A novel energy storage assisted decision-making scheduling method and system

Abstract

The present invention discloses a new energy storage assisted decision-making scheduling method and system, belonging to the technical field of power grid scheduling. First, energy storage information of an energy storage power station is obtained; based on the energy storage information, battery information of energy storage batteries in the energy storage power station is determined, and an operation profile of each energy storage power station is constructed; based on the battery information and the operation profile, the capacity attenuation situation of the energy storage power station is predicted; power grid regulation and control are carried out, and based on the battery information and the operation profile, the response ability of the energy storage power station is evaluated; based on the evaluation result, a scheduling strategy for the energy storage power station by the power grid is determined; so as to optimize the maintenance plan, extend the battery life, and more accurately predict and optimize the performance of each power station. The present invention optimizes the scheduling strategy of the energy storage power station according to the response ability of the energy storage power station to power grid scheduling, improves the power grid safety, helps to realize full-capacity monitoring and attenuation prediction of the energy storage station, and further realizes the full-automatic calling of the energy storage power station, and improves the availability and income of the energy storage power station.

Description

Background Art

[0002] In the future, in order to cope with the access of 1.5 - 1.8 billion kilowatts of new energy, 150 million kilowatts of new energy storage (excluding pumped storage) need to be configured. These new energy storage facilities will be used to achieve power balance, energy balance, operation safety of the power system, and efficient consumption of new energy in the power system. With the passage of time, this demand will increase to more than 500 million kilowatts.

[0003] Large - scale energy storage power stations will become the main force for flexible regulation and auxiliary support of the new power system. These energy storage power stations need to have application scenarios such as active grid support, large - scale peak shaving, frequency modulation, and voltage regulation, and need to have the characteristics of intrinsic safety, modularity, and intelligence.

[0004] However, there are currently some problems in the call of energy storage systems. In most cases, data depends on the individual energy storage power station yards to report independently in advance, and this method cannot achieve the call of the full capacity of the whole station. This phenomenon of "built but not adjusted" has become a pain point in the market.

[0005] In addition, the grid connection and dispatching operation methods of new energy storage also need to be improved and strengthened. How to provide the optimal dispatching strategy for dispatching is the current technical difficulty. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a new energy storage auxiliary decision - making dispatching method and system for solving the technical problem that it is difficult to optimize the dispatching strategy of energy storage power stations in view of the above - mentioned deficiencies in the prior art.

[0007] The present invention adopts the following technical solutions:

[0008] A new energy storage auxiliary decision - making dispatching method includes the following steps:

[0009] Obtain the energy storage information of the energy storage power station, where the energy storage information includes the historical operation information, dispatching response information, reliability information, battery charge - discharge information, operation conditions, and battery characteristic data of the energy storage power station;

[0010] Based on the energy storage information, determine the battery information of the energy storage battery in the energy storage power station, and construct the operation portraits of each energy storage power station;

[0011] Predict the capacity attenuation of the energy storage power station based on the battery information and the operation portraits of each energy storage power station;

[0012] Carry out grid regulation, and evaluate the response ability of the energy storage power station based on the battery information and the operation portraits to obtain an evaluation result including the response speed. The grid regulation includes primary frequency modulation, automatic generation control, and automatic voltage control;

[0013] Allocate response weights to each energy storage power station based on the evaluation results, and issue power commands to the energy storage power stations based on the response weights and the predicted grid power demand; determine the charge and discharge strategies of the energy storage batteries in each energy storage power station according to the power demand, state of charge, and capacity attenuation of the power station.

[0014] Preferably, determining the battery information of the energy storage batteries in the energy storage power station specifically includes:

[0015] Perform data processing on the energy storage information of the energy storage power station to obtain multiple segments of historical energy storage information and current energy storage information;

[0016] Extract features from multiple segments of historical energy storage information and current energy storage information respectively to obtain multiple historical battery features and current battery features, and determine the historical battery health status corresponding to each historical battery feature;

[0017] Construct an initial battery health status determination model, and train the initial battery health status determination model through multiple historical battery features and their corresponding historical battery health statuses to obtain a battery health status determination model;

[0018] Input the current battery feature into the battery health status determination model to obtain battery information including the current battery health status and the predicted battery health status.

[0019] Preferably, the battery features include battery charge and discharge features and battery characteristic features; the battery health status determination model includes a multi-scale pooling module, a gating mechanism, a long short-term memory network module, an attention mechanism, and a gated residual network;

[0020] Input the battery charge and discharge features and the battery characteristic features into the multi-scale pooling module respectively to obtain a first operation feature and a first parameter feature; screen the first operation feature and the first parameter feature respectively through the gating mechanism to obtain a second operation feature and a second parameter feature; input the second operation feature and the second parameter feature into the long short-term memory network module to obtain battery features at multiple time scales; input the battery features at multiple time scales into the attention mechanism to obtain multi-scale battery features; input the multi-scale battery features into the gated residual network to obtain the current battery health status.

[0021] Preferably, the long short-term memory network module includes multiple long short-term memory networks, and different long short-term memory networks are used to process the second operation features with different time lengths and their corresponding second parameter features.

[0022] Preferably, the loss function of the battery health status determination model L is:

[0023]

[0024] where A represents the total number of training samples, Represents the training sample variable; Represents the adjustment coefficient; Represents the interval length of the state of charge into which the current battery health state falls; Represents the L2 norm; Represents the actual battery health state of the battery, which is a range value, Represents the maximum value of the actual battery health state; Represents the minimum value of the actual battery health state.

[0025] Preferably, the current battery health state SOHc Specifically:

[0026]

[0027] Among them, Represents the sigmoid activation function; , , And Respectively represent the first parameter, the second parameter, the third parameter and the fourth parameter, which are obtained through model training; Represents the intermediate variable of the battery health state; Represents the multi-scale battery characteristics; Represents normalization; Represents element-wise multiplication.

[0028] Preferably, predicting the battery health state is specifically:

[0029] Predict the future operation information in the future time period according to the historical operation information; construct the future battery characteristics based on the future operation information; input the future battery characteristics into the battery health state determination model to obtain the predicted battery health state.

[0030] Preferably, constructing the operation portrait of each energy storage power station is specifically:

[0031] Obtain grid information and new energy information;

[0032] Extract the energy storage information based on the grid information to obtain the time periods for peak shaving and valley filling and the time periods for adjusting the power of each energy storage power station;

[0033] Extract the energy storage information based on the new energy information and the grid load data to obtain the time periods for new energy consumption of each energy storage power station;

[0034] Calculate and analyze the charge and discharge efficiency, command response speed and charge and discharge power curve of each energy storage power station in each action period, and construct the regulation operation portrait;

[0035] Extract the sub-energy storage information of each energy storage power station respectively to obtain the charge and discharge conditions of each energy storage power station;

[0036] Based on the charge and discharge conditions of each energy storage power station, determine the change in charge state, charge and discharge capacity, and charge and discharge power curve during each charge and discharge process, and construct a charge and discharge operation profile.

[0037] Preferably, the grid information includes grid load data and grid frequency data; the new energy information includes new energy generation data.

[0038] Preferably, the action periods include the periods of peak shaving and valley filling, power regulation, and new energy consumption.

[0039] Preferably, predicting the capacity attenuation of the energy storage power station based on the battery information and the operation profile of each energy storage power station is specifically as follows:

[0040] For each energy storage battery:

[0041] Determine the maximum charge state and the minimum charge state during each charge and discharge process;

[0042] Based on the difference between the maximum charge state and the minimum charge state, determine the discharge amount of the energy storage battery during this charge and discharge process;

[0043] When the difference between the maximum charge state and the minimum charge state is greater than or equal to the preset charge state difference threshold, regard this charge and discharge as a reference charge and discharge, and determine the reference battery capacity attenuation situation through the capacity attenuation model;

[0044] When the difference between the maximum charge state and the minimum charge state is less than the preset charge state difference threshold, based on the previous reference battery capacity attenuation situation and the discharge amount, charge state change amount, ambient temperature, and discharge current during this charge and discharge process, determine the battery capacity attenuation situation;

[0045] For each energy storage power station:

[0046] Take the average value of the battery capacity attenuation situations of the energy storage batteries in the energy storage power station as the capacity attenuation situation of the energy storage power station.

[0047] Preferably, the capacity attenuation model is used to process the historical reference battery capacity attenuation situation and charge and discharge situation of the energy storage battery to obtain the current reference battery capacity attenuation situation.

[0048] Preferably, the battery capacity attenuation situation Dc is:

[0049]

[0050] wherein, represents the reference battery capacity attenuation situation; represents the charge state parameter; represents the current discharge amount of the energy storage battery; represents the current ambient temperature of the capacity correction factor; represents the reference discharge current; k represents the Peukert exponent; represents the charge state correction factor.

[0051] Preferably, the objective function of the power station power demand is:

[0052]

[0053] wherein, represents taking the minimum value; n represents the variable of the energy storage power station; N represents the total number of energy storage power stations; represents the response speed of the energy storage power station n; t represents the time variable; T represents the total predicted grid scheduling time; represents the power demand of the energy storage power station n at time t; represents the power demand of the energy storage power station n at time t - 1; represents taking the absolute value.

[0054] Preferably, the constraint conditions of the power station power demand are:

[0055]

[0056] wherein, represents the predicted grid power demand at time t;

[0057]

[0058] wherein, represents the maximum power change rate of the energy storage power station n;

[0059]

[0060] wherein, represents the minimum output power of the energy storage power station n; represents the maximum output power of the energy storage power station n;

[0061]

[0062]

[0063] wherein, represents the energy state of the energy storage power station n at time t; represents the energy state of the energy storage power station n at time t - 1; represents the discharge time interval; Indicates the charge-discharge efficiency; Indicates the lowest energy state of the energy storage power station n; Indicates the highest energy state of the energy storage power station n.

[0064] Preferably, the objective function of the charge-discharge strategy of the energy storage batteries in each energy storage power station is:

[0065]

[0066] Among them, Indicates finding the minimum value; m represents the energy storage battery variable; M represents the total number of energy storage batteries in this energy storage power station; Indicates the current battery capacity attenuation situation; Indicates the rated capacity of the energy storage battery; Indicates the state of charge of the energy storage battery m at time t; Indicates the energy state of the energy storage battery m at time t.

[0067] Preferably, the constraint conditions of the charge-discharge strategy of the energy storage batteries in each energy storage power station are:

[0068]

[0069] Among them, Indicates the battery charge-discharge power of the energy storage battery m in the energy storage power station n at time t; Indicates the power demand of the power station at time t in the energy storage power station n;

[0070]

[0071] Among them, Indicates the battery charge-discharge power of the energy storage battery m in the energy storage power station n at time t-1; Indicates the maximum power change rate of the energy storage battery m;

[0072]

[0073] Among them, Indicates the minimum output power of the energy storage battery m; Indicates the maximum output power of the energy storage battery m;

[0074]

[0075] Among them, Indicates the lower limit of the state of charge of the energy storage battery; Indicates the upper limit of the state of charge of the energy storage battery.

[0076] In a second aspect, an embodiment of the present invention provides a new energy storage auxiliary decision-making and dispatching system, including:

[0077] An acquisition module that acquires the energy storage information of an energy storage power station, where the energy storage information includes the historical operation information, dispatching response information, reliability information, battery charge and discharge information, operating conditions, and battery characteristic data of the energy storage power station;

[0078] An information module that determines the battery information of the energy storage battery in the energy storage power station based on the energy storage information and constructs an operation portrait of each energy storage power station;

[0079] A prediction module that predicts the capacity attenuation of the energy storage power station based on the battery information and the operation portraits of each energy storage power station;

[0080] A regulation module that conducts power grid regulation and evaluates the response ability of the energy storage power station based on the battery information and the operation portrait to obtain an evaluation result including the response speed. The power grid regulation includes primary frequency modulation, automatic generation control, and automatic voltage control;

[0081] An output module that assigns a response weight to each energy storage power station based on the evaluation result, and issues a power command to the energy storage power station based on the response weight and the predicted power grid power demand; determines the charge and discharge strategy of the energy storage battery in each energy storage power station according to the power demand, state of charge, and capacity attenuation of the energy storage power station.

[0082] In a third aspect, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned new energy storage auxiliary decision-making and dispatching method are implemented.

[0083] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium including a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned new energy storage auxiliary decision-making and dispatching method are implemented.

[0084] In a fifth aspect, a chip includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned new energy storage auxiliary decision-making and dispatching method are implemented.

[0085] In a sixth aspect, an embodiment of the present invention provides an electronic device including a computer program, and when the computer program is executed by the electronic device, the steps of the above-mentioned new energy storage auxiliary decision-making and dispatching method are implemented.

[0086] Compared with the prior art, the present invention has at least the following beneficial effects:

[0087] A new energy storage auxiliary decision-making and scheduling method can more accurately predict the capacity attenuation of energy storage power stations and evaluate the response capabilities of energy storage power stations by collecting detailed energy storage information of energy storage power stations; optimize the scheduling strategies of energy storage power stations to improve the operating efficiency of energy storage power stations; determine the charge and discharge strategies of energy storage batteries in each energy storage power station according to the power demand, state of charge, and capacity attenuation of the energy storage power stations, enabling energy storage power stations to better adapt to the needs of the power grid, and improving the reliability and stability of the power grid; by assigning response weights to each energy storage power station and issuing power commands to energy storage power stations based on the response weights and predicted power grid power demands, ensuring the maximization of the utilization efficiency of energy storage power stations, it can reduce the operating costs of energy storage power stations and improve economic benefits; by carrying out power grid regulation, including primary frequency modulation, automatic generation control, and automatic voltage control, the operating conditions of the power grid can be improved. The stability and power supply quality of the power grid can be enhanced to provide better services for users; it can better adapt to the volatility characteristics of new energy and improve the consumption capacity of new energy. This helps to reduce energy waste and promote energy transformation and sustainable development.

[0088] Furthermore, by collecting and processing the energy storage information of energy storage power stations, using historical data for feature extraction and model training, a battery health state determination model can be obtained, which fully utilizes the advantages of data-driven and can more accurately predict the health state of the battery; by inputting the current battery characteristics into the battery health state determination model, battery information on the current battery health state and the predicted battery health state can be obtained; enabling energy storage power station operators to timely understand the health status of the battery, through the prediction of the battery health state, potential problems can be discovered in advance, early warnings can be issued, and corresponding maintenance plans can be formulated, which helps to reduce the probability of failures, extend the battery life, and reduce the operating costs of energy storage power stations; by obtaining the battery health state information, adjusting the charge and discharge strategies according to the actual situation of the battery, optimizing the operation of energy storage power stations, and improving the operating efficiency and reliability of energy storage power stations; by analyzing the energy storage information and predicting the battery health state, it provides a reference basis for the planning and design of energy storage power stations.

[0089] Furthermore, through the multi-scale pooling module, battery features at different time scales are extracted from the battery charge and discharge features and battery characteristic features, so as to better capture the dynamic changes and long-term trends of the battery; through the gating mechanism, the extracted features are screened to remove redundancy and noise, and retain the features useful for predicting the battery health state, improving the prediction accuracy of the model; through the long short-term memory network module, the time dependence of battery features can be captured, so as to better predict the battery health state; through the attention mechanism, the features more important for predicting the battery health state at different time scales can be highlighted, further improving the prediction accuracy of the model; through the gated residual network, the battery health state can be effectively predicted, providing strong support for the operation and maintenance of the energy storage power station; by accurately predicting the battery health state, potential problems can be discovered in advance, early warnings can be issued, and corresponding maintenance plans can be formulated, thereby reducing the maintenance cost and the probability of failures.

[0090] Furthermore, by using historical operation information, the battery health state in a future time period can be predicted, so as to discover potential problems in advance, issue early warnings, and formulate corresponding maintenance plans; by predicting the future battery health state, maintenance personnel and equipment can be arranged in advance to avoid losses caused by emergency repairs and outages, and improve the maintenance efficiency; by predicting the future battery health state, the operation plan of the energy storage power station can be formulated in advance, the charge and discharge strategy can be optimized, and the operation efficiency and reliability of the energy storage power station can be improved; by predicting the future battery health state, problems such as battery aging and performance degradation can be discovered in time, and corresponding measures can be taken to extend the battery service life and reduce the operation cost of the energy storage power station; by predicting the future battery health state, potential safety hazards can be discovered in advance, and corresponding measures can be taken to ensure the safe operation of the energy storage power station and reduce the accident risk.

[0091] Furthermore, by obtaining grid information and new energy information, the operation conditions of the grid and new energy can be better understood, so as to more accurately determine the time periods for the energy storage power station to perform peak shaving and valley filling and new energy consumption, and optimize the dispatching strategy of the energy storage power station; by extracting and analyzing energy storage information, indicators such as the charge and discharge efficiency, command response speed, and charge and discharge power curve of the energy storage power station can be better understood, so as to better play the role of the energy storage power station and improve the utilization rate of the energy storage power station; by constructing a regulation operation profile and a charge and discharge operation profile, the operation characteristics of the energy storage power station can be accurately depicted, providing strong support for the operation and maintenance of the energy storage power station; by analyzing the charge and discharge conditions of the energy storage power station, the usage of the battery can be better understood, so as to better formulate the battery maintenance plan and reduce the operation cost of the energy storage power station; by optimizing the dispatching strategy of the energy storage power station and improving the utilization rate of the energy storage power station, the reliability and stability of the grid can be improved, providing better services for users.

[0092] Furthermore, by considering the difference between the maximum charge state and the minimum charge state during the charge and discharge process, the capacity attenuation of the battery can be predicted more accurately, thereby better formulating the battery maintenance plan and the operation strategy of the energy storage power station. When determining the capacity attenuation of the battery, factors such as the discharge amount, the change amount of the charge state, the environmental temperature, and the discharge current are comprehensively considered, so as to more comprehensively evaluate the capacity attenuation of the battery. By taking the average value of the capacity attenuation of the energy storage battery as the capacity attenuation of the energy storage power station, the calculation process can be simplified and the calculation complexity can be reduced. By evaluating the capacity attenuation of the energy storage power station, the operation status of the energy storage power station can be better understood, providing strong support for the operation and maintenance of the energy storage power station. By accurately predicting the capacity attenuation of the battery, the operation strategy of the energy storage power station can be better formulated, improving the operation efficiency and reliability of the energy storage power station, and providing strong support for the stable and reliable operation of the power grid.

[0093] It can be understood that the beneficial effects of the second to fourth aspects above can refer to the relevant descriptions in the first aspect above, and will not be elaborated here.

[0094] In summary, the present invention optimizes the dispatching strategy of the energy storage power station according to the response ability of the energy storage power station to the power grid dispatching, improves the power grid safety, helps to realize the full-capacity monitoring and attenuation prediction of the energy storage station, and then realizes the full-automatic calling of the energy storage power station, improving the availability and revenue of the energy storage power station.

[0095] The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 It is an exemplary flowchart of a new energy storage auxiliary decision-making dispatching method provided by the present invention;

[0097] Figure 2 It is a schematic diagram of a computer device provided by an embodiment of the present invention;

[0098] Figure 3 It is a block diagram of a chip provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0099] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0100] In the description of the present invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0101] It should also be understood that the terms used in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0102] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the present invention, the character " / " generally indicates that the objects before and after are in an "or" relationship.

[0103] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present invention to describe preset ranges, etc., these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0104] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detected (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0105] Schematic diagrams of various structures according to the disclosed embodiments of the present invention are shown in the drawings. These figures are not drawn to scale, where certain details are enlarged for the purpose of clear expression, and certain details may be omitted. The shapes of the various regions and layers shown in the figures and their relative sizes and positional relationships are merely exemplary, and may actually deviate due to manufacturing tolerances or technical limitations. Those skilled in the art can additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0106] The present invention provides a new energy storage assisted decision-making and dispatching method, which acquires the energy storage information of an energy storage power station; determines the battery information of the energy storage batteries in the energy storage power station based on the energy storage information, and constructs the operation portraits of each energy storage power station; predicts the capacity attenuation of the energy storage power station based on the battery information and the operation portraits; conducts power grid regulation, and evaluates the response ability of the energy storage power station based on the battery information and the operation portraits; determines the dispatching strategy of the power grid for the energy storage power station based on the evaluation results; so as to optimize the maintenance plan, extend the battery life, and more accurately predict and optimize the performance of each power station.

[0107] Please refer to Figure 1 , a new energy storage assisted decision-making and dispatching method of the present invention includes the following steps:

[0108] S1. Acquire the energy storage information of the energy storage power station;

[0109] The energy storage information refers to various information related to the energy storage of the energy storage power station, and the energy storage information includes the historical operation information, dispatching response information, reliability information, battery charge and discharge information, operation conditions and battery characteristic data of the energy storage power station.

[0110] The historical operation information refers to the operation status and performance data of the energy storage battery in the past period of time; the historical operation information includes the charge and discharge data of the power station, the power grid interaction data, the environmental data, and the fault and alarm records, etc.

[0111] The dispatching response information refers to the reaction and execution situation of the energy storage system according to the power grid dispatching instruction; the dispatching response information may include the response time, the ramp rate, the accuracy (the matching degree between the actual output and the instruction requirement), the duration (the time that can maintain the specified output), and the availability (the time ratio that can respond to the dispatching instruction), etc.

[0112] The reliability information is used to evaluate the performance, stability and availability of the energy storage power station; the evaluation indexes of reliability may include availability, mean time between failures, mean time to repair, reliability and responsiveness, etc.

[0113] The battery charge and discharge information refers to the information related to the charge and discharge of the energy storage battery in the energy storage power station; the battery charge and discharge information includes the total charge and discharge power, the system voltage and current, the overall state of charge, the charge and discharge efficiency, the available capacity, the response time, the temperature distribution and the battery pack balance state, etc.

[0114] The operation conditions refer to the operation status and modes of the energy storage power station under different conditions and demands; the operation conditions include peak-valley filling, frequency regulation, voltage support, renewable energy smoothing, reserve capacity and demand response, etc.

[0115] Battery characteristic data refers to a series of quantitative indicators that describe the performance, behavior, and characteristics of a battery. Battery characteristic data includes capacity characteristics, charge and discharge characteristics, cycle life characteristics, temperature characteristics, self-discharge characteristics, internal resistance characteristics, power characteristics, and efficiency characteristics, etc.

[0116] S2. Determine the battery information of the energy storage battery in the energy storage power station based on the energy storage information;

[0117] Battery information refers to information related to the battery, including the current battery health status and the predicted battery health status.

[0118] The current battery health status refers to the health status of the energy storage battery at the current time;

[0119] The predicted battery health status refers to the predicted health status of the energy storage battery at a future time.

[0120] Determine the current battery health status of the energy storage battery in the energy storage power station, including:

[0121] S201. Perform data processing on the energy storage information to obtain multiple segments of historical energy storage information and current energy storage information;

[0122] Historical energy storage information refers to the operation information of the energy storage power station obtained historically. Multiple segments of historical energy storage information are obtained by dividing the historical time at time intervals; current energy storage information refers to the operation information of the current energy storage power station.

[0123] The current energy storage information includes the information of the energy storage power station at the current moment. By splicing the information of the energy storage power station at the current moment with the information at the historical moment, current energy storage information with the same time interval as the length of the historical energy storage information is obtained. Of course, the current energy storage information may not overlap with the historical energy storage information, and only the nearest energy storage information with the same time interval as the historical energy storage information is used as the current energy storage information.

[0124] S202. Respectively perform feature extraction on multiple segments of historical energy storage information and current energy storage information to obtain multiple historical battery features and current battery features;

[0125] Battery features include battery charge and discharge information and battery characteristic data. By extracting the battery charge and discharge information and battery characteristic data at the historical moment, historical battery features are obtained. Similarly, by extracting the current battery charge and discharge information and battery characteristics, current battery features are obtained.

[0126] S203. Determine the historical battery health status corresponding to each historical battery feature;

[0127] The historical battery health status refers to the battery health status of the battery in the past time, and the historical battery health status is obtained by testing and calculating the battery.

[0128] S204. Construct an initial battery health state determination model, and train the initial battery health state determination model through multiple historical battery characteristics and corresponding historical battery health states to obtain a battery health state determination model;

[0129] The initial battery health state determination model is used to generate a battery health state determination model through machine model training.

[0130] The battery health state determination model is used to determine the current health state of the battery through the current battery characteristics.

[0131] The battery characteristics include battery charge and discharge characteristics and battery property characteristics. The battery health state determination model includes a multi-scale pooling module, a gating mechanism, a long short-term memory network module, an attention mechanism, and a gated residual network.

[0132] S204. Input the battery charge and discharge characteristics and battery property characteristics into the multi-scale pooling module respectively to obtain a first operation feature and a first parameter feature; screen the logarithm features through the gating mechanism respectively to obtain a second operation feature and a second parameter feature; input the second operation feature and the second parameter feature into the long short-term memory network module to obtain battery characteristics of multiple time scales; input the battery characteristics of multiple time scales into the attention mechanism to obtain multi-scale battery characteristics; input the multi-scale battery characteristics into the gated residual network to obtain the current battery health state;

[0133] The long short-term memory network module includes multiple long short-term memory networks, and different long short-term memory networks are used to process the second operation features of different time lengths and their corresponding second parameter features.

[0134] The expression of the current battery health state is:

[0135]

[0136]

[0137] The loss function of the battery health state determination model is:

[0138]

[0139] Among them, represents the current battery health state; represents the sigmoid activation function; 、 、 and respectively represent the first parameter, the second parameter, the third parameter, and the fourth parameter, which are obtained through model training; represents an intermediate variable of the battery health state; represents the multi-scale battery characteristics; Indicates normalization; Indicates element-wise multiplication; Indicates the loss function; A represents the total number of training samples, Indicates the training sample variable; Indicates the adjustment coefficient; Indicates the length of the state-of-charge interval in which the current battery health state falls; Indicates the L2 norm; Indicates the actual battery health state of the battery, which is a range value, Indicates the maximum value of the actual battery health state; Indicates the minimum value of the actual battery health state.

[0140] S205. Input the current battery characteristics into the battery health state determination model to obtain the current battery health state;

[0141] S206. Determine the predicted battery health state of the energy storage batteries in the energy storage power station, including: predicting the future operation information in a future time period based on historical operation information; constructing future battery characteristics based on the future operation information; inputting the future battery characteristics into the battery health state determination model to obtain the predicted battery health state.

[0142] The future operation information refers to the operation information of the energy storage power station in a future time period. The future battery characteristics can at least include the predicted battery charge and discharge characteristics and battery characteristic characteristics of the energy storage power station in a future time period.

[0143] S3. Construct the operation portraits of each energy storage power station based on the energy storage information;

[0144] The operation portraits are used to describe and analyze the operation characteristics of the energy storage power stations; including grid information, new energy information, and energy storage information, etc. Constructing the operation portraits of each energy storage power station includes:

[0145] S301. Obtain the grid information and new energy information;

[0146] The grid information includes grid load data and grid frequency data; the new energy information includes new energy generation data.

[0147] S302. Extract the energy storage information based on the grid information to obtain the time periods for peak shaving and valley filling and the time periods for regulating power of each energy storage power station; extract the energy storage information based on the new energy information and grid load data to obtain the time periods for new energy consumption of each energy storage power station;

[0148] S303. Calculate and analyze the charge and discharge efficiency, command response speed, and charge and discharge power curves of each energy storage power station in each action time period, and construct the regulation operation portraits;

[0149] The operation periods include the time periods for peak shaving and valley filling, power regulation, and new energy accommodation.

[0150] S304. Respectively extract the sub-energy storage information of each energy storage power station to obtain the charge and discharge conditions of each energy storage power station;

[0151] The sub-energy storage information refers to the energy storage information of a single energy storage power station.

[0152] S305. Based on the charge and discharge conditions of each energy storage power station, determine the change in charge state, charge and discharge capacity, and charge and discharge power curve during each charge and discharge process, and construct a charge and discharge operation portrait.

[0153] S4. Based on the battery information and the operation portrait, predict the capacity attenuation of the energy storage power station;

[0154] The capacity attenuation situation refers to the situation where the actual available capacity of the energy storage power station gradually decreases over time and with an increase in the number of uses. The capacity attenuation situation can be expressed as a percentage, for example, 90%, 80%, etc. of the initial capacity. Predicting the capacity attenuation situation of the energy storage power station includes:

[0155] For each energy storage battery:

[0156] S401. Determine the maximum charge state and the minimum charge state during each charge and discharge process;

[0157] The maximum charge state refers to the minimum value between the charge state at the start of discharge and the charge state at the end of charge; the minimum charge state refers to the maximum value between the charge state at the start of charge and the charge state at the end of discharge.

[0158] S402. Based on the difference between the maximum charge state and the minimum charge state, determine the discharge amount of the energy storage battery during this charge and discharge process;

[0159] S403. When the difference between the maximum charge state and the minimum charge state is greater than or equal to the preset charge state difference threshold, regard this charge and discharge as a reference charge and discharge, and determine the reference battery capacity attenuation situation through the capacity attenuation model;

[0160] The capacity attenuation model is used to process the historical reference battery capacity attenuation situation and charge and discharge situation of the energy storage battery to obtain the current reference battery capacity attenuation situation.

[0161] The preset charge state difference threshold refers to the preset difference in the charge state change of the energy storage battery.

[0162] S4031. When the charge state change is greater than the preset charge state difference threshold, regard this charge and discharge as a complete charge and discharge, which has a certain reference value, and perform capacity attenuation prediction;

[0163] S4032. When the change in charge state is less than the preset charge state difference threshold, it indicates that the current discharge is a partial discharge, and the error may be relatively serious and not very referenceable.

[0164] The reference charge and discharge refers to the reference standard for subsequent partial discharge.

[0165] The capacity attenuation model is obtained by training with the experimental data of the battery. Since the actual capacity of the battery will decay during use, directly using the rated capacity to calculate the current capacity of the battery will cause a large error. Therefore, using the relatively accurate reference battery capacity attenuation situation to predict the battery capacity attenuation situation at the current time that is closer in time to it can improve the accuracy of subsequent calculations. Therefore, the reference battery capacity attenuation situation refers to the battery capacity attenuation situation of the reference standard for subsequent partial charge and discharge.

[0166] S404. When the difference between the maximum charge state and the minimum charge state is less than the preset charge state difference threshold, based on the previous reference battery capacity attenuation situation and the discharge amount, charge state change amount, ambient temperature, and discharge current during this charge and discharge process, determine the battery capacity attenuation situation.

[0167] The expression for the capacity attenuation situation is:

[0168]

[0169]

[0170] Among them, represents the current battery capacity attenuation situation; represents the reference battery capacity attenuation situation; represents the charge state parameter; represents the current discharge amount of the energy storage battery; represents the current ambient temperature of the capacity correction factor; represents the reference discharge current; k represents the Peukert exponent; represents the charge state correction factor; represents the reference charge state change value; represents the current charge state change value.

[0171] For each energy storage power station:

[0172] Take the average value of the battery capacity attenuation situations of the energy storage batteries in the energy storage power station as the capacity attenuation situation of the energy storage power station.

[0173] S5. Carry out grid regulation, and based on the battery information and operation profile, evaluate the response ability of the energy storage power station to obtain the response speed;

[0174] Grid regulation refers to the method of adjusting and controlling the systems within the power grid to ensure its stable operation, including primary frequency regulation, automatic generation control (AGC), and automatic voltage control (AVC).

[0175] Response ability refers to the speed and contribution of energy storage batteries to participate in grid regulation, including response speed, new energy consumption contribution, peak shaving contribution, frequency modulation contribution, and grid stability contribution.

[0176] Response speed refers to the time interval from when the energy storage battery receives a regulation command to when it reaches the required output;

[0177] New energy consumption contribution refers to the change in the acceptance and use of new energy power generation by the power system through energy storage batteries.

[0178] Frequency modulation contribution represents the ability of the energy storage power station to participate in grid frequency modulation.

[0179] Grid stability contribution can be used to represent the contribution made by the energy storage power station to grid stability (such as peak shaving and valley filling volume, etc.).

[0180] Evaluate the response ability of the energy storage power station:

[0181] S501. Construct the response curve of the energy storage power station, the grid load curve, and the new energy power generation curve;

[0182] S502. Determine the response speed and new energy consumption contribution of the energy storage power station based on the response curve of the energy storage power station, the grid load curve, and the new energy power generation curve;

[0183] S503. Determine the peak shaving contribution based on the difference between the output peak after adding the energy storage power station and the original peak;

[0184] S504. Determine the frequency modulation contribution based on the adjustment speed and difference between the actual grid frequency and the original grid frequency after adding the energy storage power station;

[0185] S505. Determine the grid stability contribution based on the difference between the actual grid response curve and the original grid response curve.

[0186] S6. Allocate response weights to each energy storage power station based on the response speed. Based on the response weights and the predicted grid power demand, send power commands to the energy storage power stations. The power commands include the power demand of each power station. Determine the charge and discharge strategies of the energy storage batteries in each energy storage power station according to the power demand of the power station, the state of charge, and the capacity attenuation of the energy storage power station. Evaluate the response capabilities of the energy storage power stations through battery information and operation portraits, and determine the strategies for the grid to adjust the energy storage power stations based on the evaluation results. While optimizing the maintenance plan and extending the battery life, accurately predict and optimize the performance of each power station. Through the prediction of the capacity attenuation of the batteries and the power stations, the reliability and efficiency of the system can be ensured, maintenance is facilitated, and the risk of failure shutdown is reduced.

[0187] S601. Allocate response weights to each energy storage power station based on the evaluation results;

[0188] The evaluation results include the response speed. The response weight refers to the weight obtained according to the response speed of the energy storage power station. The faster the response speed of the power station, the more it can improve the flexibility of the grid and accelerate the grid regulation.

[0189] S602. Based on the response weights and the predicted grid power demand, send power commands to the energy storage power stations;

[0190] The power commands include the power demand of each power station.

[0191] The predicted grid power demand refers to the grid power demand in the future time period predicted based on the historical grid load.

[0192] The power commands are used to instruct the energy storage power stations to act, including the power demand of the power station, the charge and discharge power, and the charge and discharge time, etc.

[0193] The objective function of the power demand of the power station is:

[0194]

[0195] Among them, represents taking the minimum value; n represents the energy storage power station variable; N represents the total number of energy storage power stations; represents the response speed of the energy storage power station n; t represents the time variable; T represents the total predicted grid dispatching time; represents the power demand of the power station n at time t; represents the power demand of the power station n at time t - 1; represents taking the absolute value;

[0196] The constraint conditions of the power demand of the power station are:

[0197]

[0198] Among them, represents the predicted grid power demand at time t;

[0199]

[0200] Among them, represents the maximum power change rate of energy storage power station n;

[0201]

[0202] Among them, represents the minimum output power of energy storage power station n; represents the maximum output power of energy storage power station n;

[0203]

[0204]

[0205] Among them, represents the energy state of energy storage power station n at time t; represents the energy state of energy storage power station n at time t - 1; represents the discharge time interval; represents the charge-discharge efficiency; represents the lowest energy state of energy storage power station n; represents the highest energy state of energy storage power station n.

[0206] S603. Determine the charge-discharge strategies of the energy storage batteries in each energy storage power station according to the power demand, charge state, and capacity attenuation of the energy storage power station.

[0207] The objective function of the charge-discharge strategies of the energy storage batteries in each energy storage power station is:

[0208]

[0209] Among them, represents finding the minimum value; m represents the energy storage battery variable; M represents the total number of energy storage batteries in this energy storage power station; represents the current battery capacity attenuation; represents the rated capacity of the energy storage battery; represents the charge state of energy storage battery m at time t; represents the energy state of energy storage battery m at time t;

[0210] The constraint conditions of the charge-discharge strategies of the energy storage batteries in each energy storage power station are:

[0211]

[0212] Among them, Indicates the battery charge and discharge power of the energy storage battery m in the energy storage power station n at time t; Indicates the power demand of the energy storage power station n at time t;

[0213]

[0214] Among them, Indicates the battery charge and discharge power of the energy storage battery m in the energy storage power station n at time t-1; Indicates the maximum power change rate of the energy storage battery m;

[0215]

[0216] Among them, Indicates the minimum output power of the energy storage battery m; Indicates the maximum output power of the energy storage battery m;

[0217]

[0218] Among them, Indicates the lower limit of the charge state of the energy storage battery; Indicates the upper limit of the charge state of the energy storage battery.

[0219] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, method, or program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module", or "platform" here.

[0220] In another embodiment of the present invention, a new energy storage auxiliary decision-making and dispatching system is provided. This system can be used to implement the above-mentioned new energy storage auxiliary decision-making and dispatching method. Specifically, the new energy storage auxiliary decision-making and dispatching system includes an acquisition module, an information module, a prediction module, a regulation module, and an output module.

[0221] Among them, the acquisition module acquires the energy storage information of the energy storage power station. The energy storage information includes the historical operation information, dispatching response information, reliability information, battery charge and discharge information, operating conditions, and battery characteristic data of the energy storage power station;

[0222] The information module determines the battery information of the energy storage battery in the energy storage power station based on the energy storage information and constructs the operation portraits of each energy storage power station;

[0223] The prediction module predicts the capacity attenuation of the energy storage power station based on the battery information and the operation portraits of each energy storage power station;

[0224] A regulation module conducts power grid regulation and evaluates the response capabilities of energy storage power stations based on battery information and operation profiles to obtain evaluation results including response speed. The power grid regulation includes primary frequency modulation, automatic generation control, and automatic voltage control;

[0225] An output module assigns response weights to each energy storage power station based on the evaluation results, and issues power commands to the energy storage power stations based on the response weights and predicted power grid power demands; determines the charge-discharge strategies of the energy storage batteries in each energy storage power station according to the power demands, state of charge, and capacity attenuation of the energy storage power stations.

[0226] In another embodiment of the present invention, a terminal device is provided. The terminal device includes a processor and a memory. The memory is used to store a computer program. The computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, graphics processing units (GPUs), tensor processing units (TPUs), digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the new energy storage auxiliary decision-making scheduling method, including:

[0227] Obtain the energy storage information of the energy storage power station, where the energy storage information includes the historical operation information, dispatching response information, reliability information, battery charge and discharge information, operating conditions, and battery characteristic data of the energy storage power station; determine the battery information of the energy storage battery in the energy storage power station based on the energy storage information, and construct the operation portraits of each energy storage power station; predict the capacity attenuation of the energy storage power station based on the battery information and the operation portraits of each energy storage power station; carry out power grid regulation, and evaluate the response ability of the energy storage power station based on the battery information and the operation portraits to obtain an evaluation result including the response speed, where the power grid regulation includes primary frequency modulation, automatic generation control, and automatic voltage control; allocate response weights to each energy storage power station based on the evaluation result, and issue power commands to the energy storage power station based on the response weights and the predicted power grid power demand; determine the charge and discharge strategies of the energy storage batteries in each energy storage power station according to the power demand of the power station, the state of charge, and the capacity attenuation of the energy storage power station.

[0228] Please refer to Figure 2 , the terminal device is a computer device. The computer device 60 in this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, it implements the new energy storage auxiliary decision-making dispatching method in the embodiment. To avoid repetition, it will not be elaborated here one by one. Alternatively, when the computer program 63 is executed by the processor 61, it implements the functions of each model / unit in the new energy storage auxiliary decision-making dispatching system in the embodiment. To avoid repetition, it will not be elaborated here one by one.

[0229] The computer device 60 is a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art can understand that Figure 2 These are only examples of the computer device 60 and do not constitute a limitation on the computer device 60. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.

[0230] The so-called processor 61 is a central processing unit (CPU), or other general-purpose processors, a graphics processing unit (GPU), a tensor processing unit (TPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor is a microprocessor or the like, or any conventional processor.

[0231] The memory 62 is an internal storage unit of the computer device 60, such as the hard disk or memory of the computer device 60. The memory 62 can also be an external storage device of the computer device 60, such as a plug-in hard disk equipped on the computer device 60, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0232] Furthermore, the memory 62 can also include both the internal storage unit of the computer device 60 and the external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 can also be used to temporarily store data that has been output or will be output.

[0233] Please refer to Figure 3 , the terminal device is a chip. The chip 600 in this embodiment includes a processor 622, the number of which can be one or more, and a memory 632 for storing computer programs executable by the processor 622. The computer programs stored in the memory 632 can include one or more modules each corresponding to a set of instructions. In addition, the processor 622 can be configured to execute the computer program to perform the above-mentioned new energy storage assisted decision-making scheduling method.

[0234] In addition, the chip 600 can also include a power supply component 626 and a communication component 650. The power supply component 626 can be configured to perform power management of the chip 600, and the communication component 650 can be configured to implement communication of the chip 600, for example, wired or wireless communication. In addition, the chip 600 can also include an input / output interface 658. The chip 600 can operate based on the operating system stored in the memory 632.

[0235] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium. The computer-readable storage medium is a memory device in a terminal device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. Moreover, in this storage space, one or more instructions suitable for being loaded and executed by a processor are also stored, and these instructions are one or more computer programs. It should be noted that the computer-readable storage medium here is neither a high-speed RAM memory nor an unstable memory (Non-Volatile Memory), such as at least one disk memory.

[0236] One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the novel energy storage auxiliary decision-making scheduling method in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps:

[0237] Obtain the energy storage information of the energy storage power station, where the energy storage information includes the historical operation information, dispatching response information, reliability information, battery charge and discharge information, operating conditions, and battery characteristic data of the energy storage power station; determine the battery information of the energy storage battery in the energy storage power station based on the energy storage information, and construct the operation portraits of each energy storage power station; predict the capacity attenuation of the energy storage power station based on the battery information and the operation portraits of each energy storage power station; carry out power grid regulation, and evaluate the response ability of the energy storage power station based on the battery information and the operation portraits to obtain an evaluation result including the response speed, and the power grid regulation includes primary frequency modulation, automatic generation control, and automatic voltage control; allocate response weights to each energy storage power station based on the evaluation result, and issue power commands to the energy storage power station based on the response weights and the predicted power grid power demand; determine the charge and discharge strategies of the energy storage batteries in each energy storage power station according to the power demand, state of charge, and capacity attenuation of the energy storage power station.

[0238] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0239] To verify the effectiveness of the new energy storage auxiliary decision-making scheduling method, a simulation experiment was conducted.

[0240] The experimental data was sourced from the actual operation data of a certain energy storage power station, including the historical operation information, dispatching response information, reliability information, battery charge and discharge information, operating conditions, and battery characteristic data of the energy storage power station. Using the Python programming language and the PyTorch deep learning framework, a prediction model for the health state of energy storage batteries was built, including a multi-scale pooling module, a gating mechanism, a long short-term memory network module, an attention mechanism, and a gated residual network.

[0241] The experimental results show that the new energy storage auxiliary decision-making scheduling method has obvious advantages over the traditional scheduling method in terms of the operation efficiency and reliability of the energy storage power station.

[0242] Specifically, the new energy storage auxiliary decision-making scheduling method has shown good performance in aspects such as the capacity decay prediction of the energy storage power station, the response ability of the energy storage power station, and the formulation of dispatching strategies. For example, in terms of the capacity decay prediction of the energy storage power station, the prediction error of the new energy storage auxiliary decision-making scheduling method is reduced by about 30% compared with the traditional scheduling method, which indicates that the new energy storage auxiliary decision-making scheduling method can more accurately predict the capacity decay of energy storage batteries, thereby more reasonably arranging the charge and discharge strategies of the energy storage power station and improving the operation efficiency and reliability of the energy storage power station.

[0243] In addition, the new energy storage auxiliary decision-making scheduling method has also achieved good results in practical applications. For example, in the actual operation of a certain energy storage power station, the new energy storage auxiliary decision-making scheduling method was used for dispatching, and it was found that the operation efficiency and reliability of the energy storage power station were significantly improved. The average charging efficiency of the energy storage power station increased by about 10%, the average discharge efficiency increased by about 8%, and the average availability increased by about 5%.

[0244] In summary, for the novel energy storage-assisted decision-making scheduling method and system of the present invention, on the one hand, it can improve the project revenue of power generation groups and the enthusiasm of power generation groups to participate in the construction of energy storage resources, indirectly improving the construction quality and operation and maintenance level of energy storage stations; on the other hand, it can enrich the grid balancing and regulation means in the region, support the safe and stable operation of the grid, and contribute to the construction of a new power system.

[0245] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit exists physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be repeated here.

[0246] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0247] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0248] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal and method can be implemented in other ways. For example, the device / terminal embodiments described above are only illustrative. For example, the division of the module or unit is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other is through some interfaces, and the indirect coupling or communication connection of the device or unit is in an electrical, mechanical or other form.

[0249] The unit described as a separation component may not be physically separated, and the component displayed as a unit may not be a physical unit either, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0250] In addition, each functional unit in various embodiments of the present invention can be integrated into a processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0251] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0252] This application is described with reference to the flowcharts and / or block diagrams of methods, devices, and computer program products according to the embodiments of this application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented 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, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0253] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more processes and / or blocks Figure 1 in a process or processes and / or blocks Figure 1 specified in the block or blocks.

[0254] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more processes and / or blocks Figure 1 in a process or processes and / or blocks Figure 1 specified in the block or blocks.

[0255] The above is only to illustrate the technical idea of the present invention and should not be used to limit the protection scope of the present invention. Any modification made on the basis of the technical solution according to the technical idea proposed by the present invention falls within the protection scope of the claims of the present invention.

Claims

1. A new energy storage auxiliary decision-making and scheduling method, characterized in that: The following steps are involved: Obtain energy storage information of the energy storage power station, including historical operation information, dispatch response information, reliability information, battery charging and discharging information, operating conditions and battery characteristic data of the energy storage power station; Based on the energy storage information, the battery information of the energy storage batteries in the energy storage power station is determined, and the operation profile of each energy storage power station is constructed to determine the battery information of the energy storage batteries in the energy storage power station as follows: Perform data processing on the energy storage information of the energy storage power station to obtain multiple sections of historical energy storage information and current energy storage information; Feature extraction is performed on multiple segments of historical energy storage information and current energy storage information to obtain multiple historical battery features and current battery features, and the historical battery health status corresponding to each historical battery feature is determined; An initial battery health state determination model is constructed, and the initial battery health state determination model is trained through a plurality of historical battery features and corresponding historical battery health states to obtain a battery health state determination model; Inputting the current battery characteristics into a battery health state determination model to obtain battery information including the current battery health state and the predicted battery health state; Battery characteristics include battery charge and discharge characteristics and battery characteristic characteristics; The battery health status determination model includes a multi-scale pooling module, a gating mechanism, a long short-term memory network module, an attention mechanism, and a gated residual network; Inputting the battery charge and discharge characteristics and the battery characteristic characteristics into the multi-scale pooling module respectively to obtain a first operation characteristic and a first parameter characteristic; The first operation characteristic and the first parameter characteristic are respectively screened by a gating mechanism to obtain a second operation characteristic and a second parameter characteristic; Inputting the second operation characteristic and the second parameter characteristic into the long short-term memory network module to obtain battery characteristics at multiple time scales; The battery features of multiple time scales are input into the attention mechanism to obtain multi-scale battery features; the multi-scale battery features are input into the gated residual network to obtain the current battery health status; Predict the capacity decay of energy storage power stations based on battery information and operation profiles of each energy storage power station; Carry out grid control and evaluate the response capability of energy storage power stations based on battery information and operation profiles, and obtain evaluation results including response speed. Grid control includes primary frequency regulation, automatic generation control and automatic voltage control; Based on the evaluation results, a response weight is assigned to each energy storage power station. Based on the response weight and the predicted power demand of the power grid, a power command is issued to the energy storage power station. The charging and discharging strategy of the energy storage batteries in each energy storage power station is determined according to the power demand, charge state and capacity attenuation of the energy storage power station.

2. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: The long short-term memory network module includes multiple long short-term memory networks, and different long short-term memory networks are used to process second operating characteristics of different time lengths and their corresponding second parameter characteristics.

3. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: Loss function of the battery health status determination model L for: Where A represents the total number of training samples. Represents the training sample variable; represents the adjustment coefficient; Indicates the length of the interval of charge state that the current battery health state falls into; represents the L2 norm; Indicates the actual battery health status of the battery, which is a range value. Indicates the maximum value of the actual battery health status; Indicates the minimum value of the actual battery health status.

4. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: Current battery health status SOH c Specifically: in, Represents the sigmoid activation function; , , and They represent the first parameter, the second parameter, the third parameter and the fourth parameter respectively, which are obtained through model training; An intermediate variable representing the battery health status; Represent multi-scale battery characteristics; represents normalization; Represents bit-wise multiplication of elements.

5. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: The predicted battery health status is as follows: Based on the historical operation information, the future operation information of the future time period is predicted; based on the future operation information, the future battery characteristics are constructed; the future battery characteristics are input into the battery health status determination model to obtain the predicted battery health status.

6. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: The operation profiles of each energy storage power station are as follows: Obtain power grid information and new energy information; Extract energy storage information based on power grid information to obtain the time periods for peak load shaving and valley filling and the time periods for power regulation of each energy storage power station; Extract energy storage information based on new energy information and grid load data to obtain the time period for each energy storage power station to consume new energy; Calculate and analyze the charging and discharging efficiency, command response speed and charging and discharging power curve of each energy storage power station in each operation period, and build a control operation portrait; Extract the sub-storage information of each energy storage power station respectively to obtain the charging and discharging status of each energy storage power station; Based on the charging and discharging conditions of each energy storage power station, the charge state changes, charging and discharging capacity, and charging and discharging power curves in each charging and discharging process are determined, and a charging and discharging operation profile is constructed.

7. The novel energy storage auxiliary decision-making and scheduling method according to claim 6 is characterized in that: The power grid information includes power grid load data and power grid frequency data; the new energy information includes new energy power generation data.

8. The novel energy storage auxiliary decision-making and scheduling method according to claim 6 is characterized in that: The action periods include the time periods for peak shaving and valley filling, the time periods for power regulation and the time periods for new energy consumption.

9. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: Based on the battery information and the operation profiles of each energy storage power station, the capacity attenuation of the energy storage power station is predicted as follows: For each energy storage battery: Determine the maximum state of charge and minimum state of charge during each charge and discharge process; Determine the discharge amount of the energy storage battery during the charge and discharge process based on the difference between the maximum charge state and the minimum charge state; When the difference between the maximum state of charge and the minimum state of charge is greater than or equal to a preset state of charge difference threshold, the charge and discharge is used as a reference charge and discharge, and the reference battery capacity decay is determined by a capacity decay model; When the difference between the maximum state of charge and the minimum state of charge is less than a preset state of charge difference threshold, the battery capacity decay is determined based on the previous reference battery capacity decay and the discharge amount, charge state change, ambient temperature and discharge current during the current charge and discharge process; For each energy storage plant: The average value of the battery capacity attenuation of the energy storage batteries in the energy storage power station is taken as the capacity attenuation of the energy storage power station.

10. The novel energy storage auxiliary decision-making and scheduling method according to claim 9 is characterized in that: The capacity decay model is used to process the historical reference battery capacity decay and charge and discharge conditions of the energy storage battery to obtain the current reference battery capacity decay.

11. The novel energy storage auxiliary decision-making and scheduling method according to claim 9 is characterized in that: Battery capacity attenuation D c for: in, Indicates the capacity attenuation of the reference battery; represents the charge state parameter; Indicates the current discharge amount of the energy storage battery; Indicates the current ambient temperature Capacity correction factor; Represents the reference discharge current; k represents the Peukert index; Represents the state of charge correction factor.

12. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: The objective function of the power demand of the power station is: in, Indicates taking the minimum value; n indicates the variable of the energy storage power station; N indicates the total number of energy storage power stations; represents the response speed of the energy storage power station n; t represents the time variable; T represents the predicted total grid dispatch time; represents the power demand of energy storage power station n at time t; represents the power demand of energy storage power station n at time t-1; Indicates taking the absolute value.

13. The novel energy storage auxiliary decision-making and scheduling method according to claim 12 is characterized in that: The constraints on the power demand of the power station are: in, represents the predicted grid power demand at time t; in, Indicates the maximum power change rate of energy storage station n; in, represents the minimum output power of energy storage power station n; represents the maximum output power of energy storage station n; in, represents the energy state of energy storage station n at time t; represents the energy state of energy storage station n at time t-1; Indicates the discharge time interval; Indicates the charge and discharge efficiency; Indicates the lowest energy state of energy storage station n; Indicates the highest energy state of energy storage station n.

14. The novel energy storage auxiliary decision-making and scheduling method according to claim 1 is characterized in that: The objective function of the charging and discharging strategy of the energy storage batteries in each energy storage power station is: in, Indicates finding the minimum value; m indicates the energy storage battery variable; M indicates the total number of energy storage batteries in the energy storage power station; Indicates the current battery capacity attenuation; Indicates the rated capacity of the energy storage battery; represents the charge state of the energy storage battery m at time t; Represents the energy state of the energy storage battery m at time t.

15. The novel energy storage auxiliary decision-making and scheduling method according to claim 14 is characterized in that: The constraints of the charging and discharging strategy of the energy storage batteries in each energy storage power station are: in, It represents the battery charging and discharging power of the energy storage battery m in the energy storage power station n at time t; represents the power demand of energy storage power station n at time t; in, represents the battery charging and discharging power of the energy storage battery m in the energy storage power station n at time t-1; Indicates the maximum power change rate of the energy storage battery m; in, Represents the minimum output power of the energy storage battery m; Represents the maximum output power of the energy storage battery m; in, Indicates the lower limit of the charge state of the energy storage battery; Indicates the upper limit of the charge state of the energy storage battery.

16. A new energy storage auxiliary decision-making and dispatching system, characterized in that: include: An acquisition module is used to acquire energy storage information of the energy storage power station, including historical operation information, dispatch response information, reliability information, battery charge and discharge information, operating conditions and battery characteristic data of the energy storage power station; The information module determines the battery information of the energy storage batteries in the energy storage power station based on the energy storage information, and constructs the operation profile of each energy storage power station to determine the battery information of the energy storage batteries in the energy storage power station as follows: Perform data processing on the energy storage information of the energy storage power station to obtain multiple sections of historical energy storage information and current energy storage information; Feature extraction is performed on multiple segments of historical energy storage information and current energy storage information to obtain multiple historical battery features and current battery features, and the historical battery health status corresponding to each historical battery feature is determined; An initial battery health state determination model is constructed, and the initial battery health state determination model is trained through a plurality of historical battery features and corresponding historical battery health states to obtain a battery health state determination model; Inputting the current battery characteristics into a battery health state determination model to obtain battery information including the current battery health state and the predicted battery health state; Battery characteristics include battery charge and discharge characteristics and battery characteristic characteristics; The battery health status determination model includes a multi-scale pooling module, a gating mechanism, a long short-term memory network module, an attention mechanism, and a gated residual network; Inputting the battery charge and discharge characteristics and the battery characteristic characteristics into the multi-scale pooling module respectively to obtain a first operation characteristic and a first parameter characteristic; The first operation characteristic and the first parameter characteristic are respectively screened by a gating mechanism to obtain a second operation characteristic and a second parameter characteristic; Inputting the second operation characteristic and the second parameter characteristic into the long short-term memory network module to obtain battery characteristics at multiple time scales; The battery features of multiple time scales are input into the attention mechanism to obtain multi-scale battery features; the multi-scale battery features are input into the gated residual network to obtain the current battery health status; The prediction module predicts the capacity decay of the energy storage power station based on battery information and the operation profile of each energy storage power station; The control module conducts grid control and evaluates the response capability of the energy storage power station based on battery information and operation profiles to obtain evaluation results including response speed. Grid control includes primary frequency regulation, automatic generation control, and automatic voltage control. The output module assigns a response weight to each energy storage power station based on the evaluation results, and issues power instructions to the energy storage power station based on the response weight and the predicted power demand of the power grid; and determines the charging and discharging strategy of the energy storage batteries in each energy storage power station according to the power demand, charge state and capacity attenuation of the energy storage power station.

17. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform the method of any one of claims 1 to 15.

18. A computing device, characterized in that include: One or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include steps for executing the method of any one of claims 1 to 15.

Images