Virtual power plant control method, system and equipment based on neural network

Abstract

The present application discloses a virtual power plant control method, system and device based on neural network, including: obtaining the power supply gap curve and incentive function of the power grid system in the target period; obtaining the power generation curve of the distributed power generation system in the target period through the distributed power generation system; obtaining the charge and discharge loss model through the energy storage system; constructing an optimal incentive model based on the power supply gap curve, the incentive function, the power generation curve and the charge and discharge loss model as constraints, and the optimal incentive model is configured to obtain energy storage schemes and / or energy release schemes to obtain optimal incentives; obtaining energy storage schemes and energy release schemes according to the optimal incentive model. At least the problem of lack of effective means for controlling virtual power plants in the prior art, low utilization of virtual power plants, and inability to control energy storage and energy release according to changes in power grid demand to improve the benefits of virtual power plants is solved.

Description

Technical Field

[0001] The present application relates to the field of energy management technology, and in particular to a virtual power plant control method, system and equipment based on a neural network. Background Art

[0002] With the continuous development of clean energy, decentralized energy, and controllable loads, virtual power plants that optimize energy structure and consumption and improve grid efficiency and stability have been booming. Virtual power plants are integrated energy systems that use advanced communication technology, load forecasting, and coordinated control to integrate and optimize multiple energy configurations. They can respond to changes in market and grid demand in real time and improve grid flexibility and resilience. With the depletion of fossil energy and the intensification of environmental pollution, vigorously developing renewable energy has become a strategic choice for countries to achieve a low-carbon economy and build a sustainable energy system.

[0003] Virtual power plants are mainly composed of distributed energy, energy storage systems and loads. As a highly flexible and adaptable means of resource integration, virtual power plants have the dual identities of producers and consumers. They can change their operating status according to demand and source, and truly realize the interaction between source and load. In the eyes of power grid companies, load virtual power plants are a single resource. Virtual power plants participate in peak load auxiliary services, demand response and obtain incentives.

[0004] At present, there is a lack of effective means to control virtual power plants, the utilization rate of virtual power plants is low, and it is impossible to control energy storage and release according to changes in power grid demand to improve the efficiency of virtual power plants. Summary of the invention

[0005] The present invention provides a virtual power plant control method, system and equipment based on a neural network, and provides a solution for storing and releasing energy in a virtual power plant control method, which at least solves the problems in the prior art of lacking effective means for controlling virtual power plants, low utilization of virtual power plants, and inability to perform energy storage and release control according to changes in power grid demand to improve the efficiency of virtual power plants.

[0006] The present application provides a virtual power plant control method based on a neural network, wherein the virtual power plant is connected to a power grid system, and the virtual power plant includes a control platform, a distributed power generation system, and an energy storage system. The method is executed by the control platform and includes the following steps:

[0007] Obtaining a power supply gap curve and an incentive function of the power grid system during a target period;

[0008] Obtaining, through the distributed power generation system, a power generation curve of the distributed power generation system in a target period;

[0009] Obtaining a charge and discharge loss model through the energy storage system;

[0010] According to the power supply gap curve, the incentive function, the power generation curve and the charge-discharge loss model as constraints, an optimal incentive model is constructed, wherein the optimal incentive model is configured to obtain an energy storage scheme and / or an energy release scheme to obtain an optimal incentive;

[0011] The energy storage plan and energy release plan are obtained according to the optimal incentive model.

[0012] By adopting the above scheme, the power supply gap curve and the incentive function are used to store the generated electricity during the period of low incentive through the energy storage system, and then the stored electricity is input into the power grid through the energy storage system during the period of high incentive to obtain the optimal incentive. This at least solves the problems in the prior art of lacking effective means for controlling virtual power plants, low utilization of virtual power plants, and inability to control energy storage and release according to changes in power grid demand to improve the efficiency of virtual power plants.

[0013] Optionally, the step of constructing an optimal incentive model based on the power supply gap curve, the incentive function, the power generation curve and the charge and discharge loss model as constraints includes:

[0014] According to the power supply gap curve, the power generation curve and the power release scheme, a first power release constraint is obtained, wherein the first power release constraint is used to characterize that the sum of the power release electricity and the power generation electricity in any time period within the target time period cannot exceed the power gap in the power supply gap curve in the time period;

[0015] According to the power generation curve and the energy storage scheme, a first energy storage constraint is obtained, wherein the first energy storage constraint is used to indicate that the energy storage quantity in any time period within the target time period cannot exceed the power generation quantity;

[0016] According to the energy storage scheme, the energy release scheme and the charge-discharge loss model, a second energy release constraint is obtained, wherein the second energy release constraint is used to characterize that the energy release quantity before any time point in the target time period cannot exceed the energy storage quantity obtained after calculation by the charge-discharge loss model;

[0017] According to the energy storage scheme, the energy release scheme and the energy storage system, a second energy storage constraint is obtained, wherein the second energy storage constraint is used to characterize that the amount of electricity in the energy storage system at any time point within the target time period does not exceed the energy storage upper limit of the energy storage system;

[0018] According to the power generation curve, the energy storage scheme, the energy release scheme and the incentive function, a target incentive constraint is obtained, wherein the target incentive constraint is used to characterize that the incentive obtained by adopting the energy storage scheme and the energy release scheme is maximized;

[0019] The optimal incentive model is constructed according to the first energy release constraint, the first energy storage constraint, the second energy release constraint, the second energy storage constraint and the target incentive constraint.

[0020] Optionally, the step of obtaining the power supply gap curve and incentive function of the power grid system in the target period includes:

[0021] Based on the historical power consumption data and historical power consumption characteristic data of the power grid system power supply area, a power consumption prediction model is established to predict the power consumption data based on the power consumption characteristic data;

[0022] Predicting the power consumption data of the power supply area of ​​the power grid system according to the power consumption prediction model to obtain a power consumption data curve;

[0023] According to the historical power generation data and historical power supply characteristic data of the power grid system, a power supply prediction model is established for predicting the power supply data according to the power supply characteristic data;

[0024] Predicting the power supply data of the power grid system according to the power supply prediction model to obtain a power supply data curve;

[0025] Obtaining the power supply gap curve according to the power consumption data curve and the power supply data curve;

[0026] The incentive function is obtained according to the power supply gap curve and a preset incentive standard.

[0027] Optionally, the step of obtaining, through the distributed power generation system, a power generation curve of the distributed power generation system in a target period includes:

[0028] Establishing a GA-LSTM model, wherein the GA-LSTM model is a model for optimizing LSTM neural network parameter weights and biases through a genetic algorithm;

[0029] Obtain a power generation training set and a power generation verification set based on historical power generation data and historical power generation characteristic data;

[0030] The GA-LSTM model is trained according to the power generation training set and the power generation verification set to obtain a power generation prediction model with compound preset conditions;

[0031] Obtaining power generation characteristic data corresponding to a target period through the distributed power generation system;

[0032] According to the power generation prediction model and the power generation characteristic data corresponding to the target time period, a power generation curve of the distributed power generation system in the target time period is obtained.

[0033] Optionally, the virtual power plant further includes a new energy vehicle charging and discharging system, and further includes:

[0034] Obtaining a new energy vehicle access curve of the new energy vehicle charging and discharging system in a target period, wherein the new energy vehicle access curve is a curve representing the battery capacity of the new energy vehicle connected to the new energy vehicle charging and discharging system;

[0035] According to the new energy vehicle access curve, the new energy vehicle charging and discharging system is connected to the energy storage system and serves as a part of the energy storage system.

[0036] At present, new energy vehicles have gradually become popular. New energy vehicles parked in new energy vehicle charging and discharging systems can be connected to the energy storage system as part of the energy storage system to improve the dispatching capacity of virtual power plants.

[0037] Optionally, also include:

[0038] According to the new energy vehicle charging and discharging system, a charging demand curve of the new energy vehicles connected to the new energy charging and discharging system within the target time period is obtained, wherein the charging demand is used to characterize the demand for charging power of all the new energy vehicles within the target time period;

[0039] The optimal incentive model is optimized according to the charging demand curve of the new energy vehicle during the target period.

[0040] By adopting the above method, the impact on the normal use of new energy vehicles can be reduced and the rights of new energy vehicle owners can be ensured.

[0041] Optionally, the step of optimizing the optimal incentive model according to the charging demand curve of the new energy vehicle in the target time period includes:

[0042] According to the power supply gap curve, the power generation curve and the power release scheme, a first power release constraint is obtained, wherein the first power release constraint is used to characterize that the sum of the power release electricity and the power generation electricity in any time period within the target time period cannot exceed the power gap in the power supply gap curve in the time period;

[0043] According to the power generation curve and the energy storage scheme, a first energy storage constraint is obtained, wherein the first energy storage constraint is used to indicate that the energy storage quantity in any time period within the target time period cannot exceed the power generation quantity;

[0044] According to the energy storage scheme, the energy release scheme and the charge-discharge loss model, a second energy release constraint is obtained, wherein the second energy release constraint is used to characterize that the energy release amount before any time point in the target time period cannot exceed the energy storage amount and the remaining amount in the new energy vehicle charging and discharging system when the new energy vehicle is connected, which is obtained by calculating the charge-discharge loss model;

[0045] According to the energy storage scheme, the energy release scheme and the energy storage system, a second energy storage constraint is obtained, wherein the second energy storage constraint is used to characterize that the amount of electricity in the energy storage system at any time point within the target time period does not exceed the energy storage upper limit of the energy storage system;

[0046] According to the power generation curve, the energy storage scheme, the energy release scheme and the incentive function, a target incentive constraint is obtained, wherein the target incentive constraint is used to characterize that the incentive obtained by adopting the energy storage scheme and the energy release scheme is maximized;

[0047] Constructing the optimal incentive model according to the first energy release constraint, the first energy storage constraint, the second energy release constraint, the second energy storage constraint and the target incentive constraint;

[0048] According to the charging demand curve, the energy storage scheme and the energy release scheme, a third energy release constraint is obtained, wherein the third energy release constraint is used to indicate that at any time point within the target time period, the difference between the energy storage power and the energy release power is greater than the charging power requirement of the charging demand curve at the time point;

[0049] The optimal excitation model is optimized according to the third energy release constraint.

[0050] In another aspect, a virtual power plant control system based on a neural network, the virtual power plant includes a control platform, a distributed power generation system and an energy storage system;

[0051] The control platform is configured as follows:

[0052] Obtain the power supply gap curve and incentive function of the power grid system during the target period;

[0053] Obtaining, through the distributed power generation system, a power generation curve of the distributed power generation system in a target period;

[0054] Obtaining a charge and discharge loss model through the energy storage system;

[0055] According to the power supply gap curve, the incentive function, the power generation curve and the charge-discharge loss model as constraints, an optimal incentive model is constructed, wherein the optimal incentive model is configured to obtain an energy storage scheme and / or an energy release scheme to obtain an optimal incentive;

[0056] Obtain energy storage and release plans based on the optimal incentive model;

[0057] The distributed generation system is configured as follows:

[0058] Providing the control platform with relevant parameters of the power generation curve in the target period;

[0059] The energy storage system is configured as follows:

[0060] Energy storage and energy release are performed according to the energy storage scheme and the energy release scheme.

[0061] Optionally, the virtual power plant also includes a new energy vehicle charging and discharging system;

[0062] The control platform is also configured to:

[0063] Obtaining a new energy vehicle access curve of the new energy vehicle charging and discharging system in a target period, wherein the new energy vehicle access curve is a curve representing the battery capacity of the new energy vehicle connected to the new energy vehicle charging and discharging system;

[0064] According to the new energy vehicle access curve, the new energy vehicle charging and discharging system is connected to the energy storage system and serves as a part of the energy storage system;

[0065] The new energy vehicle charging and discharging system is configured as follows:

[0066] According to the connected new energy vehicles, generating the new energy vehicle access curve and sending it to the control platform;

[0067] Access to the energy storage system as a part of the energy storage system.

[0068] On the other hand, an embodiment of the present application further provides a device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above method.

[0069] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement the above method.

[0070] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0071] The present invention provides a virtual power plant control method, system and device based on a neural network, including: obtaining the power supply gap curve and incentive function of the power grid system in the target period; obtaining the power generation curve of the distributed power generation system in the target period through the distributed power generation system; obtaining the charge and discharge loss model through the energy storage system; constructing an optimal incentive model based on the power supply gap curve, the incentive function, the power generation curve and the charge and discharge loss model as constraints, wherein the optimal incentive model is configured to obtain an energy storage scheme and / or an energy release scheme to obtain the optimal incentive; obtaining an energy storage scheme and an energy release scheme based on the optimal incentive model. At least the problem of the lack of effective means for controlling virtual power plants in the prior art, the low utilization rate of virtual power plants, and the inability to control energy storage and energy release according to changes in power grid demand to improve the benefits of virtual power plants is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0073] Figure 1 A schematic diagram of the flow of a virtual power plant control method based on a neural network in this application;

[0074] Figure 2 Schematic diagram of equipment for neural network-based virtual power plant control in this application.

[0075] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory.

[0076] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0077] In order to enable those skilled in the art to better understand the solution of the present application, the following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0078] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0079] Example 1

[0080] like Figure 1As shown, a virtual power plant control method based on a neural network is provided, wherein the virtual power plant is connected to a power grid system, and the virtual power plant includes a control platform, a distributed power generation system, and an energy storage system. The method is executed by the control platform and includes the following steps:

[0081] S1. Obtain the power supply gap curve and incentive function of the power grid system during the target period;

[0082] Specifically, the power supply gap curve may be a curve corresponding to the gap power and time, or a curve corresponding to the gap power and time;

[0083] Specifically, the incentive function may be a piecewise function segmented according to time. In a time period with a larger power supply gap, the incentive index is higher. The method for segmenting time may adopt a fixed time segmentation method, such as every 1 hour, every 2 hours, every 1 day, etc., and the incentive index in the segment is determined by calculating the average power supply gap in the segment.

[0084] Optionally, the method for obtaining the power supply gap curve and incentive function of the power grid system in the target period may be that the virtual power plant predicts the power supply gap curve and / or incentive function of the power grid system in the target period based on historical data; or the power supply gap curve and / or incentive function of the power grid system in the target period is obtained directly from the power grid system.

[0085] S2. Obtaining a power generation curve of the distributed power generation system in a target period through the distributed power generation system;

[0086] Specifically, the distributed power generation system may include a wind power generation unit and / or a solar power generation unit;

[0087] Specifically, the power generation curve may be a curve corresponding to the power generation of the distributed power generation system and time, or may be a curve corresponding to the power generation of the distributed power generation system and time;

[0088] Optionally, through the distributed power generation system, the method for obtaining the power generation curve of the distributed power generation system in the target time period may be that the virtual power plant predicts the power generation curve of the distributed power generation system in the target time period based on historical data; or the power generation curve of the distributed power generation system in the target time period is obtained directly from the distributed power generation system.

[0089] S3, obtaining a charging and discharging loss model through the energy storage system;

[0090] Specifically, the charge-discharge loss model is used to characterize the losses of charging and discharging the energy storage system;

[0091] Optionally, the charge and discharge loss model may be a fixed model or a model that is adjusted according to parameter changes of the energy storage system.

[0092] S4. Construct an optimal incentive model based on the power supply gap curve, incentive function, power generation curve and charge and discharge loss model as constraints;

[0093] Specifically, the optimal incentive model is configured to obtain an energy storage scheme and / or an energy release scheme to obtain an optimal incentive;

[0094] Specifically, the principle of constructing the optimal incentive model is to store the generated electricity during the period of low incentive through the energy storage system, and then input the stored electricity into the grid through the energy storage system during the period of high incentive to obtain the optimal incentive.

[0095] S5. Obtain energy storage and release plans based on the optimal incentive model.

[0096] Specifically, the energy storage scheme may be a scheme in which the energy storage power of the energy storage system corresponds to time, or a scheme in which the energy storage quantity of the energy storage system corresponds to time;

[0097] Specifically, the energy release scheme may be a scheme in which the energy storage power of the energy release system corresponds to time, or may be a scheme in which the energy release power of the energy release system corresponds to time.

[0098] Optionally, based on the above solution, a virtual power plant control method based on a neural network is provided, wherein the virtual power plant is connected to a power grid system, and the virtual power plant includes a control platform, a distributed power generation system, and an energy storage system. The method is executed by the control platform and includes the following steps:

[0099] S1. Obtain the power supply gap curve and incentive function of the power grid system during the target period;

[0100] Optionally, the step of obtaining a power supply gap curve and an incentive function of the power grid system in a target period includes:

[0101] Based on the historical power consumption data and historical power consumption characteristic data of the power grid system power supply area, a power consumption prediction model is established to predict the power consumption data based on the power consumption characteristic data;

[0102] The power consumption data of the power supply area of ​​the power grid system is predicted according to the power consumption prediction model to obtain a power consumption data curve;

[0103] According to the historical power generation data and historical power supply characteristic data of the power grid system, a power supply prediction model is established for predicting the power supply data according to the power supply characteristic data;

[0104] Predict the power supply data of the power grid system according to the power supply prediction model to obtain the power supply data curve;

[0105] According to the power consumption data curve and the power supply data curve, a power supply gap curve is obtained;

[0106] An incentive function is obtained according to the power supply gap curve and a preset incentive standard.

[0107] Optionally, the power consumption characteristic data may include weather data, business expansion data, user tag data, and other data that may affect power consumption;

[0108] Optionally, the power supply characteristic data may include weather data, equipment data, and other data that may affect the power supply of power supply equipment that is primarily connected to the power grid in the region.

[0109] S2. Obtaining a power generation curve of the distributed power generation system in a target period through the distributed power generation system;

[0110] Optionally, the step of obtaining, through the distributed power generation system, a power generation curve of the distributed power generation system in a target period includes:

[0111] Establish a GA-LSTM model. The GA-LSTM model is a model that optimizes the parameter weights and biases of the LSTM neural network through a genetic algorithm.

[0112] Obtain a power generation training set and a power generation verification set based on historical power generation data and historical power generation characteristic data;

[0113] The GA-LSTM model is trained based on the power generation training set and the power generation verification set to obtain a power generation prediction model with compound preset conditions;

[0114] Obtaining power generation characteristic data corresponding to a target period through a distributed power generation system;

[0115] According to the power generation prediction model and the power generation characteristic data corresponding to the target period, the power generation curve of the distributed power generation system in the target period is obtained.

[0116] Optionally, the power supply characteristic data may include weather data, equipment data, and other data that may affect wind power generation and / or solar power generation.

[0117] S3. Obtain a charging and discharging loss model through the energy storage system.

[0118] S4. Construct an optimal incentive model based on the power supply gap curve, incentive function, power generation curve and charge and discharge loss model as constraints;

[0119] Optionally, the step of constructing an optimal incentive model based on the power supply gap curve, the incentive function, the power generation curve and the charge and discharge loss model as constraints includes:

[0120] According to the power supply gap curve, the power generation curve and the power release scheme, a first power release constraint is obtained, where the first power release constraint is used to indicate that the sum of the power release quantity and the power generation quantity in any time period within the target time period cannot exceed the power gap quantity in the power supply gap curve in the time period;

[0121] According to the power generation curve and the energy storage scheme, a first energy storage constraint is obtained, where the first energy storage constraint is used to indicate that the energy storage power in any time period within the target time period cannot exceed the power generation power;

[0122] According to the energy storage scheme, the energy release scheme and the charge-discharge loss model, a second energy release constraint is obtained, where the second energy release constraint is used to characterize that the energy release quantity before any time point in the target period cannot exceed the energy storage quantity obtained after calculation by the charge-discharge loss model;

[0123] According to the energy storage scheme, the energy release scheme and the energy storage system, a second energy storage constraint is obtained, where the second energy storage constraint is used to indicate that the amount of electricity in the energy storage system at any time point within the target period does not exceed the energy storage upper limit of the energy storage system;

[0124] According to the power generation curve, energy storage scheme, energy release scheme and incentive function, the target incentive constraint is obtained, and the target incentive constraint is used to characterize the maximum incentive obtained by adopting the energy storage scheme and the energy release scheme;

[0125] An optimal incentive model is constructed according to the first energy release constraint, the first energy storage constraint, the second energy release constraint, the second energy storage constraint and the target incentive constraint.

[0126] Optionally, the first energy release constraint is: for any period within the target period, E 放 +E 发 ≤E 缺 , where E 放 is the energy released by the energy storage system during this period, E 发 is the power generation of the distributed generation system during this period, E 缺 is the power deficit during this period;

[0127] The first energy storage constraint is: for any period within the target period, E 储 ≤E 发 , where E 储 is the energy storage capacity of the energy storage system during this period, E 发 is the amount of electricity generated by the distributed generation system during this period;

[0128] The second energy release constraint is: for the period from the time point at which the target period starts to any time point within the target period, E 放 ≤E 储 *F 储 *F 放 , where E 放is the energy released by the energy storage system during this period, E 储 is the energy storage capacity of the energy storage system during this period, F 储 is the energy storage loss function, F 放 is the energy release loss function;

[0129] The second energy storage constraint is: at any time point within the target period, E 储 *F 储 -E 放 / F 放 ≤E 储max , where E 储max is the upper limit of energy storage system;

[0130] The target incentive constraint is: Q max =[E 发 ]*F 激 -[E 储 ]*F 激 +[E 放 ]*F 激 ;

[0131] Among them, Q max is the maximum incentive value, [E 发 ] is the time series data of power generation, [E 储 ] is the time series data of the power storage scheme, [E 放 ] is the time series data of the discharge plan, F 激 It is an activation function based on time segmentation.

[0132] S5. Obtain energy storage and release plans according to the optimal incentive model;

[0133] Specifically, the above optimal incentive model is solved to obtain the energy storage plan and the energy release plan.

[0134] Example 2

[0135] This embodiment is based on the embodiment 1, and is a virtual power plant control method based on a neural network. The virtual power plant is connected to the power grid system. The virtual power plant includes a control platform, a distributed power generation system and an energy storage system. The method is executed by the control platform and includes the following steps:

[0136] S1. Obtain the power supply gap curve and incentive function of the power grid system during the target period;

[0137] S2. Obtaining a power generation curve of the distributed power generation system in a target period through the distributed power generation system;

[0138] S3, obtaining a charging and discharging loss model through the energy storage system;

[0139] S4. Construct an optimal incentive model based on the power supply gap curve, incentive function, power generation curve and charge and discharge loss model as constraints;

[0140] Specifically, the optimal incentive model is configured to obtain an energy storage scheme and / or an energy release scheme to obtain an optimal incentive;

[0141] S5. Obtain energy storage and release plans according to the optimal incentive model;

[0142] Optionally, the virtual power plant also includes a new energy vehicle charging and discharging system, and also includes:

[0143] Obtaining a new energy vehicle access curve of the new energy vehicle charging and discharging system during a target period, where the new energy vehicle access curve is a curve representing the battery capacity of the new energy vehicle connected to the new energy vehicle charging and discharging system;

[0144] According to the new energy vehicle access curve, the new energy vehicle charging and discharging system is connected to the energy storage system and used as a part of the energy storage system.

[0145] Optionally, also include:

[0146] According to the new energy vehicle charging and discharging system, the charging demand curve of the new energy vehicles connected to the new energy charging and discharging system within the target period is obtained. The charging demand is used to characterize the demand for charging power of all new energy vehicles within the target period;

[0147] According to the charging demand curve of new energy vehicles during the target period, the optimal incentive model is optimized.

[0148] Optionally, when connecting the new energy vehicle to the new energy charging and discharging system, the new energy charging and discharging system can select the departure time and the expected power. The new energy charging and discharging system generates a charging demand curve based on the departure time and the expected power of the new energy vehicle to ensure that the power of the new energy vehicle is not less than the expected power when the new energy vehicle leaves.

[0149] Optionally, the step of optimizing the optimal incentive model according to the charging demand curve of the new energy vehicle in the target period includes:

[0150] According to the power supply gap curve, the power generation curve and the power release scheme, a first power release constraint is obtained, where the first power release constraint is used to indicate that the sum of the power release quantity and the power generation quantity in any time period within the target time period cannot exceed the power gap quantity in the power supply gap curve in the time period;

[0151] According to the power generation curve and the energy storage scheme, a first energy storage constraint is obtained, where the first energy storage constraint is used to indicate that the energy storage power in any time period within the target time period cannot exceed the power generation power;

[0152] According to the energy storage scheme, the energy release scheme and the charge and discharge loss model, a second energy release constraint is obtained, which is used to characterize that the energy release quantity before any time point in the target period cannot exceed the energy storage quantity and the remaining quantity in the new energy vehicle charging and discharging system when the new energy vehicle is connected, which is obtained by calculating the charge and discharge loss model;

[0153] According to the energy storage scheme, the energy discharge scheme and the energy storage system, a second energy storage constraint is obtained, where the second energy storage constraint is used to indicate that the amount of electricity in the energy storage system at any time point within the target period does not exceed the energy storage upper limit of the energy storage system, where the upper limit of the energy storage system includes the battery electricity of the new energy vehicle in the new energy vehicle charging and discharging system;

[0154] According to the power generation curve, energy storage scheme, energy release scheme and incentive function, the target incentive constraint is obtained, and the target incentive constraint is used to characterize the maximum incentive obtained by adopting the energy storage scheme and the energy release scheme;

[0155] An optimal incentive model is constructed according to a first energy release constraint, a first energy storage constraint, a second energy release constraint, a second energy storage constraint and a target incentive constraint;

[0156] According to the charging demand curve, the energy storage scheme and the energy release scheme, a third energy release constraint is obtained, where the third energy release constraint is used to indicate that at any time point in the target period, the difference between the energy storage power and the energy release power is greater than the charging power requirement of the charging demand curve at that time point;

[0157] According to the third energy release constraint, the optimal excitation model is optimized.

[0158] Optionally, the optimized constraints are:

[0159] The first energy release constraint is: for any period within the target period, E 放 +E 发 ≤E 缺 , where E 放 is the energy released by the energy storage system during this period, E 发 is the power generation of the distributed generation system during this period, E 缺 is the power deficit during this period;

[0160] The first energy storage constraint is: for any period within the target period, E 储 ≤E 发 , where E 储 is the energy storage capacity of the energy storage system during this period, E 发 is the amount of electricity generated by the distributed generation system during this period;

[0161] The second energy release constraint is: for the period from the time point at which the target period starts to any time point within the target period, E 放 ≤E 储 *F储 *F 放 +E 初 *F 放 , where E 放 is the energy released by the energy storage system during this period, E 初 It is the remaining power in the new energy vehicle charging and discharging system when the new energy vehicle is connected, E 储 is the energy storage capacity of the energy storage system during this period, F 储 is the energy storage loss function, F 放 is the energy release loss function;

[0162] The second energy storage constraint is: at any time point within the target period, E 储 *F 储 -E 放 / F 放 ≤E 储max +E 车max , where E 储max is the upper limit of energy storage system, E 车max It is the upper limit of the energy storage capacity of the battery of new energy vehicles;

[0163] The third energy release constraint is: for any time point within the target period, E 储 *F 储 -E 放 / F 放 ≥E, where E 末 is the demand for charging power at that point in time from the charging demand curve;

[0164] The target incentive constraint is: Q max =[E 发 ]*F 激 -[E 储 ]*F 激 +[E 放 ]*F 激 ;

[0165] Among them, Q max is the maximum incentive value, [E 发 ] is the time series data of power generation, [E 储 ] is the time series data of the power storage scheme, [E 放 ] is the time series data of the discharge plan, F 激 It is an activation function based on time segmentation.

[0166] Example 3

[0167] A virtual power plant control system based on neural network, which includes a control platform, a distributed power generation system and an energy storage system;

[0168] The control platform is configured as:

[0169] Obtain the power supply gap curve and incentive function of the power grid system during the target period;

[0170] Through the distributed generation system, a power generation curve of the distributed generation system in a target period is obtained;

[0171] Through the energy storage system, a charging and discharging loss model is obtained;

[0172] An optimal incentive model is constructed based on the power supply gap curve, incentive function, power generation curve and charge-discharge loss model as constraints, and the optimal incentive model is configured to obtain energy storage solutions and / or energy release solutions to obtain optimal incentives;

[0173] Obtain energy storage and release plans based on the optimal incentive model;

[0174] The distributed generation system is configured as:

[0175] Provide the control platform with relevant parameters of the power generation curve during the target period;

[0176] The energy storage system is configured as:

[0177] Energy is stored and released according to the energy storage plan and energy release plan.

[0178] Optionally, the virtual power plant also includes a new energy vehicle charging and discharging system;

[0179] The control platform is also configured to:

[0180] Obtaining a new energy vehicle access curve of the new energy vehicle charging and discharging system during a target period, where the new energy vehicle access curve is a curve representing the battery capacity of the new energy vehicle connected to the new energy vehicle charging and discharging system;

[0181] According to the new energy vehicle access curve, the new energy vehicle charging and discharging system is connected to the energy storage system and used as a part of the energy storage system;

[0182] The new energy vehicle charging and discharging system is configured as follows:

[0183] Generate a new energy vehicle access curve based on the connected new energy vehicles and send it to the control platform;

[0184] Connect to the energy storage system as part of the energy storage system.

[0185] Example 4

[0186] This embodiment provides a device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0187] Specifically, Figure 2 As shown, Figure 2The schematic diagram of the device for virtual power plant control based on neural network is an electronic device, which may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage; the processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0188] Those skilled in the art will appreciate that Figure 2 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0189] like Figure 2 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and an application program for implementing a virtual power plant control method based on a neural network.

[0190] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the application program stored in the memory 105 for implementing a virtual power plant control method based on a neural network through the processor 101 to implement the above method.

[0191] Example 5

[0192] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement any of the above methods.

[0193] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0194] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0195] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0196] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0197] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0198] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0199] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A virtual power plant control method based on neural network, characterized in that: The virtual power plant is connected to a power grid system, and the virtual power plant includes a control platform, a distributed power generation system, and an energy storage system. The method is executed by the control platform and includes the following steps: Obtaining a power supply gap curve and an incentive function of the power grid system during a target period; Obtaining, through the distributed power generation system, a power generation curve of the distributed power generation system in a target period; Obtaining a charge and discharge loss model through the energy storage system; According to the power supply gap curve, the incentive function, the power generation curve and the charge-discharge loss model as constraints, an optimal incentive model is constructed, wherein the optimal incentive model is configured to obtain an energy storage scheme and / or an energy release scheme to obtain an optimal incentive; Obtain energy storage and release plans based on the optimal incentive model; The virtual power plant also includes a new energy vehicle charging and discharging system, and further includes: Obtaining a new energy vehicle access curve of the new energy vehicle charging and discharging system in a target period, wherein the new energy vehicle access curve is a curve representing the battery capacity of the new energy vehicle connected to the new energy vehicle charging and discharging system; According to the new energy vehicle access curve, the new energy vehicle charging and discharging system is connected to the energy storage system and serves as a part of the energy storage system; Also includes: According to the new energy vehicle charging and discharging system, a charging demand curve of the new energy vehicles connected to the new energy charging and discharging system within the target time period is obtained, wherein the charging demand is used to characterize the demand for charging power of all the new energy vehicles within the target time period; Optimizing the optimal incentive model according to the charging demand curve of the new energy vehicle during the target period; The step of optimizing the optimal incentive model according to the charging demand curve of the new energy vehicle in the target time period includes: According to the power supply gap curve, the power generation curve and the power release scheme, a first power release constraint is obtained, wherein the first power release constraint is used to characterize that the sum of the power release electricity and the power generation electricity in any time period within the target time period cannot exceed the power gap in the power supply gap curve in the time period; According to the power generation curve and the energy storage scheme, a first energy storage constraint is obtained, wherein the first energy storage constraint is used to indicate that the energy storage quantity in any time period within the target time period cannot exceed the power generation quantity; According to the energy storage scheme, the energy release scheme and the charge-discharge loss model, a second energy release constraint is obtained, wherein the second energy release constraint is used to characterize that the energy release amount before any time point in the target time period cannot exceed the energy storage amount and the remaining amount in the new energy vehicle charging and discharging system when the new energy vehicle is connected, which is obtained by calculating the charge-discharge loss model; According to the energy storage scheme, the energy release scheme and the energy storage system, a second energy storage constraint is obtained, wherein the second energy storage constraint is used to characterize that the amount of electricity in the energy storage system at any time point within the target time period does not exceed the energy storage upper limit of the energy storage system; According to the power generation curve, the energy storage scheme, the energy release scheme and the incentive function, a target incentive constraint is obtained, wherein the target incentive constraint is used to characterize that the incentive obtained by adopting the energy storage scheme and the energy release scheme is maximized; Constructing the optimal incentive model according to the first energy release constraint, the first energy storage constraint, the second energy release constraint, the second energy storage constraint and the target incentive constraint; According to the charging demand curve, the energy storage scheme and the energy release scheme, a third energy release constraint is obtained, wherein the third energy release constraint is used to indicate that at any time point within the target time period, the difference between the energy storage power and the energy release power is greater than the charging power requirement of the charging demand curve at the time point; The optimal excitation model is optimized according to the third energy release constraint.

2. The virtual power plant control method based on neural network according to claim 1 is characterized in that: The step of constructing an optimal incentive model based on the power supply gap curve, the incentive function, the power generation curve and the charge-discharge loss model as constraints includes: According to the power supply gap curve, the power generation curve and the power release scheme, a first power release constraint is obtained, wherein the first power release constraint is used to characterize that the sum of the power release electricity and the power generation electricity in any time period within the target time period cannot exceed the power gap in the power supply gap curve in the time period; According to the power generation curve and the energy storage scheme, a first energy storage constraint is obtained, wherein the first energy storage constraint is used to indicate that the energy storage quantity in any time period within the target time period cannot exceed the power generation quantity; According to the energy storage scheme, the energy release scheme and the charge-discharge loss model, a second energy release constraint is obtained, wherein the second energy release constraint is used to characterize that the energy release quantity before any time point in the target time period cannot exceed the energy storage quantity obtained after calculation by the charge-discharge loss model; According to the energy storage scheme, the energy release scheme and the energy storage system, a second energy storage constraint is obtained, wherein the second energy storage constraint is used to characterize that the amount of electricity in the energy storage system at any time point within the target time period does not exceed the energy storage upper limit of the energy storage system; According to the power generation curve, the energy storage scheme, the energy release scheme and the incentive function, a target incentive constraint is obtained, wherein the target incentive constraint is used to characterize that the incentive obtained by adopting the energy storage scheme and the energy release scheme is maximized; The optimal incentive model is constructed according to the first energy release constraint, the first energy storage constraint, the second energy release constraint, the second energy storage constraint and the target incentive constraint.

3. The virtual power plant control method based on neural network according to claim 1 is characterized in that: The step of obtaining the power supply gap curve and incentive function of the power grid system in the target period includes: Based on the historical power consumption data and historical power consumption characteristic data of the power grid system power supply area, a power consumption prediction model is established to predict the power consumption data based on the power consumption characteristic data; Predicting the power consumption data of the power supply area of ​​the power grid system according to the power consumption prediction model to obtain a power consumption data curve; According to the historical power generation data and historical power supply characteristic data of the power grid system, a power supply prediction model is established for predicting the power supply data according to the power supply characteristic data; Predicting the power supply data of the power grid system according to the power supply prediction model to obtain a power supply data curve; Obtaining the power supply gap curve according to the power consumption data curve and the power supply data curve; The incentive function is obtained according to the power supply gap curve and a preset incentive standard.

4. The virtual power plant control method based on neural network according to claim 1 is characterized in that: The step of obtaining, through the distributed power generation system, a power generation curve of the distributed power generation system in a target period includes: Establishing a GA-LSTM model, wherein the GA-LSTM model is a model for optimizing LSTM neural network parameter weights and biases through a genetic algorithm; Obtain a power generation training set and a power generation verification set based on historical power generation data and historical power generation characteristic data; The GA-LSTM model is trained according to the power generation training set and the power generation verification set to obtain a power generation prediction model with compound preset conditions; Obtaining power generation characteristic data corresponding to a target period through the distributed power generation system; According to the power generation prediction model and the power generation characteristic data corresponding to the target time period, a power generation curve of the distributed power generation system in the target time period is obtained.

5. The virtual power plant control system based on neural network is characterized by: The virtual power plant includes a control platform, a distributed power generation system and an energy storage system; The control platform is configured as follows: Obtain the power supply gap curve and incentive function of the power grid system during the target period; Obtaining, through the distributed power generation system, a power generation curve of the distributed power generation system in a target period; Obtaining a charge and discharge loss model through the energy storage system; According to the power supply gap curve, the incentive function, the power generation curve and the charge-discharge loss model as constraints, an optimal incentive model is constructed, wherein the optimal incentive model is configured to obtain an energy storage scheme and / or an energy release scheme to obtain an optimal incentive; Obtain energy storage and release plans based on the optimal incentive model; The distributed generation system is configured as follows: Providing the control platform with relevant parameters of the power generation curve in the target period; The energy storage system is configured as follows: Storing and releasing energy according to the energy storage scheme and the energy release scheme; The virtual power plant also includes a new energy vehicle charging and discharging system; The control platform is also configured to: Obtaining a new energy vehicle access curve of the new energy vehicle charging and discharging system in a target period, wherein the new energy vehicle access curve is a curve representing the battery capacity of the new energy vehicle connected to the new energy vehicle charging and discharging system; According to the new energy vehicle access curve, the new energy vehicle charging and discharging system is connected to the energy storage system and serves as a part of the energy storage system; The new energy vehicle charging and discharging system is configured as follows: According to the connected new energy vehicles, generating the new energy vehicle access curve and sending it to the control platform; accessing the energy storage system as a part of the energy storage system; Also includes: According to the new energy vehicle charging and discharging system, a charging demand curve of the new energy vehicles connected to the new energy charging and discharging system within the target time period is obtained, wherein the charging demand is used to characterize the demand for charging power of all the new energy vehicles within the target time period; Optimizing the optimal incentive model according to the charging demand curve of the new energy vehicle during the target period; The step of optimizing the optimal incentive model according to the charging demand curve of the new energy vehicle in the target time period includes: According to the power supply gap curve, the power generation curve and the power release scheme, a first power release constraint is obtained, wherein the first power release constraint is used to characterize that the sum of the power release electricity and the power generation electricity in any time period within the target time period cannot exceed the power gap in the power supply gap curve in the time period; According to the power generation curve and the energy storage scheme, a first energy storage constraint is obtained, wherein the first energy storage constraint is used to indicate that the energy storage quantity in any time period within the target time period cannot exceed the power generation quantity; According to the energy storage scheme, the energy release scheme and the charge-discharge loss model, a second energy release constraint is obtained, wherein the second energy release constraint is used to characterize that the energy release amount before any time point in the target time period cannot exceed the energy storage amount and the remaining amount in the new energy vehicle charging and discharging system when the new energy vehicle is connected, which is obtained by calculating the charge-discharge loss model; According to the energy storage scheme, the energy release scheme and the energy storage system, a second energy storage constraint is obtained, wherein the second energy storage constraint is used to characterize that the amount of electricity in the energy storage system at any time point within the target time period does not exceed the energy storage upper limit of the energy storage system; According to the power generation curve, the energy storage scheme, the energy release scheme and the incentive function, a target incentive constraint is obtained, wherein the target incentive constraint is used to characterize that the incentive obtained by adopting the energy storage scheme and the energy release scheme is maximized; Constructing the optimal incentive model according to the first energy release constraint, the first energy storage constraint, the second energy release constraint, the second energy storage constraint and the target incentive constraint; According to the charging demand curve, the energy storage scheme and the energy release scheme, a third energy release constraint is obtained, wherein the third energy release constraint is used to indicate that at any time point within the target time period, the difference between the energy storage power and the energy release power is greater than the charging power requirement of the charging demand curve at the time point; The optimal excitation model is optimized according to the third energy release constraint.

6. A device, characterized in that: The device comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method according to any one of claims 1 to 4.

Images