Energy storage system energy management method and device based on artificial intelligence

Abstract

The invention discloses an artificial intelligence-based energy management method and device for an energy storage system, relates to the technical field of energy management, and aims to improve the accuracy of power consumption prediction by collecting multi-dimensional historical power consumption associated data to construct a sample, so that the energy management of the energy storage system is more accurate, and the energy management efficiency is improved. And the charging power is dynamically adjusted according to the predicted electricity consumption and the residual electric quantity of the energy storage system, so that fine management of energy of the energy storage system is realized, the energy utilization efficiency is improved, the service life of the energy storage system can be prolonged, finally, energy charging is performed in the electricity price valley period, the operation cost of the energy storage system is reduced, and the economic benefit is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy management, in particular to an energy management method and device for energy storage system based on artificial intelligence. BACKGROUND

[0002] With the transformation of energy structure and large-scale application of renewable energy, the role of energy storage system in power system is increasingly prominent. Energy storage system can store energy when power demand is low and release energy when power demand is high, thereby balancing the load of power grid and improving energy utilization efficiency. However, the traditional energy management method of energy storage system mainly relies on fixed scheduling strategy or simple prediction model, which is difficult to adapt to complex and changeable power consumption environment, resulting in low energy management efficiency, and the peak load shifting effect of energy storage system cannot be fully played. Therefore, it is difficult to balance the service life and efficiency. SUMMARY

[0003] The present application provides an energy management method and device for energy storage system based on artificial intelligence, aiming to solve the problem that the prior art cannot balance the energy management efficiency and service life.

[0004] The first aspect of the present application provides an energy management method for energy storage system based on artificial intelligence, comprising: Collecting historical power consumption correlation data corresponding to an energy supply area corresponding to an energy storage system, and constructing historical load influence samples and corresponding power consumption labels according to the historical power consumption correlation data; Using an artificial intelligence model to learn the data relationship between the historical load influence samples and the corresponding power consumption labels, to obtain a power consumption prediction model; Collecting real-time load influence samples of the energy supply area, and scheduling the power consumption prediction model to identify the real-time load influence samples to determine the predicted power consumption of the energy supply area; Determining the remaining power of the energy storage system, and determining the charging power corresponding to the energy storage system according to the remaining power and the predicted power consumption; Based on the charging power corresponding to the energy storage system, the energy management of the energy storage system is completed to achieve the energy management of the energy storage system based on artificial intelligence.

[0005] In one possible implementation, collecting historical power consumption correlation data corresponding to an energy supply area corresponding to an energy storage system, and constructing historical load influence samples and corresponding power consumption labels according to the historical power consumption correlation data, comprises: The historical power consumption correlation data at the N continuous sampling time points are collected to construct a historical load influence sample, and the historical power consumption at the N+1 sampling time point is taken as a power consumption label. The historical power consumption correlation data at the N continuous sampling time points are collected to construct a historical load influence sample, and the historical power consumption at the N+1 sampling time point is taken as a power consumption label.

[0006] In a possible implementation, a data relationship between the historical load influence sample and the corresponding power consumption label is learned by using an artificial intelligence model to obtain a power consumption prediction model, including: Random initialization coding is performed between the upper and lower limits of the model parameters of the artificial intelligence model to obtain model parameter coding, and a plurality of different model parameter codings are repeatedly obtained; Based on the historical load influence sample and the corresponding power consumption label, the fitness corresponding to all model parameter codings is obtained; According to the fitness corresponding to the model parameter coding, a multi-parameter adaptive local search mechanism is used to adaptively search the model parameter coding to obtain the model parameter coding after adaptive search; An adaptive collaborative search mechanism is used to collaboratively search the model parameter coding after adaptive search to obtain the model parameter coding after collaborative search; An adaptive number of mutation fusion mechanisms are used to perform mutation fusion search on the model parameter coding after collaborative search to obtain the model parameter coding after mutation fusion search; The adaptive search, collaborative search and mutation fusion search are repeated until the maximum training number is reached, and the target optimal parameter coding is obtained according to the model parameter coding after mutation fusion search; The power consumption prediction model is obtained according to the target optimal parameter coding.

[0007] In a possible implementation, according to the fitness corresponding to the model parameter coding, a multi-parameter adaptive local search mechanism is used to adaptively search the model parameter coding to obtain the model parameter coding after adaptive search, including: According to the fitness corresponding to the model parameter coding and the current training number, the adaptive speed adjustment factor is determined as:

[0008] Wherein, The adaptive speed adjustment factor corresponding to the i-th model parameter coding is represented as k The maximum value of the adaptive speed adjustment factor is represented as The adaptive speed adjustment factor corresponding to the i-th model parameter coding is represented as Indicates the maximum number of training iterations. This indicates the current number of training iterations. This represents the fitness corresponding to the encoding of the k-th model parameter. This represents the maximum fitness among all encoded model parameters; Based on the fitness corresponding to the model parameter encoding and the current number of training iterations, the first local learning factor and the second local learning factor are determined as follows:

[0009] in, Represents the first local learning factor. This represents the second local learning factor. Represents the cosine function. Represents pi; Based on the adaptive speed adjustment factor, the first local learning factor, and the second local learning factor, obtain the first... k The search speed corresponding to the encoding of each model parameter is:

[0010] in, Indicates the first t During the training process, the first k The search speed corresponding to each model parameter encoding Indicates the first t +1 training session k The search speed corresponding to each model parameter encoding k =1,2,...,K, K This indicates the total number of model parameter codes. Represents the first random number between (0,1). This represents the second random number between (0,1). Indicates the first k Each model parameter is encoded with its corresponding historical best value. Indicates the first k Each model parameter is encoded. The model parameter encoding representing the maximum fitness; Based on the search speed, an adaptive search is performed on the model parameter encoding to obtain the adaptively searched model parameter encoding as follows:

[0011] in, Indicates the first k The model parameters are encoded after an adaptive search.

[0012] In one possible implementation, an adaptive cooperative search mechanism is used to perform a cooperative search on the model parameter encoding after the adaptive search, to obtain the model parameter encoding after the cooperative search, including: For any dimension of the model parameters, the average value of the model parameters encoded by all the adaptive search models is calculated, and the average values ​​corresponding to all dimensions are constructed into a vector to obtain the center code; The model parameter codes after the adaptive search are arranged in ascending order of fitness to obtain the arranged model parameter codes. Based on the encoded model parameters after permutation, the first collaborative search factor and the second collaborative search factor are obtained as follows:

[0013]

[0014] in, Indicates the first i The first collaborative search factor is encoded by the model parameters after each permutation. Indicates the first i The second collaborative search factor is encoded by the model parameters after each permutation. sin Represents the sine function. cos Represents the cosine function. This represents the cooperative search direction control parameter, and , Represents a constant term. This represents a third random number between (0,1). This indicates the parameters controlling the scope of the collaborative search, and , Indicates the basic influence parameter of the search range. This represents the fourth random number between (0, 1); Indicates all Based on the current number of training iterations, the position perturbation factor is obtained as follows:

[0015] in, Indicates the location disturbance factor. Represents pi (π). This represents the maximum value of the position disturbance factor. This represents the minimum value of the position disturbance factor. Indicates the maximum number of training iterations; Based on the center code, position perturbation factor, first cooperative search factor, and second cooperative search factor, a cooperative search is performed on the arranged model parameter codes to obtain the cooperatively searched model parameter codes as follows:

[0016] wherein, denotes the model parameter encoding after the i th permutation, i =1,2,...,K, K denotes the total number of model parameter encodings, denotes the model parameter encoding after the i +1th permutation, and i =K, then is the model parameter encoding after random permutation, denotes the model parameter encoding after the i th cooperative search, denotes the center encoding.

[0017] In one possible implementation, the model parameter encoding after the cooperative search is subjected to a mutation fusion search using an adaptive number of mutation fusion mechanisms to obtain a model parameter encoding after mutation fusion search, comprising: According to the fitness of the model parameter encoding after the cooperative search, the adaptive number of mutation fusions is obtained as:

[0018] wherein, denotes the adaptive number of mutation fusions corresponding to the model parameter encoding after the m th cooperative search, m =1,2,...,K, K denotes the total number of model parameter encodings, denotes the ceiling function, denotes the fitness of the model parameter encoding after the m th cooperative search, denotes the maximum fitness among all model parameter encodings, denotes the minimum fitness among all model parameter encodings; is the model parameter encoding after the m th cooperative search, randomly selects model parameter encodings after other cooperative searches to obtain mutation fusion encodings; According to the mutation fusion encodings, the model parameter encoding after the cooperative search is subjected to a mutation fusion search to obtain a model parameter encoding after mutation fusion search as:

[0019] wherein, denotes the model parameter encoding after the m th cooperative search, denotes the model parameter encoding after the first m variation fusion search, denotes the fifth random number between (0, 1), denotes the model parameter encoding corresponding to the first j variation fusion encoding, denotes the model parameter encoding corresponding to the maximum fitness.

[0020] In a possible implementation, a real-time load impact sample of the energy supply area is collected, and the power consumption prediction model is scheduled to identify the real-time load impact sample to determine the predicted power consumption of the energy supply area, including: The real-time load impact sample of the energy supply area is collected; wherein the data structure of the real-time load impact sample is the same as that of the historical load impact sample; The real-time load impact sample is taken as the input of the power consumption prediction model to obtain the predicted power consumption of the energy supply area.

[0021] In a possible implementation, the remaining power of the energy storage system is determined, and the corresponding charging power of the energy storage system is determined according to the remaining power and the predicted power consumption, including: The remaining power of the energy storage system is determined; The difference between the remaining power and the predicted power consumption is obtained as a power difference; In the case where the power difference is greater than or equal to zero, the corresponding charging power of the energy storage system is determined as a first preset charging power; In the case where the power difference is less than zero, a second preset charging power corresponding to the power difference is determined; wherein the second preset charging power is greater than the first preset charging power; different power differences are preset with different second preset charging powers, and the power difference is directly proportional to the second preset charging power, and the first preset charging power and the second preset charging power are both less than or equal to the rated charging power designed for the energy storage system.

[0022] In a possible implementation, the energy storage system is managed based on the corresponding charging power of the energy storage system, including: Based on the corresponding charging power of the energy storage system, the energy storage system is controlled to charge in a preset time period; wherein the preset time period refers to a low price valley period.

[0023] The second aspect of the present application provides an energy storage system energy management device based on artificial intelligence, including a data acquisition module, a data training module, a power consumption prediction module, a charging determination module and an energy management module. The data collection module is configured to collect historical power consumption correlation data corresponding to a power supply area of an energy storage system, and construct a historical load influence sample and a power consumption label corresponding thereto according to the historical power consumption correlation data. The data training module is configured to learn a data relationship between the historical load influence sample and the power consumption label corresponding thereto by using an artificial intelligence model, and obtain a power consumption prediction model. The power consumption prediction module is configured to collect a real-time load influence sample of the power supply area, and schedule the power consumption prediction model to identify the real-time load influence sample, and determine a predicted power consumption of the power supply area. The charging determination module is configured to determine a remaining power of the energy storage system, and determine a charging power corresponding to the energy storage system according to the remaining power and the predicted power consumption. The energy management module is configured to perform energy management on the energy storage system based on the charging power corresponding to the energy storage system, and complete artificial intelligence-based energy storage system energy management.

[0024] Beneficial effects: The application provides an artificial intelligence-based energy storage system energy management method and device, which constructs a sample by collecting multi-dimensional historical power consumption correlation data, improves the accuracy of power consumption prediction, makes the energy storage system energy management more accurate, dynamically adjusts the charging power according to the predicted power consumption and the remaining power of the energy storage system, not only realizes fine management of the energy storage system energy, improves the energy utilization efficiency, but also prolongs the service life of the energy storage system, finally charges at the low price valley period, reduces the operation cost of the energy storage system, and improves the economic benefit. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the application. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 is a flowchart of an artificial intelligence-based energy storage system energy management method according to an embodiment of the application; Figure 2 is a structural diagram of an artificial intelligence-based energy storage system energy management device according to an embodiment of the application; Legend: 201-data collection module, 202-data training module, 203-power consumption prediction module, 204-charging determination module, 205-energy management module. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0028] As shown in Figure 1 The embodiments of the present application provide an energy storage system energy management method based on artificial intelligence, comprising: S101, historical electricity consumption correlation data corresponding to an energy supply area corresponding to an energy storage system is collected, and historical load influence samples and their corresponding electricity consumption labels are constructed according to the historical electricity consumption correlation data.

[0029] For example, the historical electricity consumption correlation data includes but is not limited to historical electricity consumption, temperature data, seasonal information, date information, holiday information, and weather information, etc. These data reflect the influencing factors of electricity consumption from different angles, and by comprehensively analyzing these data, the future electricity consumption can be more accurately predicted.

[0030] S102, an artificial intelligence model is used to learn the data relationship between the historical load influence samples and their corresponding electricity consumption labels, and an electricity consumption prediction model is obtained.

[0031] The historical load influence samples usually have an enlightening effect on electricity consumption. By learning the data relationship between the historical load influence samples and their corresponding electricity consumption labels through an artificial intelligence model, the artificial intelligence model can be enabled to have the ability to predict electricity consumption, thereby obtaining an electricity consumption prediction model.

[0032] S103, real-time load influence samples of the energy supply area are collected, and the electricity consumption prediction model is used to identify the real-time load influence samples to determine the predicted electricity consumption of the energy supply area.

[0033] The data structure of the real-time load influence samples of the energy supply area should be the same as that of the historical load influence samples, so as to ensure that the electricity consumption prediction model can accurately identify the real-time load influence samples and obtain the predicted electricity consumption of the energy supply area.

[0034] S104, the remaining electricity of the energy storage system is determined, and the charging power corresponding to the energy storage system is determined according to the remaining electricity and the predicted electricity consumption.

[0035] The greater the difference between the remaining power and the predicted power consumption, the greater the required charging power, thereby ensuring that the peak shaving effect can be achieved. The smaller the difference between the remaining power and the predicted power consumption, the smaller the required charging power, thereby ensuring the operating life of the energy storage system and avoiding the reduction in life caused by long-time high-power charging.

[0036] S105, based on the charging power corresponding to the energy storage system, energy management is performed on the energy storage system to complete the energy storage system energy management based on artificial intelligence.

[0037] Based on the charging power corresponding to the energy storage system, the energy storage system can be supplemented with energy during the low price period. The low price period generally refers to 23:00 of one day to 7:00 of the next day. Charging during this period can effectively reduce the cost of energy supplement.

[0038] The present application provides an energy storage system energy management method based on artificial intelligence. By collecting multi-dimensional historical power consumption correlation data to construct samples, the accuracy of power consumption prediction is improved, the energy storage system energy management is more accurate, and the charging power is dynamically adjusted according to the predicted power consumption and the remaining power of the energy storage system. Not only the energy storage system energy management is realized, but also the energy utilization efficiency is improved, and the service life of the energy storage system is prolonged. Finally, the energy is charged during the low price period, the operation cost of the energy storage system is reduced, and the economic benefit is improved.

[0039] In one possible implementation, historical power consumption correlation data corresponding to an energy supply area corresponding to an energy storage system is collected, and historical load influence samples and corresponding power consumption labels are constructed according to the historical power consumption correlation data, including: Based on a preset data sampling frequency, historical power consumption, the highest temperature of the day, the lowest temperature of the day, the average temperature of the day, the day of the season (such as a unique code corresponding to spring, summer, autumn and winter), date information (such as year, month and day), holiday information (such as a unique code corresponding to holidays and non-holidays), and weather information of the day (a unique code corresponding to different weather, such as a unique code corresponding to light rain, and a unique code corresponding to shower rain) corresponding to an energy supply area corresponding to an energy storage system are collected at multiple sampling time points to obtain historical power consumption correlation data.

[0040] The historical load influence samples are constructed by collecting historical power consumption correlation data at N consecutive sampling time points, and the historical power consumption at the N+1 sampling time point is taken as the power consumption label.

[0041] The data sampling frequency can be set to 1 day collection. Then, the real-time load influence sample refers to collecting historical power consumption correlation data at N consecutive sampling time points closest to the prediction time point (usually in days) that needs to be predicted.

[0042] It is worth noting that for any kind of data, the data length should be kept consistent, so that the data size or data length of the constructed historical load impact sample is consistent. For example, assuming that the historical power consumption correlation data at any sampling time point is constructed as a row of data, the historical load impact sample is a data matrix. By unifying the length of different numerical values of one kind of data, it can be ensured that the size of all historical power consumption correlation data is the same. Assuming that there is a three-digit data and a four-digit data in the historical power consumption, the three-digit data can be padded with zeros in front to make the length of the historical power consumption data at different sampling time points the same. It should be noted that for non-digital data such as the day of the season, holiday information and weather information of the day, an encoding method can be used to represent it, and a unique code with consistent length is assigned to each type.

[0043] In recent years, artificial intelligence technology has been widely applied in energy management field. Through machine learning algorithm, historical power consumption data is analyzed and predicted, which can improve the accuracy of power consumption prediction. However, the existing artificial intelligence prediction model has the problems of slow convergence speed and easy to fall into local optimum in the training process, which affects the prediction accuracy. At the same time, in the energy management strategy of energy storage system, the existing technology often lacks dynamic adjustment mechanism and cannot perform fine control according to the predicted power consumption and the actual state of the energy storage system. Therefore, the embodiments of the present application improve the defects of the prior art, as follows.

[0044] In one possible implementation, an artificial intelligence model is used to learn the data relationship between the historical load impact sample and its corresponding power consumption label, and a power consumption prediction model is obtained, including: Randomly initialize the upper and lower limits of the model parameters of the artificial intelligence model to obtain model parameter codes, and repeat to obtain multiple different model parameter codes.

[0045] The artificial intelligence model can be set as a convolutional neural network, and the model parameters of the convolutional neural network can be connection weights between different network layers. The model parameters can be randomly initialized between the upper and lower limits of the model parameters, and coded into a vector to obtain the model parameter code.

[0046] Based on the historical load impact sample and its corresponding power consumption label, the fitness of all model parameter codes is obtained.

[0047] For example, the historical load impact sample in the historical load impact sample can be taken as input, and the power consumption label can be taken as expected output to obtain the cross-entropy loss function value. The cross-entropy loss function value is added to 0.0001 and taken as the reciprocal to obtain the fitness of all model parameter codes.

[0048] According to the fitness corresponding to the model parameter code, the model parameter code is adaptively searched by using a multi-parameter adaptive local search mechanism, to obtain the model parameter code after adaptive search.

[0049] The model parameter code after adaptive search is collaboratively searched by using an adaptive collaborative search mechanism, to obtain the model parameter code after collaborative search.

[0050] The model parameter code after collaborative search is searched by using an adaptive number of mutation fusion mechanisms, to obtain the model parameter code after mutation fusion search.

[0051] The adaptive search, the collaborative search and the mutation fusion search are repeated until the maximum training number is reached, and the model parameter code after mutation fusion search is obtained, and the target optimal parameter code is obtained.

[0052] For example, in the Tth training process, the model parameter code with the maximum fitness can be obtained as the target optimal parameter code according to the model parameter code after mutation fusion search.

[0053] According to the target optimal parameter code, the power consumption prediction model is obtained, that is, the model parameters in the target optimal parameter code are taken as the target model parameters of the artificial intelligence model, to obtain the power consumption prediction model.

[0054] Optionally, after processing the model parameter code each time, the model parameter code can be processed to be out of bounds, to ensure that the model parameter code is within the effective range.

[0055] In a possible implementation, according to the fitness corresponding to the model parameter code, the model parameter code is adaptively searched by using a multi-parameter adaptive local search mechanism, to obtain the model parameter code after adaptive search, including: According to the fitness corresponding to the model parameter code and the current training number, the adaptive speed adjustment factor is determined as:

[0056] wherein, indicates the adaptive speed adjustment factor corresponding to the kth model parameter code, k indicates the maximum value of the adaptive speed adjustment factor, indicates the maximum training number, indicates the current training number, indicates the fitness corresponding to the kth model parameter code, indicates the maximum fitness of all model parameter codes; indicates the maximum fitness of all model parameter codes; Based on the fitness corresponding to the model parameter encoding and the current number of training iterations, the first local learning factor and the second local learning factor are determined as follows:

[0057] in, Represents the first local learning factor. This represents the second local learning factor. Represents the cosine function. Represents pi; Based on the adaptive speed adjustment factor, the first local learning factor, and the second local learning factor, obtain the first... k The search speed corresponding to the encoding of each model parameter is:

[0058] in, Indicates the first t During the training process, the first k The search speed corresponding to each model parameter encoding Indicates the first t +1 training session k The search speed corresponding to each model parameter encoding k =1,2,...,K, K This indicates the total number of model parameter codes. Represents the first random number between (0,1). This represents the second random number between (0,1). Indicates the first k Each model parameter is encoded with its corresponding historical best value. Indicates the first k Each model parameter is encoded. The model parameter encoding representing the maximum fitness; Based on the search speed, an adaptive search is performed on the model parameter encoding to obtain the adaptively searched model parameter encoding as follows:

[0059] in, Indicates the first k The model parameters are encoded after an adaptive search.

[0060] The adaptive local search mechanism is adopted to adaptively search the model parameter coding, and the adaptive search can be performed based on the fitness of the model parameter coding and the number of training, so that a larger range of search can be performed in the case of excessive aggregation, and vice versa, a more fine search is performed, so as to ensure the training diversity. With the progress of the algorithm, the information learning intensity of the model parameter coding with the historical optimal quality and the maximum fitness is gradually reduced, the search precision of the algorithm is improved, and the convergence of the algorithm is ensured.

[0061] In a possible implementation, an adaptive cooperative search mechanism is adopted to cooperatively search the model parameter coding after the adaptive search, to obtain the model parameter coding after the cooperative search, including: For the model parameters of any dimension, the model parameters of all the model parameter coding after the adaptive search are averaged, and the average values corresponding to all dimensions are constructed as a vector to obtain a center code; The model parameter coding after the adaptive search is arranged in order of fitness from small to large to obtain the model parameter coding after the arrangement; For the model parameter coding after the arrangement, the first cooperative search factor and the second cooperative search factor are obtained as:

[0062]

[0063] wherein, the first cooperative search factor corresponding to the model parameter coding after the arrangement, i the second cooperative search factor corresponding to the model parameter coding after the arrangement, the first cooperative search factor corresponding to the model parameter coding after the arrangement, i the second cooperative search factor corresponding to the model parameter coding after the arrangement, sin the sine function is represented by, cos the cosine function is represented by, the cooperative search direction control parameter is represented by, and , the constant term is represented by, which can be set to 6; the third random number between 0 and 1 is represented by, the cooperative search range control parameter is represented by, and , the search range base influence parameter is represented by, which can be set to 1.5; the fourth random number between 0 and 1 is represented by; the maximum value is determined in all the the minimum value is determined in all the the maximum value is determined in all the the minimum value is determined in all the

[0064] According to the current training number, the position disturbance factor is obtained as:

[0065] wherein, represents the position disturbance factor, represents the circular constant, represents the maximum value of the position disturbance factor, which can be set as 0.91; represents the minimum value of the position disturbance factor, which can be set as 0.4; represents the maximum training number; According to the center code, the position disturbance factor, the first cooperative search factor and the second cooperative search factor, the model parameter code after arrangement is cooperatively searched to obtain the model parameter code after cooperative search as:

[0066] wherein, represents the model parameter code after the first arrangement, i =1, 2,..., K, i represents the total number of model parameter codes, K represents the model parameter code after the Kth arrangement, and when =K, then i is the model parameter code after random arrangement, i represents the model parameter code after the first cooperative search, represents the center code. i The embodiment of the present application adopts the adaptive cooperative search mechanism to cooperatively search the model parameter code after adaptive search, which can make the model parameter code cooperatively search efficiently, so as to explore more solution space and facilitate to find better solution. In a possible implementation, the model parameter code after cooperative search is searched by using the adaptive number of mutation fusion mechanism to obtain the model parameter code after mutation fusion search, including:

[0067] According to the fitness of the model parameter code after cooperative search, the adaptive mutation fusion number is obtained as:

[0068] wherein, represents the adaptive mutation fusion number corresponding to the model parameter code after the first cooperative search, represents the model parameter code after the first cooperative search,

[0069] represents the center code. m m ​​= 1, 2, …, K, K denotes the total number of model parameter encodings, denotes a rounding-up function, denotes the model parameter encoding after the kth cooperative search, m denotes the fitness corresponding to the model parameter encoding after the kth cooperative search, denotes the maximum fitness in all model parameter encodings, denotes the minimum fitness in all model parameter encodings; is randomly selected from the model parameter encoding after the kth cooperative search m is randomly selected from the model parameter encoding after the kth cooperative search obtains k mutation fusion encodings; According to the k mutation fusion encodings, the mutation fusion search is performed on the model parameter encoding after the cooperative search, and the model parameter encoding after the mutation fusion search is obtained as:

[0070] wherein, denotes the model parameter encoding after the kth cooperative search, m denotes the model parameter encoding after the kth cooperative search, denotes the model parameter encoding after the kth mutation fusion search, m denotes the fifth random number between (0, 1), denotes the kth mutation fusion encoding corresponding to the model parameter encoding, denotes the model parameter encoding corresponding to the maximum fitness. j

[0071] The adaptive number of mutation fusion mechanisms are adopted in the embodiments of the present application to perform the mutation fusion search on the model parameter encoding after the cooperative search, which provides strong global search ability for the algorithm, can escape from the current optimal position, and find other positions in the solution space, thereby avoiding the algorithm from falling into the local optimum. The greedy strategy can also be used to control the mutation fusion search, and the training speed of the algorithm is ensured.

[0072] Through the mutual cooperation of the above-mentioned several mechanisms, the power consumption prediction model obtained by training can have more accurate prediction ability, thereby ensuring the accuracy of energy management.

[0073] In a possible implementation, real-time load influence samples of the energy supply area are collected, and the power consumption prediction model is dispatched to identify the real-time load influence samples, to determine the predicted power consumption of the energy supply area, including: ​​​​​Collect a real-time load influence sample of the energy supply area. The real-time load influence sample has the same data structure as the historical load influence sample.

[0074] Input the real-time load influence sample into the power consumption prediction model to obtain a predicted power consumption of the energy supply area.

[0075] Optionally, the real-time load influence sample and the historical load influence sample are normalized before being input into the power consumption prediction model.

[0076] In a possible implementation, the remaining power of the energy storage system is determined, and a charging power corresponding to the energy storage system is determined according to the remaining power and the predicted power consumption, including: The remaining power of the energy storage system is determined.

[0077] A power difference is obtained according to a difference between the remaining power and the predicted power consumption.

[0078] In a case where the power difference is greater than or equal to zero, the charging power corresponding to the energy storage system is determined as a first preset charging power.

[0079] In a case where the power difference is less than zero, a second preset charging power corresponding to the power difference is determined. The second preset charging power is greater than the first preset charging power. Different power differences are preset with different second preset charging powers, and the power difference is directly proportional to the second preset charging power. The first preset charging power and the second preset charging power are both less than or equal to a rated charging power designed for the energy storage system.

[0080] For example, the first preset charging power can be a power corresponding to a trickle charging phase. In a case where the remaining power is sufficient, a small power charging can be used to avoid life loss of the energy storage system.

[0081] Optionally, the second preset charging power maximum value should be set as the rated charging power designed for the energy storage system, that is, if the remaining power is less than the predicted power consumption, it indicates that the energy storage system needs to be powered to realize the full power supply of the power supply area. For example, if the predicted power consumption is greater than the total power of the energy storage system after being fully charged, the rated charging power can be directly used for charging to ensure that the energy storage system can charge as much as possible during the low price period. In the case that the predicted power consumption is less than or equal to the total power of the energy storage system, the second preset charging power can be set as the minimum power that meets the power consumption condition; the power consumption condition is set as the first sum value between the charging amount during the low price period and the remaining power being greater than or equal to the second sum value between the predicted power consumption and the preset fault tolerance power, and the preset fault tolerance power is the power fluctuation value set by the staff in advance, so that the actual power consumption can fluctuate upward within a certain range and meet the power supply demand. If the first sum value cannot be greater than or equal to the second sum value when the second preset charging power is set as the rated charging power, the rated charging power is directly started to charge, so as to reduce the power purchased from the power grid during the non-low price period as much as possible, thereby improving the economy.

[0082] In a possible implementation, the energy management of the energy storage system based on the charging power corresponding to the energy storage system comprises: controlling the energy storage system to charge during a preset period based on the charging power corresponding to the energy storage system; wherein the preset period refers to a low price period.

[0083] As shown in Figure 2 based on the same inventive concept, the embodiments of the present application provide an energy storage system energy management device based on artificial intelligence, which comprises a data acquisition module 201, a data training module 202, a power consumption prediction module 203, a charging determination module 204 and an energy management module 205.

[0084] The data acquisition module 201 is configured to acquire historical power consumption correlation data corresponding to a power supply area corresponding to an energy storage system, and construct a historical load influence sample and a power consumption label corresponding thereto according to the historical power consumption correlation data.

[0085] The data training module 202 is configured to learn the data relationship between the historical load influence sample and the power consumption label corresponding thereto by using an artificial intelligence model, and obtain a power consumption prediction model.

[0086] The power consumption prediction module 203 is configured to acquire a real-time load influence sample of the power supply area, and schedule the power consumption prediction model to identify the real-time load influence sample to determine the predicted power consumption of the power supply area.

[0087] The charging determination module 204 is configured to determine the residual power of the energy storage system, and determine the charging power corresponding to the energy storage system according to the residual power and the predicted power consumption.

[0088] The energy management module 205 is configured to perform energy management on the energy storage system based on the charging power corresponding to the energy storage system, to complete the energy management of the energy storage system based on artificial intelligence.

[0089] The energy management device of the energy storage system based on artificial intelligence provided by the embodiments of the present application can execute the above-mentioned method technical solutions, and has similar principles and beneficial effects, which will not be described here.

[0090] Each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referred to each other.

[0091] The embodiments of the present application are described with reference to flowcharts and / or block diagrams of the methods, devices, electronic equipment and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams 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 terminal equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal equipment realize the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The devices for realizing the functions specified in one block or multiple blocks.

[0092] These computer program instructions can also be stored in a computer readable memory which can guide the computer or other programmable data processing terminal equipment to work in a specific way, so that the instructions stored in the computer readable memory generate a product including instruction devices, which realize the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The functions specified in one block or multiple blocks.

[0093] These computer program instructions can also be loaded into the computer or other programmable data processing terminal equipment, so that a series of operation steps are executed on the computer or other programmable terminal equipment to generate a computer-implemented process, so that the instructions executed on the computer or other programmable terminal equipment provide a process for realizing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The functions specified in one block or multiple blocks.

[0094] While preferred embodiments of the application have been described, those skilled in the art will appreciate that other modifications than those specifically described can be made within the scope of the application. Accordingly, all changes coming within the meaning and equivalency range of the appended claims are intended to be embraced therein.

[0095] Finally, it is to be understood that the phraseology or terminology employed herein, such as "first" and "second", etc., are for descriptive purpose only and can not be construed as an essential element in defining the scope of the application. Moreover, the use of the term "including" or "comprising" is not meant for excluding other elements or steps but for specifying the disclosed embodiment or the specific features of the application. In addition, the use of the term "a" or "an" is not meant for excluding the plurality of the elements or steps. Furthermore, the term "another" is meant for describing an additional feature or step, not a limitation.

[0096] The principles and implementations of the present application have been described in specific examples. The above description is only used to help understand the method and its core idea of the present application. For those skilled in the art, according to the idea of the present application, the specific implementation and application range can be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. An energy management method for an artificial intelligence-based energy storage system, characterized in that, include: Collect historical electricity consumption correlation data corresponding to the energy supply area of ​​the energy storage system, and construct historical load impact samples and their corresponding electricity consumption labels based on the historical electricity consumption correlation data; An artificial intelligence model is used to learn the data relationship between the historical load impact samples and their corresponding electricity consumption tags to obtain an electricity consumption prediction model. Collect real-time load impact samples of the energy supply area, and schedule the electricity consumption prediction model to identify the real-time load impact samples to determine the predicted electricity consumption of the energy supply area; Determine the remaining power of the energy storage system, and based on the remaining power and the predicted power consumption, determine the corresponding charging power of the energy storage system; Based on the charging power of the energy storage system, energy management is performed on the energy storage system to complete energy management of the energy storage system based on artificial intelligence; An artificial intelligence model is used to learn the data relationship between the historical load impact samples and their corresponding electricity consumption tags to obtain an electricity consumption prediction model, including: Randomly initialize the model parameters between the upper and lower limits of the artificial intelligence model to obtain the model parameter codes, and repeatedly obtain multiple different model parameter codes; Based on the historical load impact samples and their corresponding electricity consumption labels, obtain the fitness corresponding to all model parameter codes; Based on the fitness corresponding to the model parameter encoding, a multi-parameter adaptive local search mechanism is used to adaptively search the model parameter encoding to obtain the adaptively searched model parameter encoding. An adaptive collaborative search mechanism is used to perform a collaborative search on the model parameter encoding after the adaptive search, resulting in the model parameter encoding after the collaborative search. An adaptive number of mutation fusion mechanisms are used to perform mutation fusion search on the model parameter encoding after the cooperative search, resulting in the model parameter encoding after mutation fusion search. Repeat adaptive search, collaborative search, and mutation fusion search until the maximum number of training iterations is reached. Obtain the model parameter encoding after mutation fusion search and obtain the target optimal parameter encoding. Based on the target optimal parameter encoding, obtain the electricity consumption prediction model.

2. The energy management method for an artificial intelligence-based energy storage system according to claim 1, characterized in that, Collect historical electricity consumption correlation data corresponding to the energy supply area of ​​the energy storage system, and construct historical load impact samples and their corresponding electricity consumption tags based on the historical electricity consumption correlation data, including: Based on a preset data sampling frequency, historical electricity consumption, daily maximum temperature, daily minimum temperature, daily average temperature, daily season, date information, holiday information, and daily weather information are collected at multiple sampling time points for the energy supply area corresponding to the energy storage system, thus obtaining historical electricity consumption related data. Historical electricity consumption data at N consecutive sampling time points are collected to construct a historical load impact sample, and the historical electricity consumption at the N+1th sampling time point is used as the electricity consumption label.

3. The energy management method for an artificial intelligence-based energy storage system according to claim 1, characterized in that, Based on the fitness corresponding to the model parameter encoding, a multi-parameter adaptive local search mechanism is used to adaptively search the model parameter encoding to obtain the adaptively searched model parameter encoding, including: Based on the fitness corresponding to the model parameter encoding and the current number of training iterations, the adaptive speed adjustment factor is determined as follows: in, Indicates the first k Each model parameter is encoded with an adaptive speed adjustment factor. This represents the maximum value of the adaptive speed adjustment factor. Indicates the maximum number of training iterations. This indicates the current number of training iterations. This represents the fitness corresponding to the encoding of the k-th model parameter. This represents the maximum fitness among all encoded model parameters; Based on the fitness corresponding to the model parameter encoding and the current number of training iterations, the first local learning factor and the second local learning factor are determined as follows: in, Represents the first local learning factor. This represents the second local learning factor. Represents the cosine function. Represents pi; Based on the adaptive speed adjustment factor, the first local learning factor, and the second local learning factor, obtain the first... k The search speed corresponding to the encoding of each model parameter is: in, Indicates the first t During the training process, the first k The search speed corresponding to each model parameter encoding Indicates the first t +1 training session k The search speed corresponding to each model parameter encoding k =1,2,...,K, K This indicates the total number of model parameter codes. Represents the first random number between (0,1). This represents the second random number between (0,1). Indicates the first k Each model parameter is encoded with its corresponding historical best value. Indicates the first k Each model parameter is encoded. The model parameter encoding representing the maximum fitness; Based on the search speed, an adaptive search is performed on the model parameter encoding to obtain the adaptively searched model parameter encoding as follows: in, Indicates the first k The model parameters are encoded after an adaptive search.

4. The energy management method for an artificial intelligence-based energy storage system according to claim 3, characterized in that, An adaptive cooperative search mechanism is used to perform a cooperative search on the model parameter encoding after the adaptive search, resulting in the model parameter encoding after the cooperative search, including: For any dimension of the model parameters, the average value of the model parameters encoded by all the adaptive search models is calculated, and the average values ​​corresponding to all dimensions are constructed into a vector to obtain the center code; The model parameter codes after the adaptive search are arranged in ascending order of fitness to obtain the arranged model parameter codes. Based on the encoded model parameters after permutation, the first collaborative search factor and the second collaborative search factor are obtained as follows: in, Indicates the first i The first collaborative search factor is encoded by the model parameters after each permutation. Indicates the first i The second collaborative search factor is encoded by the model parameters after each permutation. sin Represents the sine function. cos Represents the cosine function. This represents the cooperative search direction control parameter, and , Represents a constant term. This represents a third random number between (0,1). This indicates the parameters controlling the scope of the collaborative search, and , Indicates the basic influence parameter of the search range. This represents the fourth random number between (0, 1); Indicates all Based on the current number of training iterations, the position perturbation factor is obtained as follows: in, Indicates the location disturbance factor. Represents pi (π). This represents the maximum value of the position disturbance factor. This represents the minimum value of the position disturbance factor. Indicates the maximum number of training iterations; Based on the center code, position perturbation factor, first cooperative search factor, and second cooperative search factor, a cooperative search is performed on the arranged model parameter codes to obtain the cooperatively searched model parameter codes as follows: in, Indicates the first i The model parameter encoding after permutation, i =1,2,...,K, K This indicates the total number of model parameter codes. Indicates the first i +1 permutation of model parameter encoding, and i When =K, then Encode the model parameters after random permutation. Indicates the first i Model parameter encoding after a collaborative search Indicates the center code.

5. The energy management method for an artificial intelligence-based energy storage system according to claim 4, characterized in that, An adaptive number of mutation fusion mechanisms is used to perform mutation fusion search on the model parameter encoding after the cooperative search, resulting in the model parameter encoding after mutation fusion search, including: Based on the fitness of the model parameters encoded after collaborative search, the number of adaptive mutation fusions is obtained as follows: in, Indicates the first m The number of adaptive mutation fusions corresponding to the model parameter encoding after each collaborative search. m =1,2,...,K, K This indicates the total number of model parameter codes. This represents the floor function. Indicates the first m The fitness of the model parameters after a collaborative search is encoded. This represents the maximum fitness among all encoded model parameters. This represents the minimum fitness among all the encoded model parameters; For the first m The model parameter encoding after each collaborative search is randomly selected. The model parameters are encoded after another collaborative search, resulting in... One variant fusion code; According to the above The model parameter codes after the cooperative search are subjected to mutation fusion search to obtain the model parameter codes after mutation fusion search as follows: in, Indicates the first m Model parameter encoding after a collaborative search Indicates the first m Model parameter encoding after mutation fusion search, This represents the fifth random number between (0,1). Represents model parameter encoding The corresponding number j One variant fusion code, This represents the encoding of the model parameters corresponding to the maximum fitness.

6. The energy management method for an artificial intelligence-based energy storage system according to claim 1, characterized in that, Collect real-time load impact samples of the energy supply area, and schedule the electricity consumption prediction model to identify the real-time load impact samples to determine the predicted electricity consumption of the energy supply area, including: Collect real-time load impact samples of the energy supply area; wherein, the data structure of the real-time load impact samples is the same as that of the historical load impact samples; The real-time load impact sample is used as input to the electricity consumption prediction model to obtain the predicted electricity consumption of the energy supply area.

7. The energy management method for an artificial intelligence-based energy storage system according to claim 6, characterized in that, Determining the remaining power of the energy storage system, and based on the remaining power and the predicted power consumption, determining the corresponding charging power of the energy storage system, including: Determine the remaining power of the energy storage system; The power difference is obtained based on the difference between the remaining power and the predicted power consumption; If the power difference is greater than or equal to zero, then the charging power corresponding to the energy storage system is determined to be the first preset charging power; When the power difference is less than zero, a second preset charging power corresponding to the power difference is determined; wherein, the second preset charging power is greater than the first preset charging power; different power differences are preset with different second preset charging powers, and the power difference is proportional to the second preset charging power, and both the first preset charging power and the second preset charging power are less than or equal to the rated charging power designed for the energy storage system.

8. The energy management method for an artificial intelligence-based energy storage system according to claim 7, characterized in that, Based on the charging power corresponding to the energy storage system, energy management of the energy storage system is performed, including: Based on the charging power corresponding to the energy storage system, the energy storage system is controlled to charge during a preset period; wherein, the preset period refers to the period when electricity prices are low.

9. An artificial intelligence-based energy management device for an energy storage system, wherein the artificial intelligence-based energy management device is capable of executing the artificial intelligence-based energy management method for an energy storage system as described in any one of claims 1 to 8, characterized in that, include: The system includes a data acquisition module, a data training module, a power consumption forecasting module, a charging determination module, and an energy management module. The data acquisition module is used to collect historical electricity consumption correlation data corresponding to the energy supply area of ​​the energy storage system, and to construct historical load impact samples and their corresponding electricity consumption labels based on the historical electricity consumption correlation data. The data training module is used to learn the data relationship between the historical load impact samples and their corresponding electricity consumption tags using an artificial intelligence model, so as to obtain an electricity consumption prediction model. The electricity consumption prediction module is used to collect real-time load impact samples of the energy supply area, and to schedule the electricity consumption prediction model to identify the real-time load impact samples and determine the predicted electricity consumption of the energy supply area. The charging determination module is used to determine the remaining power of the energy storage system and, based on the remaining power and the predicted power consumption, determine the charging power corresponding to the energy storage system. The energy management module is used to manage the energy of the energy storage system based on the charging power corresponding to the energy storage system, thereby completing the energy management of the energy storage system based on artificial intelligence.

Images