Virtual power plant operation control method and system

Abstract

The invention discloses a virtual power plant operation control method, which comprises the steps of S1, acquiring historical power consumption data of a power user of a virtual power plant, and establishing a power consumption prediction model; s2, acquiring historical power generation data of each energy station of the virtual power plant, and respectively establishing a power generation prediction model; s3, using the electricity consumption prediction model to construct an electricity consumption curve in a predetermined time period; and S4, dividing the power utilization curve into a plurality of time intervals, and matching the energy station for each time interval. The invention also provides a virtual power plant operation control system. According to the invention, accurate matching between the power consumption of the power user and the energy station can be realized, energy scheduling is optimized, and energy waste is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field related to virtual power plants, and more specifically, to a virtual power plant operation control method and system. Background Art

[0002] Virtual power plants integrate decentralized energy stations, energy storage equipment, controllable loads and other resources through information and Internet technologies, optimize control, and participate in power grid dispatching, thereby reducing the electricity cost of the entire society and improving energy efficiency. At present, it is difficult for virtual power plants to match the changes in electricity consumption of electricity users, and there is a problem of energy waste. Therefore, it is necessary to design a technical solution that can overcome the above defects. Summary of the invention

[0003] One object of the present invention is to provide a virtual power plant operation control method and system, which can achieve accurate matching of electricity consumption of electricity users and energy stations, optimize energy scheduling, and reduce energy waste.

[0004] In order to achieve these objectives and other advantages of the present invention, according to one aspect of the present invention, the present invention provides a virtual power plant operation control method, including: S1: obtaining historical electricity consumption data of electricity users of the virtual power plant, and establishing an electricity consumption prediction model; S2: obtaining historical power generation data of each energy station of the virtual power plant, and establishing power generation prediction models respectively; S3: using the power consumption prediction model to construct an electricity consumption curve for a predetermined time period; S4: dividing the electricity consumption curve into multiple time intervals, and matching the energy station for each of the time intervals respectively.

[0005] Furthermore, in S4, for each of the time intervals, the energy stations are combined in multiple ways according to the power generation prediction model of each of the energy stations, and a combination matching the power consumption curve is selected to achieve matching of energy stations for each of the time intervals.

[0006] Furthermore, it also includes matching controllable loads and energy storage devices for each of the time intervals.

[0007] Furthermore, taking the matching of the combination of each of the energy stations, controllable loads, and energy storage equipment with the power consumption curve within the time interval as the objective function, constraint conditions are established according to the power generation prediction model of each of the energy stations, the power consumption of the controllable loads, and the capacity of the energy storage equipment, and the improved ant colony algorithm is used to solve the optimal combination of each of the energy stations, controllable loads, and energy storage equipment.

[0008] Furthermore, in S1, historical electricity consumption data and historical environmental data of electricity users of the virtual power plant are obtained, and a training set is established, with the electricity consumption data and environmental data of the previous time periods as input and the electricity consumption data of the next time period as output, to train a long short-term memory network and obtain the electricity consumption prediction model.

[0009] Furthermore, the environmental data includes at least maximum temperature, minimum temperature, humidity, wind speed, and sunshine.

[0010] According to another aspect of the present invention, a virtual power plant operation control system is also provided, including: a first construction module, used to obtain historical electricity consumption data of electricity users of the virtual power plant and establish an electricity consumption prediction model; a second construction module, used to obtain historical power generation data of each energy station of the virtual power plant, and establish power generation prediction models respectively; a third construction module, used to use the power consumption prediction model to construct an electricity consumption curve for a predetermined time period; a matching module, used to divide the electricity consumption curve into multiple time intervals, and match the energy station for each of the time intervals respectively.

[0011] Furthermore, the matching module takes the matching of the combination of each of the energy stations, controllable loads, and energy storage equipment with the power consumption curve within the time interval as the objective function, establishes constraints based on the power generation prediction model of each of the energy stations, the power consumption of the controllable loads, and the capacity of the energy storage equipment, and uses the improved ant colony algorithm to solve and obtain the optimal combination of each of the energy stations, controllable loads, and energy storage equipment.

[0012] Furthermore, the first construction module obtains historical electricity consumption data and historical environmental data of the electricity users of the virtual power plant, establishes a training set, takes the electricity consumption data and environmental data of the previous time periods as input, and takes the electricity consumption data of the next time period as output, trains a long short-term memory network, and obtains the electricity consumption prediction model; the environmental data includes at least maximum temperature, minimum temperature, humidity, wind speed, and sunshine.

[0013] The present invention has at least the following beneficial effects: The present invention establishes an electricity consumption prediction model based on the historical electricity consumption data of electricity users, and establishes power generation prediction models based on the historical power generation data of each energy station. The electricity consumption prediction model is used to construct an electricity consumption curve for a predetermined time period, and the electricity consumption curve is divided into multiple time intervals. The energy station is dynamically matched for each time interval, thereby achieving accurate matching of electricity consumption of electricity users and energy stations, optimizing energy scheduling, and reducing energy waste.

[0014] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of an embodiment of the present application. DETAILED DESCRIPTION

[0016] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0017] It should be understood that the terms such as "having", "including" and "comprising" used in the embodiments of the present application do not exclude the existence or addition of one or more other elements or their combinations. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative position relationship, movement, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly. When an element is referred to as "fixed on" or "set on" another element, it can be directly on the other element or there may be a centering element at the same time. When an element is referred to as "connecting" another element, it can be directly connected to another element or it can be indirectly connected to another element through a centering element. The description of "first", "second", etc. in the embodiments of the present application is only for descriptive purposes, and cannot be understood as indicating or implying its relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features.

[0018] It should be noted that the technical solutions between the various embodiments of the present application can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0019] like Figure 1 As shown, an embodiment of the present application provides a virtual power plant operation control method, including: S1: Obtain historical electricity consumption data of users of virtual power plants and establish an electricity consumption prediction model; Exemplarily, electricity users include enterprise users and residential users; Exemplarily, electricity consumption data is obtained through smart meters installed at various locations; Exemplarily, a power consumption prediction model is established using regression models, machine learning and other methods and historical power consumption data; S2: Obtain historical power generation data of each energy station of the virtual power plant and establish power generation prediction models respectively; Exemplarily, energy stations include thermal power stations, photovoltaic power stations, wind power stations, hydropower stations, etc.; Exemplarily, a power generation prediction model is established by using regression models, machine learning and other methods, historical power generation data, weather data, and actual power generation capacity; for example, a power generation prediction model for a thermal power station is established based on thermal power generating units, and a power generation prediction model for a wind power station and a photovoltaic power station is established by using weather data and historical power generation data; S3: constructing a power consumption curve for a predetermined time period using the power consumption prediction model; This step uses the power consumption prediction model to predict the power consumption at multiple time points within a predetermined time period, and constructs a power consumption curve. The predetermined time period is relatively long, which can be one month, one quarter or half a year. The predetermined time period is the time period in which energy scheduling is required; S4: dividing the power consumption curve into multiple time intervals, and matching the energy station to each time interval; In this step, the scheduled time period is divided into multiple small segments, each of which is a time interval. Each time interval is 5 days, 7 days or 10 days. The energy station combination is adjusted in each time period to make full use of the power generation and power generation trend of each energy station and improve the utilization efficiency. The matching in this step means that the power generation curve of the matched energy station combination is close to the power consumption curve of each time interval. Of course, it does not mean complete overlap, but a certain error is allowed. The specific error can be determined according to the actual energy scheduling needs. It can be seen that this embodiment establishes an electricity consumption prediction model based on the historical electricity consumption data of electricity users, and establishes power generation prediction models based on the historical power generation data of each energy station. The electricity consumption prediction model is used to construct an electricity consumption curve for a predetermined time period, and the electricity consumption curve is divided into multiple time intervals. Energy stations are dynamically matched for each time interval, thereby achieving accurate matching between electricity consumption of electricity users and energy stations, optimizing energy scheduling, realizing on-demand power supply, and reducing energy waste.

[0020] In another embodiment, in S4, for each of the time intervals, according to the power generation prediction model of each of the energy stations, multiple combinations of the energy stations are performed, and a combination matching the power consumption curve is selected to achieve matching of energy stations for each of the time intervals; This embodiment utilizes the differences in power generation time and power generation peak of different energy stations to combine the energy stations so that the combined power generation of the energy stations matches the power consumption given on the power consumption curve, thereby realizing on-demand power supply and reducing energy waste.

[0021] In another embodiment, it also includes matching a controllable load and an energy storage device for each of the time intervals; the load of the controllable load is adjustable, and the energy storage device can store energy and store excess electricity. Matching the controllable load and the energy storage device can ensure the stability of the power grid and further reduce energy waste.

[0022] In another embodiment, the objective function is to match the combination of each of the energy stations, controllable loads, and energy storage devices with the power consumption curve within the time interval, and to establish constraints based on the power generation prediction model of each of the energy stations, the power consumption of the controllable loads, and the capacity of the energy storage device. The improved ant colony algorithm is used to solve the problem and obtain the optimal combination of each of the energy stations, controllable loads, and energy storage devices. This embodiment uses an improved ant colony algorithm to combine energy stations, controllable loads, and energy storage devices. The objective function is to minimize the error between the power generation curve of the combination of each energy station, controllable load, and energy storage device and the power consumption curve within the time interval. The predicted power generation model of each energy station, the power consumption of the controllable load, the capacity of the energy storage device, and the power consumption curve within the time interval are used as constraints. The allocation process of multiple energy stations, multiple controllable loads, and multiple energy storage devices is simulated as an ant colony network. L is defined as the number of iterations, L max is the maximum number of cycles, k is the number of ants, which can be selected as the total number of energy stations, controllable loads and energy storage devices, the pheromone inspiration factor is α, the expected inspiration factor is β, and the information volatility coefficient is ρ. Each ant selects a combination of energy stations, controllable loads and energy storage devices. The ants do not disturb each other. They select the next hop node according to the selection rule and use the pheromone update rule to update the pheromone. After the maximum number of cycles is reached, the cycle is terminated, and finally the optimal combination of energy stations, controllable loads and energy storage devices is obtained. The optimal combination is used to supply power and store energy to the electricity users in the time interval. Pheromone update rules: ; Ant selection rules: ; in, represents the pheromone concentration of path i to j at time t, represents the pheromone increment left by the ant on the path from i to j, represents the probability from i to j, is the heuristic function.

[0023] In another embodiment, in S1, historical power consumption data and historical environmental data of power users of the virtual power plant are obtained, and a training set is established, so that the power consumption data and environmental data of the previous time periods are used as input, and the power consumption data of the next time period is used as output, and a long short-term memory network is trained to obtain the power consumption prediction model; This embodiment proposes a preferred method for constructing a power consumption prediction model, namely, using a long short-term memory network, which is suitable for processing and predicting important events with very long intervals and delays in time series, and is more suitable for constructing a power consumption prediction model; organizing the collected historical power consumption data and historical environmental data into multiple time periods, using the power consumption data and environmental data of the first few time periods as input, and the power consumption data of the last time period as output. After experiments, the first three time periods are selected for training to obtain a power consumption prediction model with higher prediction accuracy; this embodiment also takes into account the impact of environmental factors on power consumption, and adds them to the power consumption prediction model, further improving the prediction accuracy. The environmental data at least includes the maximum temperature, the minimum temperature, humidity, wind speed, and sunshine, and the sunshine includes sunshine intensity and sunshine duration.

[0024] An embodiment of the present application also provides a virtual power plant operation control system, including: a first construction module, used to obtain historical electricity consumption data of electricity users of the virtual power plant and establish an electricity consumption prediction model; a second construction module, used to obtain historical power generation data of each energy station of the virtual power plant, and establish power generation prediction models respectively; a third construction module, used to use the power consumption prediction model to construct an electricity consumption curve for a predetermined time period; a matching module, used to divide the electricity consumption curve into multiple time intervals, and match the energy station for each of the time intervals respectively.

[0025] This embodiment uses a computer program to construct a first construction module, a second construction module, a third construction module and a matching module. The first construction module collects historical electricity consumption data of electricity users to establish an electricity consumption prediction model. The second construction module collects historical power generation data of each energy station and establishes a power generation prediction model respectively. The third construction module uses the power consumption prediction model to construct an electricity consumption curve for a predetermined time period. The matching module divides the electricity consumption curve into multiple time intervals and dynamically matches energy stations for each time interval, thereby achieving accurate matching between electricity consumption of electricity users and energy stations, optimizing energy scheduling, realizing on-demand power supply, and reducing energy waste.

[0026] In another embodiment, the matching module takes the matching of the combination of each of the energy stations, controllable loads, and energy storage devices with the power consumption curve within the time interval as the objective function, establishes constraint conditions according to the power generation prediction model of each of the energy stations, the power consumption of the controllable loads, and the capacity of the energy storage device, and uses the improved ant colony algorithm to solve and obtain the optimal combination of each of the energy stations, controllable loads, and energy storage devices; This embodiment uses an improved ant colony algorithm to combine energy stations, controllable loads, and energy storage equipment, establishes an objective function, takes the power generation capacity of the energy station, the power consumption of the controllable load, and the capacity of the energy storage equipment as constraints, and initializes the relevant parameters of the improved ant colony algorithm, including the number of ants, pheromone volatilization factor, pheromone constant coefficient, and maximum number of iterations, etc. Each ant selects a combination of energy stations, controllable loads, and energy storage equipment, performs optimization operations, and finally obtains the optimal combination of energy stations, controllable loads, and energy storage equipment, and uses the optimal combination to supply power and store energy to electricity users in the time interval.

[0027] In another embodiment, the first construction module obtains historical power consumption data and historical environmental data of the power users of the virtual power plant, establishes a training set, takes the power consumption data and environmental data of the previous time periods as input, takes the power consumption data of the next time period as output, trains the long short-term memory network, and obtains the power consumption prediction model; the environmental data at least includes the maximum temperature, the minimum temperature, humidity, wind speed, and sunshine; This embodiment proposes a preferred method for constructing a power consumption prediction model, namely, using a long short-term memory network, which is suitable for processing and predicting important events with very long intervals and delays in time series, and is more suitable for constructing a power consumption prediction model; the collected historical power consumption data and historical environmental data are sorted into multiple time periods, with the power consumption data of the first few time periods as input and the power consumption data of the last time period as output. After experiments, the first three time periods are selected for training to obtain a power consumption prediction model with higher prediction accuracy; this embodiment also takes into account the impact of environmental factors on power consumption, and adds them to the power consumption prediction model, further improving the prediction accuracy.

[0028] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A virtual power plant operation control method, characterized in that: include: S1: Obtain historical electricity consumption data of users of virtual power plants and establish an electricity consumption prediction model; S2: Obtain historical power generation data of each energy station of the virtual power plant and establish power generation prediction models respectively; S3: constructing a power consumption curve for a predetermined time period using the power consumption prediction model; S4: Divide the power consumption curve into multiple time intervals, and match the energy station for each time interval respectively.

2. The virtual power plant operation control method according to claim 1, characterized in that: In S4, for each of the time intervals, the energy stations are combined in multiple ways according to the power generation prediction model of each of the energy stations, and a combination matching the power consumption curve is selected to achieve matching of energy stations for each of the time intervals.

3. The virtual power plant operation control method according to claim 2, characterized in that: It also includes matching controllable loads and energy storage devices for each of the time intervals.

4. The virtual power plant operation control method according to claim 3, characterized in that: Taking the matching of the combination of each of the energy stations, controllable loads, and energy storage equipment with the power consumption curve within the time interval as the objective function, constraint conditions are established according to the power generation prediction model of each energy station, the power consumption of the controllable load, and the capacity of the energy storage equipment, and the improved ant colony algorithm is used to solve the problem to obtain the optimal combination of each of the energy stations, controllable loads, and energy storage equipment.

5. The virtual power plant operation control method according to claim 1, characterized in that: In S1, the historical electricity consumption data and historical environmental data of the electricity users of the virtual power plant are obtained, and a training set is established, with the electricity consumption data and environmental data of the previous time periods as input and the electricity consumption data of the next time period as output, to train a long short-term memory network and obtain the electricity consumption prediction model.

6. The virtual power plant operation control method according to claim 5, characterized in that: The environmental data at least includes maximum temperature, minimum temperature, humidity, wind speed, and sunshine.

7. Virtual power plant operation control system, characterized in that: include: The first building module is used to obtain the historical electricity consumption data of the electricity users of the virtual power plant and establish an electricity consumption prediction model; The second construction module is used to obtain the historical power generation data of each energy station of the virtual power plant and establish a power generation prediction model respectively; A third construction module is used to construct a power consumption curve for a predetermined time period using the power consumption prediction model; The matching module is used to divide the power consumption curve into multiple time intervals and match the energy station for each time interval respectively.

8. The virtual power plant operation control system according to claim 7, characterized in that: The matching module takes the matching of the combination of each of the energy stations, controllable loads, and energy storage equipment with the power consumption curve within the time interval as the objective function, establishes constraint conditions based on the power generation prediction model of each of the energy stations, the power consumption of the controllable loads, and the capacity of the energy storage equipment, and uses the improved ant colony algorithm to solve and obtain the optimal combination of each of the energy stations, controllable loads, and energy storage equipment.

9. The virtual power plant operation control system according to claim 7, characterized in that: The first construction module obtains the historical electricity consumption data and historical environmental data of the electricity users of the virtual power plant, establishes a training set, takes the electricity consumption data and environmental data of the previous time periods as input, and takes the electricity consumption data of the next time period as output, trains the long short-term memory network, and obtains the electricity consumption prediction model; the environmental data includes at least the maximum temperature, the minimum temperature, humidity, wind speed, and sunshine.

Images