174] In a possible implementation manner, after evaluating the power supply adequacy of the solar power supply system on rainy days, it further includes:

[0175] Judge whether the power supply adequacy evaluation result is of the insufficient type. If so, generate a power supply insufficient warning and transmit the power supply insufficient warning to the device or system designated by the staff; otherwise, repeat the power supply adequacy evaluation method of the solar power supply system.

[0176] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The solutions in the embodiments of the present invention can be implemented in various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript, etc.

[0177] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0178] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for realizing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0180] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0181] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for evaluating the power supply adequacy of a solar power supply system for rainy and cloudy days, characterized in that, Including: Collect the solar power supply impact factors and daily power supply under rainy and cloudy conditions, and use the GISA-BP algorithm to learn the solar power supply impact factors and daily power supply to determine the first prediction rule; Collect the regional electricity consumption characteristics and daily electricity consumption corresponding to the solar power supply area, and use the GISA-BP algorithm to learn the regional electricity consumption characteristics and daily electricity consumption to determine the second prediction rule; Collect the real-time solar power supply impact factors during rainy and cloudy days, and use the first prediction rule to analyze the real-time solar power supply impact factors to determine the predicted solar power supply; Collect the real-time regional electricity consumption characteristics corresponding to the solar power supply area, and use the second prediction rule to analyze the real-time regional electricity consumption characteristics to determine the predicted regional electricity consumption; According to the predicted solar power supply and the predicted regional electricity consumption, evaluate the power supply adequacy of the solar power supply system on rainy and cloudy days to obtain the power supply adequacy evaluation result; Using the GISA-BP algorithm to learn the solar power supply impact factors and the daily power supply to determine the first prediction rule includes: Use the BP algorithm to create the first initial rule and initialize the parameters of the first initial rule to obtain the first parameter individual, and repeat to obtain multiple different first parameter individuals; Form the solar power supply impact factors into a vector and use it as the input data of the first initial rule, and use the daily power supply corresponding to the solar power supply impact factor as the expected label to obtain the loss function value corresponding to each first parameter individual; Determine the optimal first parameter individual according to the loss function value corresponding to each first parameter individual; Based on the optimal first parameter individual, use the adaptive vibration-guided search strategy to update each first parameter individual to obtain the first parameter individual after vibration-guided search; For the first parameter individual after vibration-guided search, use the adaptive local area search strategy to update each first parameter individual to obtain the first parameter individual after local area search; For the first parameter individual after local area search, use the adaptive population cooperation search strategy to update each first parameter individual to obtain the first parameter individual after population cooperation search; Repeat the above vibration-guided search, local area search, and population cooperation search until the number of training times reaches the maximum number of training times, re-obtain the optimal first parameter individual, and apply the parameters included in the optimal first parameter individual to the first initial rule to obtain the first prediction rule.

2. The method for evaluating the power supply adequacy of a solar power supply system for rainy and cloudy days according to claim 1, wherein, Collect the solar power supply impact factors and daily power supply under rainy and cloudy conditions, including: Collect the average temperature, daily temperature range, average relative humidity, average wind speed, sunshine duration, visibility, global horizontal radiation, global tilted radiation, diffuse horizontal radiation, and diffuse tilted radiation under rainy and cloudy conditions to obtain the solar power supply impact factors; Collect the daily power supply under rainy and cloudy conditions.

3. The method for evaluating the power supply adequacy of the solar power supply system for rainy and cloudy days according to claim 1, characterized in that Based on the optimal first parameter individual, use the adaptive vibration-guided search strategy to update each first parameter individual to obtain the first parameter individual after vibration-guided search, including: Based on the current number of training times, determine the adaptive attenuation factor as: Among them, z t represents the adaptive decay factor during the t-th training process, z max represents the maximum value corresponding to the adaptive decay factor, z min represents the minimum value corresponding to the adaptive decay factor, e represents the natural constant, and T represents the maximum number of training times; According to the adaptive attenuation factor, obtain the first adaptive vibration guiding coefficient and the second adaptive vibration guiding coefficient as: α1 = 2z t r1 - z t α2 = kz t r2 + 1 Where, α1 represents the first adaptive vibration guiding coefficient, r1 represents the first random number between (0, 1), α2 represents the second adaptive vibration guiding coefficient, k represents the natural constant, and r2 represents the second random number between (0, 1); Generate a third random number r3 between (0, 1), and determine whether the third random number r3 is less than the first decision probability. If so, based on the optimal first parameter individual, and according to the first adaptive vibration guiding coefficient and the second adaptive vibration guiding, perform the first vibration guiding search on the first parameter individual to obtain the first parameter individual after the vibration guiding search. Otherwise, based on the optimal first parameter individual, and according to the first adaptive vibration guiding coefficient and the second adaptive vibration guiding, perform the second vibration guiding search on the first parameter individual; Based on the optimal first parameter individual, and according to the first adaptive vibration guiding coefficient and the second adaptive vibration guiding, the first vibration guiding search on the first parameter individual is: Among them, represents the i-th first-parameter individual in the t-th training process, where i = 1, 2, …, I, and I represents the total number of first-parameter individuals, represents the optimal first-parameter individual, represents the first-parameter individual after vibration-guided search Based on the optimal first parameter individual, and according to the first adaptive vibration guiding coefficient and the second adaptive vibration guiding, the second vibration guiding search on the first parameter individual is: Where, π represents the pi, cos represents the cosine function, and sin represents the sine function.

4. The method for evaluating the power supply adequacy of the solar power supply system for rainy and cloudy days according to claim 3, wherein For the first parameter individual after the vibration guiding search, adopt the adaptive local area search strategy to update each first parameter individual to obtain the first parameter individual after the local area search, including: Based on the current number of training times, determine the adaptive local exploitation factor as: p = (1 - t / T) t / T Where, p represents the adaptive local exploitation factor; For the first parameter individual after the vibration guiding search, generate a fourth random number r4 between (0, 1), and determine whether the fourth random number r4 is less than the second decision probability. If so, perform the first local area search on the first parameter individual to obtain the first parameter individual after the local area search. Otherwise, perform the second local area search on the first parameter individual to obtain the first parameter individual after the local area search; The first local area search on the first parameter individual is: Among them, represents the first parameter individual after the nth vibration-guided search, where n = 1, 2, …, I, r5 represents the fifth random number between (0, 1), and F represents a random quantity between [-1, 1]; The second local area search on the first parameter individual is: Among them, represents the first parameter individual after local area search 5. The method for evaluating the power supply adequacy of the solar power supply system for rainy and cloudy days according to claim 4, wherein, For the first parameter individual after the local area search, adopt the adaptive population cooperation search strategy to update each first parameter individual to obtain the first parameter individual after the population cooperation search, including: Based on the current number of training times, determine the adaptive cooperation factor as: Among them, represents the adaptive cooperation factor corresponding to the first parameter individual after the m-th local area search in the t-th training process, and β0 represents the first preset constant. represents the intermediate coefficient corresponding to the first parameter individual after the m-th local area search, where m = 1, 2, …, I, and ξ max represents the maximum value corresponding to the intermediate coefficient, and ξ min represents the minimum value corresponding to the intermediate coefficient. represents the fitness value corresponding to the first parameter individual after the m-th local area search. represents the minimum fitness value among the first parameter individuals after the local area search. represents the average fitness value among the first parameter individuals after the local area search; the fitness value is obtained by taking the reciprocal after adding the loss function value and the second preset constant. For the first parameter individual after the m-th local area search, according to the adaptive cooperation factor, determine the cooperation influence of all other first parameter individuals on the first parameter individual as: Among them, represents the collaborative influence, r6 represents the sixth random number between (0, 1), represents the first parameter individual after the k-th local area search and the first parameter individual after the m-th local area search Regarding the influence on the d-th dimensional parameter, d = 1, 2, …, D, D represents the total dimension of the parameters of the first parameter individual, ε represents the second preset constant, and ε = 0.0001; represents the first parameter individual corresponding weight, represents the first parameter individual corresponding weight, and is obtained in the same way; represents the d-th dimensional parameter of the first parameter individual and represents the d-th dimensional parameter of the first parameter individual and represents the degree of position superiority or inferiority corresponding to the first parameter individual and represents the degree of position superiority or inferiority corresponding to the first parameter individual, f and m represents the fitness value corresponding to the first parameter individual after the m-th local area search, f w represents the minimum fitness value among the first parameter individuals after the local area search, f best represents the maximum fitness value among the first parameter individuals after the local area search; According to the collaborative influence and the weight determine that the collaborative influence term corresponding to the d - dimensional parameter of the first - parameter individual is as follows: According to the first parameter individual The collaborative influence item corresponding to the d-th dimensional parameter of Determine the first parameter individual The increment item corresponding to the d-th dimensional parameter of is: Among them, represents the incremental term corresponding to the d-th dimension parameter of the first parameter individual during the t-th training process, represents the incremental term corresponding to the d-th dimension parameter of the first parameter individual during the (t + 1)-th training process, r7 represents the seventh random number between (0, 1), A1 represents the first constant between (0, 1), and r8 represents the eighth random number between (-1, 1). represents the d-th dimension parameter of the optimal first parameter individual, A2 represents the second constant between (0, 1), and r9 represents the ninth random number between (-1, 1); According to the incremental term corresponding to the d-th dimensional parameter of the first parameter individual the first parameter individual is updated as follows: Among them, represents the d-th dimensional parameter of the first parameter individual after the population collaborative search.

6. The method for evaluating the power supply adequacy of the solar power supply system for rainy and cloudy days according to claim 5, characterized in that, Collect the regional electricity consumption characteristics and daily electricity consumption corresponding to the solar power supply area, including: Collect the seasonal data, weather data, temperature data, and date type data of the power supply area to obtain the regional electricity consumption characteristics corresponding to the solar power supply area; Collect the daily electricity consumption corresponding to the regional electricity consumption characteristics; Among them, the season data includes spring, summer, autumn or winter, the weather data includes rainy, sunny, cloudy or snowy days, and the date type data includes working days or non-working days.

7. The method for evaluating the power supply adequacy of the solar power supply system for rainy and cloudy days according to claim 6, wherein The GISA-BP algorithm is used to learn the regional electricity consumption characteristics and daily electricity consumption, and determine the second prediction rule, including: The BP algorithm is used to create a second initial rule and initialize the parameters of the second initial rule to obtain a second parameter individual, and multiple different second parameter individuals are repeatedly obtained; The regional electricity consumption characteristics are composed into a vector and used as the input data of the second initial rule, and the daily electricity consumption corresponding to the regional electricity consumption characteristics is used as the expected label to obtain the loss function value corresponding to each second parameter individual; According to the loss function value corresponding to each second parameter individual, the optimal second parameter individual is determined; Based on the optimal second parameter individual, an adaptive vibration-guided search strategy is used to update each second parameter individual to obtain the second parameter individual after vibration-guided search; For the second parameter individual after vibration-guided search, an adaptive local area search strategy is used to update each second parameter individual to obtain the second parameter individual after local area search; For the second parameter individual after local area search, an adaptive population cooperation search strategy is used to update each second parameter individual to obtain the second parameter individual after population cooperation search; Repeat the above vibration-guided search, local area search and population cooperation search until the number of training times reaches the maximum number of training times, re-obtain the optimal second parameter individual, and apply the parameters included in the optimal second parameter individual to the second initial rule to obtain the second prediction rule.

8. The method for evaluating the power supply adequacy of the solar power supply system for rainy and cloudy days according to claim 7, wherein According to the predicted solar power supply and the predicted regional electricity consumption, the power supply adequacy of the solar power supply system on rainy and cloudy days is evaluated to obtain the power supply adequacy evaluation result, including: Judge whether the difference obtained by subtracting the predicted regional electricity consumption from the predicted solar power supply is greater than the preset power supply adequacy threshold. If so, determine that the power supply adequacy evaluation result is sufficient power supply; otherwise, determine that the power supply adequacy evaluation result is insufficient power supply.

9. The method for evaluating the power supply adequacy of the solar power supply system for rainy and cloudy days according to any one of claims 1 to 8, characterized in that, After evaluating the power supply adequacy of the solar power supply system on rainy and cloudy days, it also includes: Judge whether the power supply adequacy evaluation result is of the insufficient type. If so, generate a power supply insufficiency warning and transmit the power supply insufficiency warning to the device or system designated by the staff; otherwise, repeat the method for evaluating the power supply adequacy of the solar power supply system.

Images