Energy storage control method and system for new energy consumption

Abstract

This application proposes a method and system for energy storage control for new energy consumption. The method includes: establishing a short-term power forecast optimization model and calculating the optimized short-term power forecast value; establishing multiple conditional constraint models, configuring the energy storage capacity and energy storage power of new energy stations with the goal of maximizing the combined value of new energy power generation and energy storage investment return; inputting the optimized short-term power forecast value, energy storage capacity, and energy storage power into the energy storage objective function model to obtain the day-ahead planning curve for new energy storage; establishing an ultra-short-term power forecast optimization model and calculating the optimized ultra-short-term power forecast value; inputting the optimized ultra-short-term power forecast value, energy storage capacity, and energy storage power into the energy storage objective function model to obtain the output control curve for new energy storage; and controlling the energy storage output of the station according to the day-ahead planning curve and the output control curve. This method can rationally configure new energy storage and is conducive to promoting new energy consumption.

Description

Technical Field

[0001] The present application relates to the field of energy storage control technology, and in particular to an energy storage control method and system for new energy consumption. Background Art

[0002] The penetration of renewable energy power generation is gradually increasing. However, due to the volatility, randomness, and intermittency of renewable energy output, it is difficult to predict and has poor dispatchability, which can have a serious impact on the power system. When renewable energy accounts for a high proportion of power, improper allocation of renewable energy storage can lead to serious problems in renewable energy absorption, waste of electricity resources, and economic losses.

[0003] In related technologies, methods commonly used to solve the problem of new energy consumption include: improving power forecasting accuracy, limiting new energy output, and using energy storage regulation. However, improving power forecasting accuracy is difficult, and it is difficult to fundamentally change problems such as the intermittent and volatile nature of new energy. Limiting the output of new energy will affect the consumption of green electricity and is not in line with the growing renewal of new energy power supply. The use of energy storage regulation is usually to optimize control during the operation phase with the goal of maximizing new energy consumption. However, the current energy storage configuration scheme and consumption method of this method are not unified, making it difficult to achieve overall optimization.

[0004] Therefore, how to reasonably control the energy storage and configuration of new energy stations to promote the consumption of new energy has become an urgent problem that needs to be solved. Summary of the Invention

[0005] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0006] To this end, the first purpose of this application is to propose a storage control method for new energy consumption, which can reasonably configure the storage parameters of the new energy system and reasonably control the new energy storage output, thereby improving the accuracy of new energy storage control and promoting new energy consumption.

[0007] The second object of this application is to propose an energy storage control system for new energy consumption;

[0008] A third object of the present application is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, a first embodiment of the present application is to propose an energy storage control method for new energy consumption, the method comprising the following steps:

[0010] Establishing a short-term power prediction optimization model based on historical short-term power prediction data of the new energy station and the corresponding first related data, and calculating an optimized short-term power prediction value according to the short-term power prediction optimization model, wherein the short-term time length is in days;

[0011] Establish multiple conditional constraint models to calculate the energy storage capacity and power of the new energy station with the goal of maximizing the combined power generation of new energy and the return on investment of energy storage;

[0012] The optimized short-term power forecast value, the energy storage capacity, and the energy storage power are input into a preset energy storage objective function model, and a day-ahead planning curve for new energy storage is generated with the goal of optimizing the revenue and on-grid power within a preset number of days in the future;

[0013] Establishing an ultra-short-term power prediction optimization model based on historical ultra-short-term power prediction data of the new energy station and corresponding second related data, and calculating an optimized ultra-short-term power prediction value according to the ultra-short-term power prediction optimization model, wherein the ultra-short-term time length is in hours;

[0014] Inputting the optimized ultra-short-term power forecast value, the energy storage capacity, and the energy storage power into the energy storage objective function model, and generating an output control curve for the new energy storage in the next period of time with the goal of optimizing the revenue and online power generation in the next preset number of hours;

[0015] The energy storage output of the new energy station is controlled according to the day-ahead planning curve and the output control curve, so that the energy storage output of the new energy station in the next time period matches the electricity demand.

[0016] Optionally, in one embodiment of the present application, the first relevant data includes: the first station actual data, first resource data, first station unit status data and first unit position data within the time corresponding to the historical short-term power forecast data, and the historical short-term power forecast data of the new energy station and the corresponding first relevant data are used to establish a short-term power forecast optimization model through a multivariate linear regression method, including: calculating the difference between the historical short-term power forecast data and the first station actual data; according to the difference, the first resource data, the first station unit status data and the first unit position data, the probability distribution of the short-term power forecast deviation is statistically analyzed to establish a deviation distribution model; based on the deviation distribution model, the short-term power forecast optimization model is established by solving multivariate linear regression.

[0017] Optionally, in one embodiment of the present application, when calculating the energy storage capacity and energy storage power of the new energy station, the calculation target is generated by the following formula:

[0018]

[0019] in, ,

[0020] Where J is the sum of renewable energy power generation and energy storage investment return rate, ROI is the return on investment within the preset period, is the online power consumption of the new energy system and energy storage system at time t, Benefit is the total revenue of the new energy station within the preset period, Cost is the total cost within the preset period, T is the number of time intervals within the preset period, and t is any moment within the period.

[0021] Optionally, in one embodiment of the present application, the total revenue of the new energy station within the preset period is calculated by the following formula:

[0022]

[0023] in, is the on-grid electricity price of the new energy system at time t;

[0024] The total cost within the preset period is calculated using the following formula:

[0025]

[0026] in, is the unit capacity cost of the energy storage system, is the unit power cost of the energy storage system, is the fixed cost investment amount of the energy storage system, S is the rated capacity of the energy storage system, and P is the rated power of the energy storage system.

[0027] Optionally, in one embodiment of the present application, the multiple conditional constraint models include: energy storage charging and discharging power constraint, energy storage state of charge (SOC) constraint, and acceptable power constraint for new energy stations connected to the grid. The energy storage charging and discharging power constraint is expressed by the following formula:

[0028]

[0029] in, is the rated power of the energy storage system;

[0030] The energy storage state of charge (SOC) constraint is expressed by the following formula:

[0031]

[0032] in, is the energy storage SOC during period t, and are the maximum energy storage SOC and the minimum energy storage SOC in period t respectively;

[0033] The acceptable power constraint for the new energy station to be connected to the grid is expressed by the following formula:

[0034]

[0035] in, The maximum grid-connected power of the new energy station given by the power grid.

[0036] Optionally, in one embodiment of the present application, the second related data includes: the second station actual data, second resource data, second station unit status data and second unit position data within the time corresponding to the historical ultra-short-term power forecast data, and the ultra-short-term power forecast optimization model is established based on the historical ultra-short-term power forecast data of the new energy station and the corresponding second related data, including: calculating the difference between the historical ultra-short-term power forecast data and the second station actual data; combining the difference, the second resource data, the second station unit status data and the second unit position data to establish the ultra-short-term power forecast optimization model of the new energy station.

[0037] To achieve the above objectives, the second embodiment of the present application further proposes an energy storage control system for new energy consumption, comprising the following modules:

[0038] A first establishing module is configured to establish a short-term power prediction optimization model based on historical short-term power prediction data of the new energy station and corresponding first related data, and calculate an optimized short-term power prediction value according to the short-term power prediction optimization model, wherein the short-term time length is in days;

[0039] A calculation module is used to establish multiple conditional constraint models, with the goal of maximizing the combined energy generation of renewable energy and the energy storage investment return rate, to calculate the energy storage capacity and energy storage power of the renewable energy station;

[0040] A first generating module is configured to input the optimized short-term power forecast value, the energy storage capacity, and the energy storage power into a preset energy storage objective function model, and generate a day-ahead planning curve for new energy energy storage with the goal of optimizing the revenue and on-grid power within a preset number of days in the future;

[0041] A second establishing module is used to establish an ultra-short-term power prediction optimization model based on the historical ultra-short-term power prediction data of the new energy station and the corresponding second related data, and calculate an optimized ultra-short-term power prediction value according to the ultra-short-term power prediction optimization model, wherein the ultra-short-term time length is in hours;

[0042] The second generation module is configured to input the optimized ultra-short-term power forecast value, the energy storage capacity, and the energy storage power into the energy storage objective function model, and generate an output control curve for the new energy storage in the next period of time with the goal of optimizing the revenue and online power generation for a preset number of hours in the future;

[0043] The control module is used to control the energy storage output of the new energy station according to the day-ahead planning curve and the output control curve, so that the energy storage output of the new energy station in the next time period matches the electricity demand.

[0044] Optionally, in one embodiment of the present application, the first relevant data includes: the first station actual data, first resource data, first station unit status data and first unit position data within the time corresponding to the historical short-term power forecast data, and the first establishment module is specifically used to: calculate the difference between the historical short-term power forecast data and the first station actual data; based on the difference, the first resource data, the first station unit status data and the first unit position data, perform statistics on the probability distribution of the short-term power forecast deviation and establish a deviation distribution model; based on the deviation distribution model, establish the short-term power forecast optimization model by solving multiple linear regression.

[0045] Optionally, in one embodiment of the present application, the calculation module is specifically configured to generate a calculation target by the following formula when calculating the energy storage capacity and energy storage power of the new energy station:

[0046]

[0047] in, ,

[0048] Where J is the sum of renewable energy power generation and energy storage investment return rate, ROI is the return on investment within the preset period, is the online power consumption of the new energy system and energy storage system at time t, Benefit is the total revenue of the new energy station within the preset period, Cost is the total cost within the preset period, T is the number of time intervals within the preset period, and t is any moment within the period.

[0049] In order to implement the above embodiments, the third aspect of the present application further proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the energy storage control method for new energy consumption in the above embodiments is implemented.

[0050] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects: By establishing a corresponding neural network model, this application optimizes and predicts the short-term and ultra-short-term power of renewable energy, and combines the calculated configuration parameters such as the energy storage capacity and power of the renewable energy station to generate a new energy storage control curve for the next day and the next period. This allows for control of renewable energy storage from multiple perspectives, thereby improving the rationality and accuracy of renewable energy station energy storage control and enhancing the control capabilities of the renewable energy system. Furthermore, through the rational control of renewable energy storage, it is possible to promote the consumption of renewable energy, avoid the waste of renewable energy power resources, and ensure the benefits of renewable energy power generation.

[0051] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0053] Figure 1 This is a flow chart of an energy storage control method for new energy consumption proposed in an embodiment of the present application;

[0054] Figure 2 A flowchart of a specific method for constructing a short-term power prediction optimization model proposed in an embodiment of the present application;

[0055] Figure 3 This is a structural diagram of an energy storage control system for new energy consumption proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0057] The following describes an energy storage control method and device for new energy consumption proposed in an embodiment of the present application with reference to the accompanying drawings.

[0058] Figure 1 This is a flow chart of an energy storage control method for new energy consumption proposed in an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0059] Step S101: Based on the historical short-term power forecast data of the new energy station and the corresponding first related data, a short-term power forecast optimization model is established, and an optimized short-term power forecast value is calculated according to the short-term power forecast optimization model, wherein the short-term time length is in days.

[0060] Among them, new energy sites include sites that generate electricity through new energy systems such as photovoltaic power generation and wind power generation. The new energy sites in this application also include energy storage systems, which can store electricity and output power when needed. The first relevant data is the relevant data of the new energy sites within the corresponding period of historical short-term power forecast data. The short-term time length is measured in days. For example, the historical short-term power forecast data can be the power forecast data for the previous day or several days.

[0061] In one embodiment of the present application, the first relevant data includes: the first station actual data, the first resource data, the first station unit status data, and the first unit location data within the time corresponding to the historical short-term power forecast data. In this embodiment of the present application, a short-term power forecast optimization model can be established through a multivariate linear regression method. Specifically, in order to more clearly illustrate the specific implementation process of establishing the short-term power forecast optimization model in this application, the following is an exemplary description of a method for constructing a short-term power forecast optimization model proposed in this embodiment. Figure 2 This is a flowchart of a specific method for constructing a short-term power prediction optimization model proposed in an embodiment of the present application, such as Figure 2 As shown, the method includes the following steps:

[0062] Step S201: Calculate the difference between historical short-term power prediction data and actual power data of the first station.

[0063] Specifically, after obtaining historical short-term power forecast data and first related data within a time period corresponding to the historical short-term power forecast data by reading historical data stored in a database, the deviation between the historical short-term power forecast data and the actual power data is calculated. The actual power data includes actual data such as the actual power generated by the energy station within the corresponding time period.

[0064] Step S202 : statistically analyzing the probability distribution of the short-term power forecast deviation based on the difference, the first resource data, the first station unit status data, and the first unit location data, and establishing a deviation distribution model.

[0065] Specifically, we analyze the impact of multiple factors such as resource data, station unit status data, and unit location data on the deviation between actual data and predicted data, conduct statistics on the probability distribution of short-term power forecast deviations caused by various data, and establish a deviation distribution model. The deviation distribution model is a data model used to represent the distribution law of difference values.

[0066] Step S203 : establishing a short-term power prediction optimization model by solving multiple linear regression based on the deviation distribution model.

[0067] Specifically, short-term power is used as the dependent variable, and multiple data affecting short-term power are used as independent variables. Due to the presence of multiple independent variables, this application uses multiple linear regression to analyze the relationship between short-term power and multiple factors. Combined with the deviation distribution model obtained in the above steps, the weight of each independent variable, i.e., the regression coefficient, is solved with the goal of reducing the deviation. In specific implementation, the model parameters can be estimated using methods such as the least squares method. Then, a short-term power prediction optimization model is established based on the obtained parameters, and the optimized short-term power prediction value is subsequently calculated based on the trained short-term power prediction optimization model.

[0068] It should be noted that the prediction model established in this application can be various neural network models based on deep learning or machine learning. When establishing the prediction model, the historical data obtained and the parameters obtained by the multivariate linear regression method are used as training data to train the pre-built neural network model, configure the weights of the parameters of each layer in the neural network model, and obtain the corresponding prediction model after the training is completed.

[0069] For example, a long short-term memory network (LSTM) can be selected as a prediction model, and then the long short-term memory artificial neural network LSTM can be trained. The specific training method can refer to the training method of the neural network model in the existing technology, including data preprocessing, feature extraction, selection and classification, etc. The objective function is optimized through the gradient descent algorithm until the prediction accuracy meets the requirements. It will not be described in detail here.

[0070] Furthermore, after the short-term power prediction optimization model is trained, the relevant data for the current energy storage control scenario is input into the trained long short-term memory artificial neural network (LSTM) to obtain the output prediction value of the prediction optimization model, thereby optimizing the short-term power prediction. In this application, the subsequent prediction models can be trained in accordance with the above method, and no further details will be given.

[0071] Step S102 , establishing multiple conditional constraint models, with the goal of maximizing the combined energy generation and energy storage investment return rate, to calculate the energy storage capacity and energy storage power of the new energy station.

[0072] In one embodiment of the present application, the energy storage capacity and power of a new energy station can be calculated using an ant colony optimization algorithm. The ant colony optimization algorithm is a probabilistic algorithm used to find optimization paths. It features distributed computing, positive feedback, and heuristic search, and can calculate the optimal solution to the problem being optimized. In this embodiment of the present application, the ant colony optimization algorithm can be used to calculate the energy storage parameters to be optimized, such as the energy storage capacity and power of a new energy station.

[0073] Specifically, an ant colony optimization algorithm is used to calculate the energy storage capacity and power of the energy station that maximizes the combined renewable energy generation and energy storage investment return, subject to the constraints of multiple conditional constraint models. The conditional constraint model is a data model used to represent each constraint.

[0074] In one embodiment of the present application, when calculating the energy storage capacity and energy storage power of a new energy station, the objective function of the above calculation can be generated by combining the new energy power generation and the energy storage investment return rate using the following formula:

[0075]

[0076] in, ,

[0077] Where J is the sum of renewable energy power generation and energy storage investment return rate, ROI is the return on investment within the preset period, is the online power consumption of the new energy system and energy storage system at time t, Benefit is the total revenue of the new energy station within the preset period, Cost is the total cost within the preset period, T is the number of time intervals within the preset period, and t is any moment within the preset period.

[0078] In this embodiment, the total benefit of the new energy station within the above preset period is calculated by the following formula:

[0079]

[0080] in, is the on-grid electricity price of the new energy system at time t, It is the online power of new energy + energy storage at time t.

[0081] Furthermore, the total cost within the above preset period is calculated using the following formula:

[0082]

[0083] in, is the unit capacity cost of the energy storage system, is the unit power cost of the energy storage system, is the fixed cost investment amount of the energy storage system, S is the rated capacity of the energy storage system, and P is the rated power of the energy storage system.

[0084] Therefore, this application constructs an overall target model for configuring new energy storage parameters:

[0085]

[0086] By maximizing the target model, that is, combining the renewable energy power generation and the energy storage investment return rate, with the maximum of this combination as the goal, optimization algorithms such as ant colony are used to calculate the capacity and power of the energy storage configured in the renewable energy station.

[0087] In an embodiment of the present application, multiple conditional constraint models include: energy storage charging and discharging power constraints, energy storage state of charge (SOC) constraints, and acceptable power constraints for new energy stations connected to the power grid.

[0088] Specifically, as a first example, this application constructs an equation constraint for the combined output power of new energy and energy storage. In this example, the combined output power of new energy and energy storage is equal to the actual output power of the new energy station minus the charging and discharging power of the energy storage system, which can be specifically expressed by the following formula:

[0089]

[0090] in, It is the combined output power of new energy + energy storage. It is the actual power generated by new energy. is the charging and discharging power of the energy storage system. When When , it means that the energy storage system is discharging. Charging the energy storage system means that the excess power generation of new energy is stored and utilized, and the actual power generation of new energy decreases. Discharging the energy storage system means releasing part of the battery power, which increases the actual power generation of new energy.

[0091] As a second example, this application constructs energy storage charge and discharge power constraints. In this example, the energy storage charge and discharge power constraints are expressed by the following formula:

[0092]

[0093] in, is the rated power of the energy storage system.

[0094] As a third example, this application constructs an energy storage SOC constraint. In this example, the energy storage state of charge SOC constraint is expressed by the following formula:

[0095]

[0096] in, is the energy storage SOC during period t, and They are the maximum energy storage SOC and the minimum energy storage SOC in period t respectively.

[0097] As a fourth example, this application constructs an acceptable power constraint for a new energy station to access the grid. In this example, the acceptable power constraint for a new energy station to access the grid is expressed by the following formula:

[0098]

[0099] in, The maximum grid-connected power of the new energy station given by the power grid.

[0100] In step S103, the optimized short-term power forecast value, energy storage capacity, and energy storage power are input into a preset energy storage objective function model, and a day-ahead planning curve for new energy storage is generated with the goal of optimizing the revenue and grid-connected power within a preset number of days in the future.

[0101] The preset number of days is determined based on actual forecasting needs. For example, in order to improve the accuracy and pertinence of the generated day-ahead planning curve, the day-ahead planning curve can be generated for the next day with the goal of optimizing the revenue and online power consumption for the next day.

[0102] In an embodiment of the present application, the grid-connected electricity price of the new energy station and the short-term optimized power forecast data after optimization in step S101 are obtained, and then the configured energy storage capacity, power, and other energy storage operation characteristic parameters calculated in step S102, such as energy storage duration, are obtained. Then, combined with the above parameters, the above parameters are brought into a pre-established station configuration energy storage objective function model. In this model, with the goal of optimizing the revenue and grid-connected power for the next day, the wolf pack algorithm is used to optimize the energy storage output curve for the next day to obtain the day-ahead planning curve for energy storage.

[0103] The wolf pack algorithm, a swarm intelligence algorithm, is based on a bottom-up design approach using artificial wolves and a collaborative search path based on division of responsibilities. In this embodiment, the wolf pack algorithm is used to optimize the energy storage output for the next day. Specifically, the output of the energy storage system corresponding to the optimal revenue and grid-connected power is calculated, thereby obtaining the energy storage output curve for the next day, which is used as the day-ahead planning curve.

[0104] Step S104: Based on the historical ultra-short-term power prediction data of the new energy station and the corresponding second related data, an ultra-short-term power prediction optimization model is established, and the optimized ultra-short-term power prediction value is calculated according to the ultra-short-term power prediction optimization model, wherein the ultra-short-term time length is in hours.

[0105] The second relevant data is the relevant data of the new energy station within the corresponding time of the historical ultra-short-term power forecast data. The ultra-short-term time length is shorter than the short-term time length. For example, the historical ultra-short-term power forecast data can be the power forecast data within one or several hours before the current moment.

[0106] In one embodiment of the present application, the acquired second relevant data includes: actual power transmission data of the second station, second resource data, unit status data of the second station, and second unit location data within a time period corresponding to the historical ultra-short-term power forecast data. In this embodiment, establishing the ultra-short-term power forecast optimization model includes first calculating the difference between the historical ultra-short-term power forecast data and the actual power transmission data of the second station, and then combining the difference, the second resource data, the unit status data of the second station, and the second unit location data to establish the ultra-short-term power forecast optimization model for the new energy station.

[0107] Specifically, ultra-short-term power forecast data of new energy stations, actual data of stations at corresponding times, resource data, station unit status data, unit location data, etc. are obtained. According to the deviation between the ultra-short-term power forecast data and actual data of new energy stations, combined with resource data, station unit status data, unit location data, etc., the above data are used as training data to train pre-built long and short neural network models. After the training is completed, an ultra-short-term power prediction optimization model is obtained, and the optimized ultra-short-term power prediction value is calculated through this model.

[0108] Step S105 , inputting the optimized ultra-short-term power forecast value, energy storage capacity, and energy storage power into the energy storage objective function model, and generating an output control curve for the next period of time with the goal of optimizing the revenue and on-grid power in the next preset number of hours.

[0109] The number of hours selected is predetermined based on actual forecasting needs. For example, the optimal forecast period can be selected by combining historical operating experience of new energy stations and expert knowledge. The output control curve of new energy storage in the next cycle, that is, within 4 hours after the current moment, can be generated with the goal of optimizing revenue and online power generation in the next 4 hours.

[0110] Among them, the next time period corresponding to the output control curve is the next preset number of hours, which can refer to the next 4-hour period after the current moment with reference to the above example. In one embodiment of the present application, real-time new energy grid-connected electricity price data and the optimized ultra-short-term power forecast data obtained in step S104 are obtained, and combined with other energy storage operation characteristic parameters such as energy storage capacity, energy storage power and duration, they are brought into the established site configuration energy storage objective function model. Among them, the site configuration energy storage objective function model can be the same as the objective function model in step S103, and then with the goal of optimizing the revenue and grid-connected power in the next 4 hours, the wolf pack algorithm is used to optimize the energy storage output curve for the next 4 hours, and the output control curve of the energy storage is obtained, so as to facilitate the subsequent control of the energy storage output at the next moment according to the output control curve.

[0111] Step S106 , controlling the energy storage output of the new energy station according to the day-ahead planning curve and the output control curve, so that the energy storage output of the new energy station in the next period matches the electricity demand.

[0112] In one embodiment of the present application, the energy storage output for the next day is configured in advance as a whole according to the day-ahead planning curve, and the energy storage output for the next period is controlled in real time according to the output control curve. By combining these two control methods, new energy storage is controlled from the perspectives of both pre-overall control and real-time control.

[0113] Furthermore, by controlling energy storage in this manner, the energy storage output of renewable energy sources is aligned with actual electricity demand, and the energy storage output matches electricity demand. For example, the energy storage output of renewable energy sources is equal to the actual electricity demand of the market, or the error is within an allowable range, so that the energy storage output of renewable energy sources can be fully absorbed, which is conducive to the absorption of renewable energy electricity. Specifically, the on-grid power of renewable energy power generation systems and energy storage systems can be adjusted based on the day-ahead planning curve and the output control curve. For example, the on-grid power of the energy storage system in the next four hours can be determined based on the output control curve. Alternatively, the excess power in the next period can be dispatched and transmitted to other load points with electricity demand based on the current energy storage power of the energy storage system, the day-ahead planning curve, and the energy storage output curve for the next four hours, thereby promoting the absorption of renewable energy electricity.

[0114] In summary, the energy storage control method for new energy consumption in the embodiment of the present application first establishes a short-term power prediction optimization model through the multivariate linear regression method, calculates the optimized short-term power prediction value, then configures the energy storage capacity and energy storage power of the new energy station, and then inputs the optimized short-term power prediction value, energy storage capacity and energy storage power into the energy storage objective function model to obtain the day-ahead planning curve of the new energy storage, then establishes an ultra-short-term power prediction optimization model, calculates the optimized ultra-short-term power prediction value, and inputs the optimized ultra-short-term power prediction value, energy storage capacity and energy storage power into the energy storage objective function model to obtain the output control curve of the new energy storage, and finally performs energy storage control according to the day-ahead planning curve and the output control curve. This method optimizes and predicts the short-term power and ultra-short-term power of the new energy by establishing a corresponding neural network model, and combines the calculated configuration parameters such as the energy storage capacity and power of the new energy station to generate the new energy storage control curve for the next day and the next period, thereby controlling the new energy storage from multiple angles, thereby improving the rationality and accuracy of the energy storage control of the new energy station and enhancing the control capability of the new energy system. Furthermore, through the reasonable control of new energy storage, it is possible to promote the consumption of new energy, avoid the waste of new energy power resources and ensure the benefits of new energy power generation.

[0115] In order to implement the above embodiment, the present application also proposes an energy storage control system for new energy consumption. Figure 3 This is a structural diagram of an energy storage control system for new energy consumption proposed in an embodiment of the present application, such as Figure 3 As shown, the system includes a first establishing module 100 , a calculating module 200 , a first generating module 300 , a second establishing module 400 , a second generating module 500 and a control module 600 .

[0116] Among them, the first establishment module 100 is used to establish a short-term power prediction optimization model based on the historical short-term power prediction data of the new energy site and the corresponding first related data, and calculate the optimized short-term power prediction value according to the short-term power prediction optimization model, wherein the short-term time length is in days.

[0117] The calculation module 200 is used to establish multiple conditional constraint models, and calculate the energy storage capacity and energy storage power of the new energy station with the goal of maximizing the combined value of new energy power generation and energy storage investment return rate.

[0118] The first generation module 300 is used to input the optimized short-term power forecast value, energy storage capacity and energy storage power into a preset energy storage objective function model, and generate a day-ahead planning curve for new energy storage with the goal of optimizing the revenue and online power within a preset number of days in the future.

[0119] The second establishment module 400 is used to establish an ultra-short-term power prediction optimization model based on the historical ultra-short-term power prediction data of the new energy station and the corresponding second related data, and calculate the optimized ultra-short-term power prediction value according to the ultra-short-term power prediction optimization model, wherein the ultra-short-term time length is in hours.

[0120] The second generation module 500 is used to input the optimized ultra-short-term power forecast value, energy storage capacity and energy storage power into the energy storage objective function model, and generate the output control curve of the new energy storage in the next period with the goal of optimizing the revenue and online power in the next preset number of hours.

[0121] The control module 600 is used to control the energy storage output of the new energy station according to the day-ahead planning curve and the output control curve, so that the energy storage output of the new energy station in the next period matches the electricity demand.

[0122] Optionally, in one embodiment of the present application, the first relevant data includes: the first station actual data, the first resource data, the first station unit status data and the first unit position data within the time corresponding to the historical short-term power forecast data, and the first establishment module 100 is specifically used to: calculate the difference between the historical short-term power forecast data and the first station actual data; based on the difference, the first resource data, the first station unit status data and the first unit position data, perform statistics on the probability distribution of the short-term power forecast deviation and establish a deviation distribution model; based on the deviation distribution model, establish a short-term power forecast optimization model by solving multiple linear regression.

[0123] Optionally, in one embodiment of the present application, the calculation module 200 is specifically configured to generate a calculation target by using the following formula when calculating the energy storage capacity and energy storage power of the new energy station:

[0124]

[0125] in, ,

[0126] Where J is the sum of renewable energy power generation and energy storage investment return rate, ROI is the return on investment within the preset period, is the online power consumption of the new energy system and energy storage system at time t, Benefit is the total revenue of the new energy station within the preset period, Cost is the total cost within the preset period, T is the number of time intervals within the preset period, and t is any moment within the period.

[0127] Optionally, in one embodiment of the present application, the calculation module 200 is specifically configured to calculate the total revenue of the new energy station within a preset period using the following formula:

[0128]

[0129] in, is the on-grid electricity price of the new energy system at time t;

[0130] The total cost within the preset period is calculated using the following formula:

[0131]

[0132] in, is the unit capacity cost of the energy storage system, is the unit power cost of the energy storage system, is the fixed cost investment amount of the energy storage system, S is the rated capacity of the energy storage system, and P is the rated power of the energy storage system.

[0133] Optionally, in one embodiment of the present application, the multiple conditional constraint models include: energy storage charging and discharging power constraint, energy storage state of charge (SOC) constraint, and acceptable power constraint for new energy station access to the grid. The calculation module 200 is specifically configured to generate the energy storage charging and discharging power constraint using the following formula:

[0134]

[0135] in, is the rated power of the energy storage system;

[0136] The energy storage state of charge (SOC) constraint is generated by the following formula:

[0137]

[0138] in, is the energy storage SOC during period t, and are the maximum energy storage SOC and the minimum energy storage SOC in period t respectively;

[0139] The acceptable power constraint for new energy stations connected to the grid is generated by the following formula:

[0140]

[0141] in, The maximum grid-connected power of the new energy station given by the power grid.

[0142] Optionally, in one embodiment of the present application, the second related data includes: the second station actual data, second resource data, second station unit status data and second unit position data within the time corresponding to the historical ultra-short-term power forecast data, and the second establishment module 400 is specifically used to: calculate the difference between the historical ultra-short-term power forecast data and the second station actual data; combine the difference, the second resource data, the second station unit status data and the second unit position data to establish an ultra-short-term power forecast optimization model for the new energy station.

[0143] It should be noted that the aforementioned explanation of the embodiment of the energy storage control method for new energy consumption is also applicable to the system of this embodiment and will not be repeated here.

[0144] In summary, the energy storage control system for new energy consumption in the embodiments of the present application establishes a corresponding neural network model to optimize and predict the short-term power and ultra-short-term power of new energy. Combined with the calculated configuration parameters such as the energy storage capacity and power of the new energy station, it generates new energy storage control curves for the next day and the next period. This allows for control of new energy storage from multiple perspectives, thereby improving the rationality and accuracy of energy storage control at the new energy station and enhancing the control capabilities of the new energy system. Furthermore, through the rational control of new energy storage, it is possible to promote new energy consumption, avoid wasting new energy power resources, and ensure the benefits of new energy power generation.

[0145] In order to implement the above embodiments, the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the energy storage control method for new energy consumption as described in any of the above embodiments.

[0146] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0147] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0148] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0149] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" is any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0150] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0151] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0152] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0153] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for controlling energy storage for absorbing new energy, characterized in that: The following steps are involved: Establishing a short-term power prediction optimization model based on historical short-term power prediction data of the new energy station and the corresponding first related data, and calculating an optimized short-term power prediction value according to the short-term power prediction optimization model, wherein the short-term time length is in days; Establish multiple conditional constraint models to calculate the energy storage capacity and power of the new energy station with the goal of maximizing the combined power generation of new energy and the return on investment of energy storage; The optimized short-term power forecast value, the energy storage capacity, and the energy storage power are input into a preset energy storage objective function model, and a day-ahead planning curve for new energy storage is generated with the goal of optimizing the revenue and on-grid power within a preset number of days in the future; Establishing an ultra-short-term power prediction optimization model based on historical ultra-short-term power prediction data of the new energy station and corresponding second related data, and calculating an optimized ultra-short-term power prediction value according to the ultra-short-term power prediction optimization model, wherein the ultra-short-term time length is in hours; Inputting the optimized ultra-short-term power forecast value, the energy storage capacity, and the energy storage power into the energy storage objective function model, and generating an output control curve for the new energy storage in the next period of time with the goal of optimizing the revenue and online power generation in the next preset number of hours; The energy storage output of the new energy station is controlled according to the day-ahead planning curve and the output control curve, so that the energy storage output of the new energy station in the next time period matches the electricity demand.

2. The energy storage control method according to claim 1, characterized in that: The first related data includes: actual power generation data of the first station, first resource data, status data of the first station unit, and location data of the first unit within a time period corresponding to the historical short-term power forecast data. The short-term power forecast optimization model is established by a multiple linear regression method based on the historical short-term power forecast data of the new energy station and the corresponding first related data, including: Calculating the difference between the historical short-term power forecast data and the actual power data transmitted by the first station; performing statistics on a probability distribution of a short-term power forecast deviation based on the difference, the first resource data, the first station unit status data, and the first unit location data, and establishing a deviation distribution model; Based on the deviation distribution model, the short-term power prediction optimization model is established by solving multiple linear regression.

3. The energy storage control method according to claim 1, characterized in that: When calculating the energy storage capacity and energy storage power of the new energy station, the calculation target is generated by the following formula: in, , Where J is the sum of renewable energy power generation and energy storage investment return rate, ROI is the return on investment within the preset period, is the online power consumption of the new energy system and energy storage system at time t, Benefit is the total revenue of the new energy station within the preset period, Cost is the total cost within the preset period, T is the number of time intervals within the preset period, and t is any moment within the period.

4. The energy storage control method according to claim 3, characterized in that: The total revenue of the new energy station within the preset period is calculated using the following formula: in, is the on-grid electricity price of the new energy system at time t; The total cost within the preset period is calculated using the following formula: in, is the unit capacity cost of the energy storage system, is the unit power cost of the energy storage system, is the fixed cost investment amount of the energy storage system, S is the rated capacity of the energy storage system, and P is the rated power of the energy storage system.

5. The energy storage control method according to claim 1, characterized in that: The multiple conditional constraint models include: energy storage charging and discharging power constraint, energy storage state of charge (SOC) constraint, and acceptable power constraint for new energy stations connected to the grid. The energy storage charging and discharging power constraint is expressed by the following formula: in, is the rated power of the energy storage system; The energy storage state of charge (SOC) constraint is expressed by the following formula: in, for t Energy storage SOC of the time period, and They are t The maximum energy storage SOC and minimum energy storage SOC of the time period; The acceptable power constraint for the new energy station to be connected to the grid is expressed by the following formula: in, The maximum grid-connected power of the new energy station given by the power grid.

6. The energy storage control method according to claim 1, characterized in that: The second related data includes: actual power generation data of the second station, second resource data, status data of the second station unit, and location data of the second unit within a time period corresponding to the historical ultra-short-term power forecast data. The ultra-short-term power forecast optimization model is established based on the historical ultra-short-term power forecast data of the new energy station and the corresponding second related data, including: Calculating the difference between the historical ultra-short-term power forecast data and the actual power data of the second station; An ultra-short-term power prediction optimization model for the new energy station is established by combining the difference, the second resource data, the second station unit status data and the second unit location data.

7. An energy storage control system for new energy consumption, characterized in that: include: A first establishing module is configured to establish a short-term power prediction optimization model based on historical short-term power prediction data of the new energy station and corresponding first related data, and calculate an optimized short-term power prediction value according to the short-term power prediction optimization model, wherein the short-term time length is in days; A calculation module is used to establish multiple conditional constraint models to calculate the energy storage capacity and energy storage power of the new energy station with the goal of maximizing the combined amount of new energy power generation and the energy storage investment return rate; A first generating module is configured to input the optimized short-term power forecast value, the energy storage capacity, and the energy storage power into a preset energy storage objective function model, and generate a day-ahead planning curve for new energy energy storage with the goal of optimizing the revenue and on-grid power within a preset number of days in the future; A second establishing module is used to establish an ultra-short-term power prediction optimization model based on the historical ultra-short-term power prediction data of the new energy station and the corresponding second related data, and calculate an optimized ultra-short-term power prediction value according to the ultra-short-term power prediction optimization model, wherein the ultra-short-term time length is in hours; The second generation module is configured to input the optimized ultra-short-term power forecast value, the energy storage capacity, and the energy storage power into the energy storage objective function model, and generate an output control curve for the new energy storage in the next period of time with the goal of optimizing the revenue and online power generation for a preset number of hours in the future; A control module is used to control the energy storage output of the new energy station according to the day-ahead planning curve and the output control curve, so that the energy storage output of the new energy station in the next time period matches the electricity demand.

8. The control system according to claim 7, characterized in that: The first related data includes: first station actual power data, first resource data, first station unit status data, and first unit location data within a time period corresponding to the historical short-term power forecast data. The first establishing module is specifically configured to: Calculating the difference between the historical short-term power forecast data and the actual power data transmitted by the first station; performing statistics on a probability distribution of a short-term power forecast deviation based on the difference, the first resource data, the first station unit status data, and the first unit location data, and establishing a deviation distribution model; Based on the deviation distribution model, the short-term power prediction optimization model is established by solving multiple linear regression.

9. The control system according to claim 7, characterized in that: The calculation module is specifically used to generate a calculation target using the following formula when calculating the energy storage capacity and energy storage power of the new energy station: in, , Where J is the sum of renewable energy power generation and energy storage investment return rate, ROI is the return on investment within the preset period, is the online power consumption of the new energy system and energy storage system at time t, Benefit is the total revenue of the new energy station within the preset period, Cost is the total cost within the preset period, T is the number of time intervals within the preset period, and t is any moment within the period.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the energy storage control method for new energy consumption as described in any one of claims 1 to 6 is implemented.

Images