Park new energy storage system scheduling method, device and equipment and storage medium

Abstract

Embodiments of the present application provide a kind of park new energy energy storage system scheduling method, device, equipment and storage medium, belong to power distribution system optimization scheduling technical field.The method comprises: using swarm intelligence algorithm, the predicted value of the power load and the power generation of multiple time periods in future one day is optimized and solved, and the charge-discharge power of multiple time periods after preliminary optimization scheduling is obtained;Using the predicted value of the power generation of multiple time periods after 4 hours of current time period and the actual power generation of multiple time periods before current time period is updated, and the updated charge-discharge power of multiple time periods is obtained;Using swarm intelligence algorithm, the charge-discharge power of multiple time periods after updating and the residual capacity of current time period of energy storage system are optimized and solved, and the charge-discharge power of multiple time periods after final optimization scheduling is obtained.The charge-discharge power of multiple time periods after preliminary optimization scheduling is corrected and updated in the present application, and accurate charge-discharge power of multiple time periods is obtained.

Description

Technical Field

[0001] This invention relates to the field of power distribution system optimization and scheduling technology, specifically to a scheduling method for a new energy storage system in a park, a scheduling device for a new energy storage system in a park, an electronic device, and a computer-readable storage medium. Background Technology

[0002] With the increasing penetration of new energy sources and the growing scale of controllable loads, the peak-shaving situation of the power grid is becoming increasingly severe, and the distributed characteristics of the distribution network are becoming more and more apparent. Traditional distribution networks are gradually evolving into active distribution systems with abundant dispatch resources, capable of actively controlling and managing distributed generation, flexible loads, and energy storage. Effectively utilizing the interaction between distributed energy sources and loads within the active distribution system can, on the one hand, ensure the safe and economical operation of the system itself, and on the other hand, address the peak-shaving needs of the power grid, enhancing the reliability and controllability of the power system. Therefore, in-depth research on the optimal dispatching problem of the power system has significant theoretical and practical value.

[0003] Currently, the following methods are mainly used for optimization scheduling: (1) By predicting the power generation and load power in a two-layer manner, the power of the energy storage system is regulated to achieve load response; (2) The basic data of the power prediction of 96 points of wind turbines in 24 hours is used to optimize the system with the minimum fluctuation rate of the combined output of wind and energy storage as the optimization objective; (3) The rolling window technique is used to repeatedly optimize the local system by using the improved symbiotic biological search algorithm to minimize the system cost. However, the first method focuses on the prediction of photovoltaic output and has less description of energy storage scheduling. The model is relatively simple and lacks clear optimization methods and implementation scenarios. The second method often has inaccurate prediction of the 24-hour power of wind turbines and has deviations. Therefore, optimization based on the prediction data cannot guarantee the best results; (3) The overall benefits are relatively low due to the pursuit of local optima. At the same time, the optimization process has high requirements for computer resources.

[0004] In summary, existing power distribution system scheduling optimization schemes are not only unable to optimize scheduling for industrial parks and new energy operation scenarios, but also unable to accurately predict 24-hour power generation to achieve lower daily electricity costs. Summary of the Invention

[0005] The purpose of this invention is to provide a scheduling method, device, equipment, and storage medium for a new energy storage system in a park, in order to solve the problems that existing power distribution system scheduling optimization schemes not only cannot optimize scheduling for park and new energy operation scenarios, but also cannot accurately predict 24-hour power generation to obtain lower daily electricity costs.

[0006] To achieve the above objectives, embodiments of the present invention provide a scheduling method for a new energy storage system in a park, comprising:

[0007] Obtain forecasts of power load and power generation for multiple time periods within the next 24 hours for the park's new energy storage system;

[0008] Using a swarm intelligence algorithm, the predicted values ​​of power load and power generation for multiple time periods in the next 24 hours are optimized and solved to obtain the charging and discharging power for multiple time periods in the next 24 hours after preliminary optimized scheduling.

[0009] Using the predicted power generation values ​​of multiple time periods within 4 hours after the current time period and the actual power generation values ​​of multiple time periods before the current time period, the charging and discharging power of multiple time periods within the next 24 hours after the preliminary optimized scheduling is updated to obtain the updated charging and discharging power of multiple time periods within the next 24 hours.

[0010] Using a swarm intelligence algorithm, the charging and discharging power of multiple time periods in the updated next 24 hours and the remaining capacity of the energy storage system in the current time period are optimized and solved to obtain the final optimized charging and discharging power of multiple time periods in the next 24 hours.

[0011] Optionally, the predicted power load values ​​for multiple time periods within the next 24 hours of the park's new energy storage system are obtained through the following methods:

[0012] Get the number of employees, work schedule, weather data, and date type for the day;

[0013] By inputting the number of employees, work plan, weather data, and date type for the day into the power load forecasting model, the predicted power load values ​​for multiple time periods within the next 24 hours of the park's new energy storage system are obtained.

[0014] Optionally, the power load forecasting model is obtained in the following way:

[0015] Obtain the number of employees, work schedule, weather data, date type, and actual power load for multiple time periods within a specific historical day;

[0016] The pre-built time series model is trained using the number of employees, work plans, weather data, and date type for a specific historical day. The power load prediction model is obtained when the power load predicted by the time series model for multiple periods within the next 24 hours of a specific historical day is equal to the actual power load for multiple periods within the specific historical day.

[0017] Optionally, before the step of inputting the number of employees, work plan, weather data, and date type of the day into the power load forecasting model to obtain the predicted power load values ​​for multiple time periods within the next 24 hours of the park's new energy storage system, the method further includes:

[0018] The number of employees, work plan, weather data, and date type for the day are preprocessed; wherein, the preprocessing includes noise reduction and normalization.

[0019] Optionally, the method further includes:

[0020] Using formula (1), the charging and discharging power and duration of multiple time periods in the next 24 hours after the final optimized scheduling are calculated respectively to obtain the charging and discharging power of the energy storage system in multiple time periods in the next 24 hours.

[0021]

[0022] Where, m e This indicates the charging and discharging capacity for each time period within the next 24 hours. This represents the charging power for each time period within the next 24 hours, and is a positive value. Δt represents the discharge power for each time period within the next 24 hours and is a negative value; Δt represents the duration of each time period within the next 24 hours.

[0023] Using formula (2), the operation and maintenance cost of the energy storage system, the revenue of the park selling electricity to the grid, the amount of electricity sold to the grid, the cost of the park purchasing electricity from the grid, the amount of electricity purchased from the grid, and the charging and discharging amount of the energy storage system in the multiple time periods of the next 24 hours are calculated respectively, and the sum of the electricity charges in the multiple time periods of the next 24 hours is obtained.

[0024] F=min{∑[a b m b +a e m e -a s m s ]} (2);

[0025] Where F represents the sum of electricity costs for multiple time periods within the next 24 hours; a e This represents the operation and maintenance cost of the energy storage system for each time period within the next 24 hours; m e This indicates the charging and discharging capacity of the energy storage system for each time period within the next 24 hours; a s This represents the revenue per kilowatt-hour from the sale of electricity from the park to the grid for each time period within the next 24 hours; m s This indicates the amount of electricity sold from the park to the grid for each time period within the next 24 hours; ab This represents the cost per kilowatt-hour of electricity purchased from the grid by the park for each time period within the next 24 hours; m b This indicates the amount of electricity the park will purchase from the power grid for each time period within the next 24 hours.

[0026] In a second aspect of the present invention, a scheduling device for a new energy storage system in a park is provided, comprising:

[0027] The data acquisition module is used to obtain the predicted values ​​of power load and power generation of the park's new energy storage system for multiple time periods in the next 24 hours;

[0028] The first calculation module is used to optimize and solve the predicted values ​​of power load and power generation for multiple time periods in the next 24 hours using a swarm intelligence algorithm, so as to obtain the charging and discharging power for multiple time periods in the next 24 hours after preliminary optimization scheduling.

[0029] The data update module is used to update the charging and discharging power of multiple periods in the next 24 hours after the preliminary optimized scheduling by using the predicted power generation values ​​of multiple periods in the next 4 hours and the actual power generation of multiple periods in the previous 24 hours, so as to obtain the updated charging and discharging power of multiple periods in the next 24 hours.

[0030] The second calculation module is used to optimize the charging and discharging power of multiple time periods in the next 24 hours and the remaining capacity of the energy storage system in the current time period using a swarm intelligence algorithm, so as to obtain the final optimized charging and discharging power of multiple time periods in the next 24 hours.

[0031] Optionally, the data acquisition module is specifically used for:

[0032] Get the number of employees, work schedule, weather data, and date type for the day;

[0033] By inputting the number of employees, work plan, weather data, and date type for the day into the power load forecasting model, the predicted power load values ​​for multiple time periods within the next 24 hours of the park's new energy storage system are obtained.

[0034] Optionally, the device further includes:

[0035] The power calculation module is used to calculate the charging and discharging power and duration of multiple time periods in the next 24 hours after the final optimized scheduling using formula (1), so as to obtain the charging and discharging power of the energy storage system in multiple time periods in the next 24 hours.

[0036]

[0037] Where, me This indicates the charging and discharging capacity for each time period within the next 24 hours. This represents the charging power for each time period within the next 24 hours, and is a positive value. Δt represents the discharge power for each time period within the next 24 hours and is a negative value; Δt represents the duration of each time period within the next 24 hours.

[0038] The electricity cost calculation module is used to calculate the operation and maintenance cost of the energy storage system, the revenue of the park selling electricity to the grid, the amount of electricity sold to the grid, the cost of the park purchasing electricity from the grid, the amount of electricity purchased from the grid, and the charging and discharging amount of the energy storage system in the multiple time periods of the next 24 hours using formula (2), so as to obtain the sum of the electricity costs in the multiple time periods of the next 24 hours.

[0039] F=min{∑[a b m b +a e m e -a s m s ]} (2);

[0040] Where F represents the sum of electricity costs for multiple time periods within the next 24 hours; a e This represents the operation and maintenance cost of the energy storage system for each time period within the next 24 hours; m e This indicates the charging and discharging capacity of the energy storage system for each time period within the next 24 hours; a s This represents the revenue per kilowatt-hour from the sale of electricity from the park to the grid for each time period within the next 24 hours; m s This indicates the amount of electricity sold from the park to the grid for each time period within the next 24 hours; a b This represents the cost per kilowatt-hour of electricity purchased from the grid by the park for each time period within the next 24 hours; m b This indicates the amount of electricity the park will purchase from the power grid for each time period within the next 24 hours.

[0041] In a third aspect of the present invention, an electronic device is provided, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions, when executed by the processor, execute the above-described scheduling method for a new energy storage system in a park.

[0042] In a fourth aspect of the present invention, a computer-readable storage medium is provided, on which instructions are stored, which are used to cause a machine to execute the above-described scheduling method for a new energy storage system in a park.

[0043] In this embodiment of the invention, by utilizing a swarm intelligence algorithm, the predicted values ​​of power load and power generation of the new energy storage system in the park for multiple time periods within the next 24 hours are optimized and solved to obtain the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling. Then, the predicted power generation values ​​for multiple time periods 4 hours after the current time period and the actual power generation values ​​for multiple time periods before the current time period are used to update the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling to obtain the updated charging and discharging power for multiple time periods within the next 24 hours. Then, using a swarm intelligence algorithm, the updated charging and discharging power for multiple time periods within the next 24 hours and the remaining capacity of the energy storage system in the current time period are optimized and solved to obtain the final charging and discharging power for multiple time periods after optimization scheduling. This realizes the correction and update of the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling, and obtains accurate charging and discharging power for multiple time periods within the next 24 hours.

[0044] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0045] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0046] Figure 1 This is a flowchart illustrating the scheduling method for a new energy storage system in a park provided in an embodiment of the present invention;

[0047] Figure 2 This is a flowchart illustrating the Harris Eagle algorithm provided in an embodiment of the present invention;

[0048] Figure 3 This is a curve comparison chart of actual power load and predicted power load provided in an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram of the structure of a long short-term memory network provided in an embodiment of the present invention;

[0050] Figure 5 This is a graph showing the theoretical and actual electricity consumption of new energy sources in the park without energy storage systems, provided in an embodiment of the present invention.

[0051] Figure 6 This is a graph showing the theoretical and actual electricity consumption and the charging and discharging power of the new energy storage system in the park after only preliminary optimization and scheduling, as provided in this embodiment of the invention.

[0052] Figure 7These are the theoretical and actual power consumption curves and the charging and discharging power curves after adopting the scheduling method of the park's new energy storage system provided in the embodiments of the present invention.

[0053] Figure 8 This is a schematic diagram of the scheduling device for the park's new energy storage system provided in an embodiment of the present invention. Detailed Implementation

[0054] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this application.

[0056] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0057] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0058] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating the scheduling method for a new energy storage system in a park provided by an embodiment of the present invention. The method includes the following steps:

[0059] S100 obtains the predicted values ​​of power load and power generation of the park's new energy storage system for multiple time periods in the next 24 hours;

[0060] It is understood that the application scenario of this invention is "industrial park + new energy", and the "industrial park + new energy" is equipped with an energy storage system.

[0061] A park refers to a designated area planned and managed centrally by the government, where enterprises and companies of a specific industry or type are set up and managed in a unified manner. It includes, but is not limited to, office parks, industrial parks, free trade parks, industrial parks, animation parks, etc.

[0062] New energy sources include, but are not limited to, wind power generation, photovoltaic power generation, etc.

[0063] Specifically, the next 24 hours are divided into multiple time periods proportionally, including but not limited to 24, 48, and 96. For example: 1440 minutes (24h) ÷ 24 = 60 minutes, which means there are 24 time periods in 60-minute units; 1440 minutes (24h) ÷ 48 = 30 minutes, which means there are 48 time periods in 30-minute units; 1440 minutes (24h) ÷ 96 = 15 minutes, which means there are 96 time periods in 15-minute units.

[0064] Electrical load, also known as "electrical load", in this embodiment of the invention refers to the total electrical power drawn by the electrical equipment of an electrical user from the energy storage system at a certain moment.

[0065] In this embodiment of the invention, power generation refers to the amount of work done by the energy storage system per unit time.

[0066] In one embodiment, the predicted power generation value can be obtained through a new energy system. Since the predicted power generation value in the new energy system is obtained through a corresponding algorithm, which is a relatively mature technology, an accurate predicted power generation value can be obtained through the new energy system. This embodiment of the invention does not specifically limit the method for predicting power generation, and can flexibly select one according to actual application needs.

[0067] S200 uses a swarm intelligence algorithm to optimize the predicted values ​​of power load and power generation for multiple time periods in the next 24 hours, and obtains the charging and discharging power for multiple time periods in the next 24 hours after preliminary optimized scheduling.

[0068] Swarm intelligence algorithms refer to a class of intelligent algorithms with distributed intelligent behavior characteristics designed by being inspired by the group behavior of insects, herds of animals, flocks of birds, and schools of fish. They are used to find optimal solutions and include, but are not limited to, particle swarm optimization, ant swarm optimization, and Harris Eagle optimization. This embodiment of the invention does not make specific limitations on these algorithms and can be flexibly selected according to actual application needs.

[0069] It should be noted that in order to optimize the predicted values ​​of power load and power generation for multiple time periods in the next 24 hours, it is necessary to set an objective function and constraints. The objective function is the goal of the optimization solution, and the constraints are used to determine the upper and lower limits. The calculation formula of the objective function is shown in formula (2), and the calculation formulas of the constraints are shown in formulas (3), (4) and (5).

[0070] F=min{∑[a b m b +a e m e -a s m s ]} (2);

[0071] Where F represents the sum of electricity costs for multiple time periods within the next 24 hours; a e This represents the operation and maintenance cost of the energy storage system for each time period within the next 24 hours; m e This indicates the charging and discharging capacity of the energy storage system for each time period within the next 24 hours; a s This represents the revenue per kilowatt-hour from the sale of electricity from the park to the grid for each time period within the next 24 hours; m s This indicates the amount of electricity sold from the park to the grid for each time period within the next 24 hours; a b This represents the cost per kilowatt-hour of electricity purchased from the grid by the park for each time period within the next 24 hours; m b This indicates the amount of electricity the park will purchase from the power grid for each time period within the next 24 hours;

[0072] The formula for calculating the state-of-charge constraints is as follows:

[0073]

[0074] Where SOC(t) represents the state of charge at the end of the next time period; SOC(t-1) represents the state of charge at the end of each time period; δ represents the self-discharge rate of the energy storage battery in each time period; and η represents the charging efficiency of the energy storage battery in each time period. This represents the charging power of the energy storage battery at each time period, and is a positive value; E represents the discharge power of the energy storage battery at each time period, and is a negative value; Δt represents the time interval between each time period; b Indicates the rated capacity of the energy storage system for each time period; SOC min Indicates the minimum permissible state of charge; SOC max Indicates the maximum permissible state of charge;

[0075] The formula for calculating the power balance constraint is as follows:

[0076] P s +Pb -P l =0 (4); where, P s P represents the power generation capacity of new energy sources in each time period, and is always a positive value; b This represents the power of the energy storage battery at each time period; it is positive during charging and negative during discharging. (P) l This represents the load power for each time period, and is always a positive value;

[0077] The formula for calculating the maximum charge / discharge power constraint is as follows:

[0078] in, This indicates the maximum allowable charging and discharging power of the energy storage system.

[0079] The Harris Eagle algorithm is used as an example to illustrate swarm intelligence algorithms. The following is a detailed explanation:

[0080] The Harris Eagle algorithm is mainly divided into two stages: global search and local exploration. The main process can be found in [reference needed]. Figure 2 As shown:

[0081] 1. During the global search phase, the Harris Eagle will randomly distribute its positions and update them using the following two strategies:

[0082]

[0083] Where t represents the current iteration number; X(t) represents the position vector of the Harris Eagle; X rand (t) represents a random individual selected from the flock of eagles; X m (t) represents the average position of the eagle flock; X prey (t) indicates the location of the prey; r i q represents a random number before (0,1); lb represents the upper limit of the variable value; ub represents the lower limit of the variable value.

[0084] X m The calculation of (t) is shown in formula (7):

[0085] Where N represents the number of Harris eagles in the eagle population.

[0086] Then, the Harris Eagle will decide whether to enter the local development phase or continue the global search based on the energy required for the prey to escape. The escape energy is calculated as shown in formula (8):

[0087]

[0088] Where E0 represents the initial energy of the prey, -1≤E0≤1; T represents the number of iterations.

[0089] When |E|>1, the Harris Eagle remains in the global search phase and will not enter the subsequent local development phase.

[0090] Second, during the layout and development phase, the Harris Eagle determines the action to be taken based on the prey's escape energy E and escape probability r. It can be divided into four strategies: soft encirclement, hard encirclement, soft encirclement with gradual rapid dive, and hard encirclement with gradual rapid dive.

[0091] 1. When |E|≥0.5 and r≥0.5, a soft encirclement strategy is adopted, and the update is performed according to formula (9):

[0092]

[0093] Where ΔX(t) represents the difference between the prey's position and the current position; J = 2(1-r i ); represents the jump distance during the prey's escape; r i This represents a random number before (0,1).

[0094] 2. When |E| < 0.5 and r ≥ 0.5, a hard encirclement strategy is adopted, and the update is performed according to formula (10):

[0095] X(t+1)=X prey (t)-E|ΔX(t) (10).

[0096] 3. When |E|≥0.5 and r<0.5, a gradual, rapid dive soft encirclement strategy is adopted. The position update in this case can be divided into two types:

[0097] The first interpretation can be that the prey did not escape, and the update should be performed according to formula (11):

[0098] Y = X prey (t)-E|JX prey (t)-X(t) (11); where Y represents the position to be updated.

[0099] The second approach can be understood as approaching the prey by diving when it escapes, and updating the algorithm according to formula (12):

[0100] Z = Y + S × Levy(D) (12); where Z represents the updated position; S represents a 1 x D random vector; D represents the dimension of the problem; Levy(D) is the flight equation of the model's flight action;

[0101] Levy(D) can be calculated using formula (13):

[0102] Where μ and v represent random numbers between (0, 1); β represents a constant of 1.5.

[0103] σ can be calculated using formula (14):

[0104]

[0105] Finally, combining the two position update methods mentioned above, the position update of the soft enclosure in the progressive rapid dive needs to be performed according to (15):

[0106] Here, F(Y) and F(Z) represent the objective function values.

[0107] 4. When |E| < 0.5 and r < 0.5, a gradual, rapid dive hard encirclement strategy is adopted, and updates are performed according to formula (16):

[0108] Y = X prey (t)-E|JX prey (t)-X m (t) (15);

[0109] Z = Y + S × Levy(D) (12).

[0110] S300 uses the predicted power generation values ​​of multiple time periods within 4 hours after the current time period and the actual power generation of multiple time periods before the current time period to update the charging and discharging power of multiple time periods within the next 24 hours after the preliminary optimized scheduling, and obtains the updated charging and discharging power of multiple time periods within the next 24 hours.

[0111] To make it easier to understand, the following examples are provided:

[0112] Assuming the next 24 hours are divided into 96 equal periods, with the current period being i and the end periods of multiple periods within 4 hours after the current period being j, then the period [0, i] uses the actual power generation of multiple periods before the current period, the period [i, j] uses the predicted power generation of multiple periods within 4 hours after the current period, and the period [j, 96] uses the charging and discharging power of multiple periods within the next 24 hours, finally obtaining the updated charging and discharging power of multiple periods within the next 24 hours.

[0113] The S400 uses a swarm intelligence algorithm to optimize the charging and discharging power of multiple time periods in the next 24 hours and the remaining capacity of the energy storage system in the current time period, so as to obtain the final optimized charging and discharging power of multiple time periods in the next 24 hours.

[0114] In this embodiment of the invention, remaining capacity refers to the amount of capacity remaining in the energy storage system after a certain period of use.

[0115] In this embodiment, by utilizing a swarm intelligence algorithm, the predicted values ​​of power load and power generation of the new energy storage system in the park for multiple time periods within the next 24 hours are optimized and solved to obtain the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling. Then, the predicted power generation values ​​for multiple time periods 4 hours after the current time period and the actual power generation values ​​for multiple time periods before the current time period are used to update the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling to obtain the updated charging and discharging power for multiple time periods within the next 24 hours. Then, using a swarm intelligence algorithm, the updated charging and discharging power for multiple time periods within the next 24 hours and the remaining capacity of the energy storage system in the current time period are optimized and solved to obtain the final charging and discharging power for multiple time periods after optimization scheduling. This realizes the correction and update of the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling, and obtains the accurate charging and discharging power for multiple time periods within the next 24 hours.

[0116] Optionally, the predicted power load values ​​for multiple time periods within the next 24 hours of the park's new energy storage system are obtained through the following methods:

[0117] S1. Obtain the number of employees, work plan, weather data, and date type for the current day;

[0118] S2. Input the number of employees, work plan, weather data and date type for the day into the power load forecasting model to obtain the predicted power load values ​​for multiple time periods in the next 24 hours for the park's new energy storage system.

[0119] The number of employees includes, but is not limited to, the number of employees present and the types of employees present.

[0120] The work plan includes, but is not limited to, the commissioning plan for large equipment.

[0121] Weather data includes, but is not limited to, maximum temperature, minimum temperature, and humidity.

[0122] Date types include, but are not limited to, weekdays and non-working days.

[0123] A power load forecasting model is a model obtained by training a pre-built time series model using the number of employees, work plans, weather data, and date type for the day.

[0124] Specifically, through Figure 3 It can be seen that by using the number of employees, work plans, weather data, and date type as inputs to the power load forecasting model, the power load predicted by the power load forecasting model is almost close to the actual power load.

[0125] In this embodiment, by using the number of employees, work schedule, weather data, and date type as inputs to the power load forecasting model, the predicted power load becomes more accurate.

[0126] Optionally, the power load forecasting model is obtained in the following way:

[0127] Step 1: Obtain the number of employees, work schedule, weather data, date type, and actual power load for multiple time periods for a specific historical day;

[0128] The second step is to train a pre-built time series model using the number of employees, work plans, weather data, and date type for a specific historical day. The power load prediction model is obtained when the power load predicted by the time series model for multiple periods within the next 24 hours of a specific historical day is equal to the actual power load for multiple periods within the same historical day.

[0129] Understandably, we need to train the system using historical data on the number of employees, work schedules, weather conditions, and date type for a specific day to predict electricity load; this can be understood as time series forecasting. Therefore, to address the vanishing and exploding gradient problems during long-sequence training, this embodiment of the invention employs a time series model.

[0130] Temporal models include, but are not limited to, long short-term memory networks, recurrent neural networks, and gated recurrent unit networks.

[0131] The temporal model, using Long Short-Term Memory (LSTM) networks as an example, is explained below:

[0132] Reference Figure 4 , Figure 4 This is a schematic diagram of the structure of a long short-term memory network provided in an embodiment of the present invention.

[0133] Long short-term memory (LSTM) is an improved time-recurrent neural network that includes a forget gate, an input gate, and an output gate. The outputs of the three gates are each connected to a multiplication unit, thereby controlling the network's input, output, and the state of the cell unit, which enables the network to converge better and faster, improving the accuracy of power load forecasting.

[0134] In this embodiment, a pre-built time series model is trained using the number of employees, work plans, weather data, and date type of a historical day to obtain a power load prediction model. This enables the direct prediction of the power load of the park's new energy storage system for the next 24 hours in practical applications.

[0135] Optionally, the method may further include the following steps before step S1:

[0136] The number of employees, work plans, weather data, and date type for the day are preprocessed; the preprocessing includes noise reduction and normalization.

[0137] In the field of algorithm models, the data cleaning process is also known as "feature engineering". Common methods include selecting features based on correlation, denoising based on the degree of dispersion, and data normalization. The purpose is to improve the data quality, make more reasonable use of each feature to predict more accurate results, or fit a model with higher accuracy. Therefore, this embodiment uses noise reduction and normalization to preprocess the data.

[0138] Specifically, the least squares method is used to fit the data for the number of employees, work plans, weather data, and date type. A deviation threshold h is set for each data type, and points where the deviation between the sample value and the fitted value exceeds the threshold h are treated as noise and deleted. The threshold h is determined based on the number of employees, work plans, weather data, and date type.

[0139] Specifically, the noise-reduced number of employees, work plans, weather data, and date types are normalized by dividing each data point by its maximum value. This normalization process flattens the value ranges of various data points, keeping them within the same range and avoiding parameter clustering issues caused by large differences in value ranges between data points, thus improving the model's final prediction performance.

[0140] In this embodiment, by performing noise reduction and normalization processing on the acquired number of employees, work plans, weather data, and date type for the day, the quality of the data is guaranteed, thereby providing favorable input conditions for the power load forecasting model and resulting in higher accuracy of the output results of multiple power load forecasting models.

[0141] Optionally, after step S400 above, the following steps may also be included:

[0142] S1, using formula (1), calculate the charging and discharging power and duration of multiple time periods in the next 24 hours after the final optimized scheduling, and obtain the charging and discharging power of the energy storage system in multiple time periods in the next 24 hours.

[0143]

[0144] Where, m e This indicates the charging and discharging capacity for each time period within the next 24 hours. This represents the charging power for each time period within the next 24 hours, and is a positive value. Δt represents the discharge power for each time period within the next 24 hours and is a negative value; Δt represents the duration of each time period within the next 24 hours.

[0145] S2, using formula (2), calculate the operation and maintenance cost of the energy storage system, the revenue of the park selling electricity to the grid, the amount of electricity sold to the grid, the cost of the park purchasing electricity from the grid, the amount of electricity purchased from the grid, and the charging and discharging amount of the energy storage system in multiple time periods in the next 24 hours, and obtain the sum of the electricity charges in multiple time periods in the next 24 hours.

[0146] F=min{∑[a b m b +a e m e -a s m s ]} (2);

[0147] Where F represents the sum of electricity costs for multiple time periods within the next 24 hours; a e This represents the operation and maintenance cost of the energy storage system for each time period within the next 24 hours; m e This indicates the charging and discharging capacity of the energy storage system for each time period within the next 24 hours; a s This represents the revenue per kilowatt-hour from the sale of electricity from the park to the grid for each time period within the next 24 hours; m s This indicates the amount of electricity sold from the park to the grid for each time period within the next 24 hours; a b This represents the cost per kilowatt-hour of electricity purchased from the grid by the park for each time period within the next 24 hours; m b This indicates the amount of electricity the park will purchase from the power grid for each time period within the next 24 hours.

[0148] Taking the scheduling method of the park's new energy storage system provided in this embodiment of the invention as an example, the electricity fee calculation table under the actual electricity consumption is as follows (negative values ​​in the table represent electricity fed back to the grid, and there is no revenue from the fed-back electricity):

[0149]

[0150]

[0151]

[0152] For ease of understanding, the following is in conjunction with the appendix. Figure 5-7 Please provide a detailed explanation:

[0153] See also 5, 6 and 7, Figure 5 This is a graph showing the theoretical and actual electricity consumption of new energy sources in the park without energy storage systems, provided in an embodiment of the present invention. Figure 6 This is a graph showing the theoretical and actual electricity consumption and the charging and discharging power of the new energy storage system in the park after only preliminary optimization and scheduling, as provided in this embodiment of the invention. Figure 7These are the theoretical and actual power consumption curves and the charging and discharging power curves after adopting the scheduling method of the park's new energy storage system provided in this embodiment of the invention.

[0154] Without an energy storage system, the projected daily electricity cost for new energy in the park is approximately 8433 yuan, while the actual cost is approximately 7748 yuan. The curve of electricity drawn from the grid is shown below. Figure 6 As shown.

[0155] Assuming the park's new energy configuration includes a 300kW, 600kWh energy storage system, and after optimizing the scheduling based on the predicted power generation load and output for each time period within the next 24 hours, the park's theoretical daily electricity cost is approximately 8085 yuan, while the actual cost is 7383 yuan. The curves for electricity drawn from the grid and the charging / discharging power are shown below. Figure 7 As shown.

[0156] Assuming the park's new energy configuration includes a 300kW and 600kWh energy storage system, after initial optimization scheduling based on the predicted power generation load and output for each time period within the next 24 hours, the predicted power generation load and output for each time period within the next 24 hours are updated by combining the power generation output for multiple time periods within the next 4 hours and the power generation output for multiple time periods before the current time period. Finally, the remaining capacity of the energy storage system is used for further optimization scheduling. The theoretical daily electricity cost for the park is approximately 8082 yuan, while the actual daily cost is 7166 yuan. The curves for electricity drawn from the grid and the charging / discharging power curves are shown below. Figure 8 As shown.

[0157] In summary, the comparison shows that the scheduling method for the park's new energy storage system provided by this invention reduces electricity costs by approximately 582 yuan compared to a scheme without a storage system, and by approximately 217 yuan compared to a scheme that only optimizes the scheduling of predicted power generation load and power for each time period within the next 24 hours. Therefore, this invention provides a more accurate charging and discharging power result by updating the predicted power generation load and power for each time period within the next 24 hours after the initial optimization scheduling, using power generation data from multiple time periods within the next four hours and from multiple time periods before the current time period. This leads to lower daily electricity costs for the park's new energy system.

[0158] In this embodiment, the sum of electricity costs for multiple time periods within the next 24 hours of the energy storage system is calculated using formulas (1) and (2). The calculated sum of electricity costs for multiple time periods within the next 24 hours of the energy storage system is lower than that of existing optimized scheduling schemes. This means that the data demonstrates that the scheduling method for the park new energy storage system provided by this embodiment of the invention can better optimize the charging and discharging power of new energy in the park and achieve lower daily electricity costs.

[0159] Based on the same inventive concept, embodiments of the present invention also provide a scheduling device 200 for a new energy storage system in a park, characterized in that it includes:

[0160] Please refer to Figure 8 , Figure 8 This is a schematic diagram of the scheduling device structure of a new energy storage system in a park, provided by an embodiment of the present invention.

[0161] The data acquisition module 210 is used to acquire the predicted values ​​of power load and power generation of the park's new energy storage system for multiple time periods in the next 24 hours;

[0162] The first calculation module 220 is used to optimize and solve the predicted values ​​of power load and power generation for multiple time periods in the next 24 hours using a swarm intelligence algorithm, so as to obtain the charging and discharging power for multiple time periods in the next 24 hours after preliminary optimization scheduling.

[0163] The data update module 230 is used to update the charging and discharging power of multiple periods in the next 24 hours after the preliminary optimized scheduling by using the predicted power generation values ​​of multiple periods in the next 4 hours after the current period and the actual power generation of multiple periods in the previous period, so as to obtain the updated charging and discharging power of multiple periods in the next 24 hours.

[0164] The second calculation module 240 is used to optimize the charging and discharging power of multiple time periods in the next 24 hours and the remaining capacity of the energy storage system in the current time period using a swarm intelligence algorithm, so as to obtain the final optimized charging and discharging power of multiple time periods in the next 24 hours.

[0165] Optionally, the data acquisition module 220 is specifically used for:

[0166] Get the number of employees, work schedule, weather data, and date type for the day;

[0167] By inputting the number of employees, work plan, weather data, and date type for the day into the power load forecasting model, the predicted power load values ​​for multiple time periods within the next 24 hours for the park's new energy storage system are obtained.

[0168] Optionally, the dispatching device 200 for the park's new energy storage system also includes:

[0169] The power calculation module 250 is used to calculate the charging and discharging power and duration of multiple time periods in the next 24 hours after the final optimized scheduling using formula (1), so as to obtain the charging and discharging power of the energy storage system in multiple time periods in the next 24 hours.

[0170]

[0171] Where, m e This indicates the charging and discharging capacity for each time period within the next 24 hours. This represents the charging power for each time period within the next 24 hours, and is a positive value. Δt represents the discharge power for each time period within the next 24 hours and is a negative value; Δt represents the duration of each time period within the next 24 hours.

[0172] The electricity cost calculation module 260 is used to calculate the energy storage system operation and maintenance cost, the revenue of the park selling electricity to the grid, the amount of electricity sold to the grid, the cost of the park purchasing electricity from the grid, the amount of electricity purchased from the grid, and the charging and discharging amount of the energy storage system in multiple time periods in the next 24 hours using formula (2), so as to obtain the sum of the electricity costs in multiple time periods in the next 24 hours.

[0173] F=min{∑[a b m b +a e m e -a s m s ]} (2);

[0174] Where F represents the sum of electricity costs for multiple time periods within the next 24 hours; a e This represents the operation and maintenance cost of the energy storage system for each time period within the next 24 hours; m e This indicates the charging and discharging capacity of the energy storage system for each time period within the next 24 hours; a s This represents the revenue per kilowatt-hour from the sale of electricity from the park to the grid for each time period within the next 24 hours; m s This indicates the amount of electricity sold from the park to the grid for each time period within the next 24 hours; a b This represents the cost per kilowatt-hour of electricity purchased from the grid by the park for each time period within the next 24 hours; m b This indicates the amount of electricity the park will purchase from the power grid for each time period within the next 24 hours.

[0175] It should be understood that this device corresponds to the scheduling method embodiment of the above-mentioned park new energy storage system, and is capable of executing the various steps involved in the above method embodiment. The specific functions of this device can be found in the description above, and detailed descriptions are omitted here to avoid repetition. The device includes at least one software functional module that can be stored in memory or embedded in the device's operating system (OS) in the form of software or firmware.

[0176] Based on the same inventive concept, embodiments of the present invention also provide an electronic device, which includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0177] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0178] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0179] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed by a processor, are adapted to execute a program having the following method steps: obtaining predicted values ​​of power load and power generation for multiple time periods within the next 24 hours of a new energy storage system in a park; using a swarm intelligence algorithm to optimize and solve the predicted values ​​of power load and power generation for multiple time periods within the next 24 hours, obtaining the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling; updating the charging and discharging power for multiple time periods within the next 24 hours after preliminary optimization scheduling using the predicted values ​​of power generation for multiple time periods within 4 hours after the current time period and the actual power generation for multiple time periods before the current time period, obtaining the updated charging and discharging power for multiple time periods within the next 24 hours; using a swarm intelligence algorithm to optimize and solve the updated charging and discharging power for multiple time periods within the next 24 hours and the remaining capacity of the energy storage system in the current time period, obtaining the final optimized charging and discharging power for multiple time periods within the next 24 hours.

[0180] In one embodiment, the scheduling method for the above-mentioned new energy storage system in the park further includes: obtaining the number of employees, work plan, weather data and date type for the day; inputting the number of employees, work plan, weather data and date type for the day into the power load forecasting model to obtain the predicted power load values ​​for multiple time periods in the next 24 hours of the new energy storage system in the park.

[0181] In one embodiment, the scheduling method of the above-mentioned new energy storage system in the park further includes: obtaining the number of employees, work plans, weather data, date type, and actual power load of multiple time periods within a historical day; training a pre-built time series model using the number of employees, work plans, weather data, and date type within a historical day; and obtaining a power load prediction model when the power load of multiple time periods within the next 24 hours of a historical day predicted by the time series model is equal to the actual power load of multiple time periods within a historical day.

[0182] In one embodiment, the scheduling method of the above-mentioned new energy storage system in the park further includes: using formula (1), calculating the charging and discharging power and duration of multiple time periods in the next 24 hours after the final optimized scheduling, so as to obtain the charging and discharging power of the energy storage system in multiple time periods in the next 24 hours. Where, m e This indicates the charging and discharging capacity for each time period within the next 24 hours. This represents the charging power for each time period within the next 24 hours, and is a positive value. Δt represents the discharge power of each time period in the next 24 hours, and is a negative value; Δt represents the duration of each time period in the next 24 hours; using formula (2), the operation and maintenance cost of the energy storage system, the revenue of the park selling electricity to the grid, the amount of electricity sold to the grid, the cost of the park purchasing electricity from the grid, the amount of electricity purchased from the grid, and the charging and discharging amount of the energy storage system in multiple time periods in the next 24 hours are calculated respectively, and the sum of the electricity charges in multiple time periods in the next 24 hours is obtained; F=max{∑[a s m s -a b m b -a e m e ]} (2); where F represents the sum of electricity charges for multiple time periods within the next 24 hours; a e This represents the operation and maintenance cost of the energy storage system for each time period within the next 24 hours; m e This indicates the charging and discharging capacity of the energy storage system for each time period within the next 24 hours; a s This represents the revenue per kilowatt-hour from the sale of electricity from the park to the grid for each time period within the next 24 hours; m s This indicates the amount of electricity sold from the park to the grid for each time period within the next 24 hours; a b This represents the cost per kilowatt-hour of electricity purchased from the grid by the park for each time period within the next 24 hours; m b This indicates the amount of electricity the park will purchase from the power grid for each time period within the next 24 hours.

[0183] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0184] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0185] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0186] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0187] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not describe the various possible combinations separately.

[0188] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0189] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A park new energy storage system scheduling method, characterized in that, The method comprises the following steps: obtaining predicted values of power load and power generation of multiple time periods within 24 hours in the future of a new energy storage system of a park; using a swarm intelligence algorithm to optimize and solve the predicted values of power load and power generation of multiple time periods within 24 hours in the future, to obtain the charging and discharging power of multiple time periods within 24 hours in the future after preliminary optimized scheduling; wherein the optimization and solution is based on a set target function and constraint condition; the constraint condition comprises a state of charge constraint condition, a balance power constraint condition and a maximum charging and discharging power constraint condition; State of Charge constraint is: ; wherein, represents the State of Charge at the end of the next time period of each time period; represents the State of Charge at the end of each time period; represents the self-discharge rate of the energy storage battery for each time period; represents the charging efficiency of the energy storage battery for each time period; represents the charging power of the energy storage battery for each time period, which is positive; represents the discharging power of the energy storage battery for each time period, which is negative; represents the time interval between each time period; represents the rated capacity of the energy storage system for each time period; represents the minimum State of Charge allowed; represents the maximum State of Charge allowed; The balance power constraint condition is: ; wherein, represents the power generation of new energy of each period, and is always positive; represents the power of the energy storage battery of each period, and is positive when charging and negative when discharging; represents the load power of each period, and is always positive; The maximum charge-discharge power constraint condition is: ; wherein, represents the maximum charge-discharge power allowed by the energy storage system; using the predicted values of power generation of multiple time periods within 4 hours after the current time period and the actual power generation of multiple time periods before the current time period to update the charging and discharging power of multiple time periods within 24 hours in the future after the preliminary optimized scheduling, to obtain the updated charging and discharging power of multiple time periods within 24 hours in the future; using the swarm intelligence algorithm to optimize and solve the updated charging and discharging power of multiple time periods within 24 hours in the future and the remaining capacity of the storage system of the current time period, to obtain the charging and discharging power of multiple time periods within 24 hours in the future after final optimized scheduling.

2. The method of claim 1, wherein, The predicted values of power load of multiple time periods within 24 hours in the future of the new energy storage system of the park are obtained by the following method: obtaining the number of workers, work plan, weather data and date type of the day; inputting the number of workers, work plan, weather data and date type of the day into a power load prediction model to obtain the predicted values of power load of multiple time periods within 24 hours in the future of the new energy storage system of the park.

3. The method of claim 2, wherein, The power load prediction model is obtained by the following method: obtaining the number of workers, work plan, weather data and date type and actual power load of multiple time periods of a historical day; training a pre-constructed time series model using the number of workers, work plan, weather data and date type of the historical day, and obtaining the power load prediction model when the power load of multiple time periods of the historical day predicted by the time series model within 24 hours in the future is equal to the actual power load of multiple time periods of the historical day.

4. The method of claim 2, wherein, Before the step of inputting the number of workers, work plan, weather data and date type of the day into a power load prediction model to obtain the predicted values of power load of multiple time periods within 24 hours in the future of the new energy storage system of the park, the method further comprises: preprocessing the number of workers, work plan, weather data and date type of the day; wherein the preprocessing comprises noise reduction processing and normalization processing.

5. The method of claim 1, wherein, The method further comprises: using formula (1) to calculate the charging and discharging power of the storage system of multiple time periods within 24 hours in the future and the length of multiple time periods respectively, to obtain the charging and discharging power of the storage system of multiple time periods within 24 hours in the future. （1）； wherein, represents the charging-discharging power for each period within the next 24 hours; represents the charging power for each period within the next 24 hours, which is positive; represents the discharging power for each period within the next 24 hours, which is negative; represents the length of time for each period within the next 24 hours; The energy storage system operation and maintenance cost, the park selling electricity to the grid degree electricity income, the park selling electricity to the grid electricity quantity, the park purchasing electricity from the grid degree electricity cost, the park purchasing electricity from the grid electricity quantity and the charging and discharging electricity quantity of the energy storage system in the plurality of time periods in the future 24 hours are calculated respectively by using formula (2), and the sum of electricity fees in the plurality of time periods in the future 24 hours is obtained; （2）； wherein, represents the sum of electricity charges of a plurality of time periods within the next 24 hours; represents the operation and maintenance cost of the energy storage system of each time period within the next 24 hours; represents the charging and discharging electricity quantity of the energy storage system of each time period within the next 24 hours; represents the degree electricity income of the park selling electricity to the grid of each time period within the next 24 hours; represents the electricity quantity of the park selling electricity to the grid of each time period within the next 24 hours; represents the degree electricity cost of the park buying electricity from the grid of each time period within the next 24 hours; represents the electricity quantity of the park buying electricity from the grid of each time period within the next 24 hours.

6. A park new energy storage system scheduling device, characterized in that, Comprise: The data acquisition module is used for acquiring the predicted values of power load and power generation of the new energy energy storage system of the park in a plurality of time periods in the future 24 hours; The first calculation module is used for optimizing and solving the predicted values of power load and power generation in the plurality of time periods in the future 24 hours by using a swarm intelligence algorithm, and obtaining the charging and discharging power in the plurality of time periods in the future 24 hours after preliminary optimization scheduling; wherein, the optimization and solving is based on the set objective function and constraint condition; the constraint condition comprises: state of charge constraint condition, balance power constraint condition and maximum charging and discharging power constraint condition; State of Charge constraint is: ; wherein, represents the State of Charge at the end of the next time period of each time period; represents the State of Charge at the end of each time period; represents the self-discharge rate of the energy storage battery of each time period; represents the charging efficiency of the energy storage battery of each time period; represents the charging power of the energy storage battery of each time period, which is positive; represents the discharging power of the energy storage battery of each time period, which is negative; represents the time interval between each time period; represents the rated capacity of the energy storage system of each time period; represents the minimum State of Charge allowed; represents the maximum State of Charge allowed; The balance power constraint condition is: ; wherein, represents the power generation of the new energy in each period, and is always positive; represents the power of the energy storage battery in each period, and is positive when charging and negative when discharging; represents the load power in each period, and is always positive; The maximum charge-discharge power constraint condition is: ; wherein, represents the maximum charge-discharge power allowed by the energy storage system; The data updating module is used for updating the charging and discharging power in the plurality of time periods in the future 24 hours after preliminary optimization scheduling by using the predicted values of power generation in the plurality of time periods in the 4 hours after the current period and the actual power generation in the plurality of time periods before the current period, and obtaining the updated charging and discharging power in the plurality of time periods in the future 24 hours; The second calculation module is used for optimizing and solving the updated charging and discharging power in the plurality of time periods in the future 24 hours and the remaining capacity of the energy storage system in the current period by using a swarm intelligence algorithm, and obtaining the charging and discharging power in the plurality of time periods in the future 24 hours after final optimization scheduling. 7.The park new energy storage system scheduling device according to claim 6, characterized in that, The data acquisition module is specifically used for: Acquiring the number of workers, work plan, weather data and date type of the day; The predicted values of power load of the new energy energy storage system of the park in the plurality of time periods in the future 24 hours are obtained by inputting the number of workers, work plan, weather data and date type of the day into a power load prediction model. 8.The park new energy storage system scheduling device according to claim 6, characterized in that, The device further comprises: The power calculation module is used for calculating the charging and discharging electricity quantity of the energy storage system in the plurality of time periods in the future 24 hours by using formula (1) and the charging and discharging power in the plurality of time periods in the future 24 hours after final optimization scheduling and the time length of the plurality of time periods respectively; （1）； wherein, represents the charging-discharging power for each period within the next 24 hours; represents the charging power for each period within the next 24 hours, which is positive; represents the discharging power for each period within the next 24 hours, which is negative; represents the length of time for each period within the next 24 hours; The electricity fee calculation module is used for calculating the energy storage system operation and maintenance cost, the park selling electricity to the grid degree electricity income, the park selling electricity to the grid electricity quantity, the park purchasing electricity to the grid degree electricity cost, the park purchasing electricity to the grid electricity quantity and the charging and discharging electricity quantity of the energy storage system in the future 24 hours by using formula (2), and obtaining the sum of electricity fees in the plurality of time periods in the future 24 hours; （2）； wherein, represents the sum of electricity charges of a plurality of time periods within the next 24 hours; represents the operation and maintenance cost of the energy storage system of each time period within the next 24 hours; represents the charging and discharging electricity quantity of the energy storage system of each time period within the next 24 hours; represents the degree electricity income of the park selling electricity to the grid of each time period within the next 24 hours; represents the electricity quantity of the park selling electricity to the grid of each time period within the next 24 hours; represents the degree electricity cost of the park purchasing electricity from the grid of each time period within the next 24 hours; represents the electricity quantity of the park purchasing electricity from the grid of each time period within the next 24 hours.

9. An electronic device, comprising: Comprise: A processor and a memory, the memory stores machine readable instructions executable by the processor, the machine readable instructions are executed by the processor to execute the scheduling method of the new energy energy storage system of the park in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions for causing a machine to perform the method of dispatching the new energy and energy storage system of the park according to any one of claims 1-7.

Images