Virtual power plant optimization scheduling method and device combined with electric vehicle, and storage medium

By building prediction and control modules in virtual power plants and combining with the scheduling of electric vehicle batteries, the lack of integrity of wind and light generation fluctuation regulation needs is solved, and effective response to wind and light generation uncertainty and grid stability are achieved.

CN119093449APending Publication Date: 2024-12-06SHANDONG LUNENG SOFTWARE TECH
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411236517.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing virtual power plant scheduling model is difficult to fully meet the regulation needs of wind and light power generation fluctuations, and lacks integrity and comprehensiveness, resulting in imbalance in supply and demand of the power grid and instability in frequency.

Method used

Using the virtual power plant optimization scheduling method of combined electric vehicles, by building prediction modules and control modules, based on wind and light power generation equipment, load demand and electric vehicle clusters, a wind and light power generation prediction model, load demand forecast model and charging prediction model are established, combined with envelope constraints and historical data, dispatch electric vehicle batteries for energy storage or release, and adjust charging information to cope with uncertainty in wind and light power generation.

Benefits of technology

It improves the adaptability of virtual power plants to wind and light power generation uncertainty, enhances the integrity and comprehensiveness of scheduling, can quickly respond to changes in power grid demand, meets the regulation needs of wind and light power generation fluctuations, and ensures the stable operation of the power grid.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119093449A_ABST
    Figure CN119093449A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of power system optimization scheduling, in particular to a virtual power plant optimization scheduling method combined with an electric vehicle. Comprising the following steps: S1, constructing a virtual power plant based on wind-solar power generation equipment, load requirements and an electric vehicle cluster; s2, establishing a wind-solar power generation prediction model, establishing a load demand prediction model, and establishing a charging prediction model; s3, predicting the uncertain range of wind and light power generation based on envelope constraint combination; s4, acquiring a wind-solar power generation uncertain range at the current moment, and judging whether the predicted load demand data at the current moment falls into the wind-solar power generation uncertain range or not; if not, transferring the battery of the electric vehicle to store energy or release energy; if yes, the charging information of the electric vehicle is adjusted according to the predicted charging data and a preset threshold value. The battery of the moving vehicle can be regarded as a mobile energy storage device, and can quickly respond to the demand change of the power grid, thereby improving the adaptability of the virtual power plant to the uncertainty of wind and light power generation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization and dispatching, and in particular to a virtual power plant optimization and dispatching method, device and storage medium combined with electric vehicles. Background Art

[0002] In the context of today's energy transformation, the world is increasingly dependent on renewable energy. With the continuous advancement of wind power and photovoltaic power generation technology and the gradual reduction of costs, the proportion of wind and solar energy in the power system continues to rise. However, wind and solar energy are naturally intermittent and uncertain, which poses a huge challenge to the stable operation of the power system.

[0003] On the one hand, the output power of wind power generation is affected by many factors such as wind speed, wind direction, and air density, and is highly random. Changes in wind speed are difficult to predict accurately, and even in the same area, wind speeds may vary greatly at different times. Photovoltaic power generation is highly dependent on light intensity and weather conditions. The movement of clouds, alternation of day and night, and seasonal changes will significantly affect its power generation. This uncertainty makes it difficult for traditional power dispatching models to adapt, and may lead to problems such as imbalance between supply and demand in the power grid, voltage fluctuations, and unstable frequency.

[0004] On the other hand, in order to alleviate the impact of the uncertainty of wind and solar energy, the importance of energy storage technology in the power system has become increasingly prominent. Various energy storage devices, such as battery energy storage and pumped storage, can store energy when there is excess wind and solar power generation, and release energy when there is insufficient power generation, thereby balancing the supply and demand of the power grid. However, the capacity of energy storage equipment is limited, the cost is high, and its charging and discharging efficiency is also affected by many factors. Therefore, how to effectively dispatch wind, light, and energy storage resources to achieve stable operation of the power system and maximize economic benefits has become an important issue in the current power field.

[0005] At present, most of the existing virtual power plant-related dispatching models focus on the prediction and dispatching of wind, solar, and energy storage resources, mainly because of the importance and complexity of these three in the power system. The investment cost of energy storage equipment is high, which limits the scale of energy storage capacity in virtual power plants. In practical applications, it may not be able to fully meet the regulation needs of wind and solar power generation fluctuations, lacking a certain degree of completeness and comprehensiveness. Summary of the invention

[0006] In order to solve the problem that the regulation demand of wind and solar power generation fluctuations cannot be fully met and a certain degree of completeness and comprehensiveness is lacking, the present invention provides a virtual power plant optimization scheduling method combined with electric vehicles.

[0007] In a first aspect, the present invention provides a virtual power plant optimization scheduling method for electric vehicles, which adopts the following technical solutions: A virtual power plant optimization scheduling method for electric vehicles includes the following steps: S1, build a virtual power plant based on wind and solar power generation equipment, load demand and electric vehicle clusters, and obtain historical wind and solar power generation data, historical grid load data, electric vehicle historical charging data and electric vehicle capacity data. The virtual power plant includes a prediction module and a control module; S2, in the prediction module of the virtual power plant, Establish a wind and solar power generation prediction model, with historical wind and solar power generation data as input and predicted wind and solar power generation data as output; Establish a load demand forecasting model, with historical grid load data as input and predicted grid load data as output; Establish a charging prediction model, with the electric vehicle historical charging data as input and the predicted charging data as output; S3, in the prediction module of the virtual power plant, the uncertainty range of wind and solar power generation is predicted based on the envelope constraint and the historical wind and solar power generation data and the predicted wind and solar power generation data; S4, in the control module of the virtual power plant, the uncertainty range of wind and solar power generation at the current moment is obtained, and it is determined whether the predicted load demand data at the current moment falls within the uncertainty range of wind and solar power generation. The virtual power plant makes corresponding decisions based on the determination result; When it is determined that it does not fall into the category, the virtual power plant mobilizes electric vehicle batteries to store or release energy; When it is determined to fall into the limit, the virtual power plant adjusts the charging information of the electric vehicle based on the predicted charging data and the preset threshold.

[0008] Optionally, the historical wind and solar power generation data include wind power generation data, photovoltaic power generation data and meteorological data at different times; the historical power grid load data include power grid load data at different times, and all power grid load data are divided into peak period load, stable period load and valley period load; the charging data include charging demand, charging power data and charging time data; the electric vehicle capacity data include battery capacity of different electric vehicles and available battery capacity at different times.

[0009] Optionally, in step S3, the predicted uncertainty range of wind and solar power generation includes: ; = + ; [ *(1- ), *(1+ )]; Where: is the uncertainty interval; is the wind and solar power generation data in period t, is the predicted wind and solar power generation data for period t; is the photovoltaic power generation data in period t; is the wind power generation data in period t; It is the uncertainty range of the scenery predicted at the next moment.

[0010] Optionally, in step S4, when it is determined that the condition does not fall into the range, the virtual power plant mobilizes the electric vehicle battery to store or release energy, specifically including: When it is determined that the predicted load data is greater than the upper limit of the wind and solar uncertainty range and there is no charging demand, the virtual power plant discharges the battery whose available capacity is less than the discharge threshold; When it is determined that the predicted load data is less than the upper limit of the wind and solar uncertainty range, the virtual power plant charges the batteries whose available capacity is greater than the energy storage threshold.

[0011] Optionally, when it is determined that the predicted load data is greater than the upper limit of the wind and solar uncertainty range and there is a demand for charging, the virtual power plant changes the charging time of the electric vehicle to the time when the load is in the off-peak period.

[0012] Optionally, the preset threshold includes a first threshold and a second threshold, the first threshold is close to the lower limit of the wind-solar uncertainty range, and the second threshold is close to the upper limit of the wind-solar uncertainty range; in step S4, when it is determined to fall into, the virtual power plant adjusts the charging information of the electric vehicle according to the predicted charging data and the preset threshold, specifically including: When it is determined that the grid load data is between the lower limit of the wind and solar uncertainty range and the first threshold, the virtual power plant increases the charging power of the electric vehicle to reduce the charging time; When it is determined that the grid load data is between the second threshold and the upper limit of the wind and solar uncertainty range, the virtual power plant reduces the charging power of the electric vehicle and / or disperses the charging time.

[0013] Optionally, the prediction model training in step S2 includes: Build training and validation sets based on historical data; Train the model based on the training set to complete the initial training of the model; The model is verified based on the validation set, with the input being the historical data at a certain moment and the output being the predicted data at the next moment; The mean square error loss function is used to calculate the loss value between the predicted data at the next moment and the historical data at the next moment of the historical data at one moment. When the loss value is judged to be greater than the preset threshold, the model parameters are adjusted. When the loss value is judged to be less than the preset threshold, the prediction model is obtained.

[0014] Optionally, the prediction models all adopt an autoregressive moving average model; before model training, it is necessary to: Determine the model order: based on the autocorrelation function and partial autocorrelation function of the time series; Determine model parameters: Use the least squares method to estimate the parameters of the model and determine the value of the parameter by minimizing the sum of squared errors between the actual data and the data predicted by the model.

[0015] In a second aspect, a virtual power plant optimization scheduling device for electric vehicles is provided, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the memory is coupled to the processor, and the processor implements any of the above-mentioned methods for optimizing the scheduling of virtual power plants for electric vehicles when executing the computer program.

[0016] In a third aspect, a computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any of the above-mentioned methods for optimizing the scheduling of a virtual power plant for electric vehicles.

[0017] In summary, the present invention has the following beneficial technical effects: The batteries of electric vehicles can be regarded as mobile energy storage devices, which have higher flexibility than fixed energy storage facilities. They can be connected to the power grid at different locations to provide energy storage services for the grid. At the same time, the batteries of electric vehicles have a fast response speed and can be charged and discharged in a short time. This enables them to quickly respond to changes in grid demand, improve the adaptability of virtual power plants to the uncertainty of wind and solar power generation, better meet the regulation needs of wind and solar power generation fluctuations, and make the scheduling in virtual power plants complete and comprehensive. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of constructing a virtual power plant according to an embodiment of the present invention.

[0019] Figure 2 It is a flow chart of a method for optimizing scheduling of a virtual power plant in conjunction with electric vehicles according to an embodiment of the present invention.

[0020] Figure 3 yes Figure 2 Detailed process diagram. DETAILED DESCRIPTION

[0021] The following is combined with Figure 1 -Attached Figure 3 The present invention is described in further detail.

[0022] Example 1 Reference Figure 1, a virtual power plant is a power coordination management system that uses advanced information and communication technologies and software systems to achieve aggregation and coordinated optimization of DERs such as DG, energy storage systems, controllable loads, and electric vehicles, so as to participate in the power market and power grid operation as a special power plant. The core of the concept of virtual power plants can be summarized as "communication" and "aggregation". The key technologies of virtual power plants mainly include coordinated control technology, smart metering technology, and information and communication technology. The most attractive function of virtual power plants is that they can aggregate DERs to participate in the operation of the power market and ancillary service market, and provide management and ancillary services for distribution and transmission networks.

[0023] Reference Figure 2 and Figure 3 , a virtual power plant optimization scheduling method for electric vehicles in this embodiment includes the following steps: S1, based on wind and solar power generation equipment, load demand and electric vehicle cluster construction Figure 1 The virtual power plant shown in the figure obtains historical wind and solar power generation data, historical grid load data, historical electric vehicle charging data and electric vehicle capacity data. The virtual power plant includes a prediction module and a control module. Historical wind and solar power generation data include wind power generation data, photovoltaic power generation data and meteorological data at different times; historical grid load data include grid load data at different times, load during peak hours and load during off-peak hours; charging data include charging demand, charging power data and charging time data; electric vehicle capacity data include battery capacity of different electric vehicles and available battery capacity at different times.

[0024] S2, in the prediction module of the virtual power plant, a wind and solar power generation prediction model is established, with historical wind and solar power generation data as input and predicted wind and solar power generation data as output; Establish a load demand forecasting model, with historical grid load data as input and predicted grid load data as output; A charging prediction model is established, with the historical charging data of electric vehicles as input and the predicted charging data as output.

[0025] Prediction model training includes: Build training and validation sets based on historical data; Train the model based on the training set to complete the initial training of the model; The model is verified based on the validation set, with the input being the historical data at a certain moment and the output being the predicted data at the next moment; The mean square error loss function is used to calculate the loss value between the predicted data at the next moment and the historical data at the next moment of the historical data at one moment. When the loss value is judged to be greater than the preset threshold, the model parameters are adjusted. When the loss value is judged to be less than the preset threshold, the prediction model is obtained.

[0026] The prediction models all use the autoregressive moving average model; before model training, you need to: Determine the model order: based on the autocorrelation function and partial autocorrelation function of the time series; The autocorrelation function measures the linear correlation between data at different time points in a time series. For a given time series data, calculate the autocorrelation coefficient at different lag orders. If the autocorrelation function decays rapidly to zero after a certain lag order, then this order may be a suitable reference for the order of the autoregressive (AR) part.

[0027] The partial autocorrelation function measures the correlation between data at two time points after controlling the influence of the intermediate variables. When the partial autocorrelation function is truncated at a certain lag order (that is, it suddenly becomes zero), this order is likely to be a suitable autoregressive order.

[0028] Combining the analysis results of the autocorrelation function and the partial autocorrelation function, the order of the autoregressive part in the autoregressive moving average model can be determined more accurately. At the same time, combined with the analysis of the moving average part, the order of the entire model can be determined.

[0029] Determine model parameters: Use the least squares method to estimate the parameters of the model and determine the value of the parameter by minimizing the sum of squared errors between the actual data and the data predicted by the model.

[0030] Assume that the model expression after the parameters are determined is:

[0031] in is the value of the time series at time t, is a constant term, and are the parameters of the autoregressive and moving average parts, and are the orders of autoregression and moving average, respectively. is the error term.

[0032] By using the least squares method, we can find the parameters , and The value of minimum, where n is the length of the time series, is the model's prediction for time t.

[0033] S3, in the prediction module of the virtual power plant, the uncertainty range of wind and solar power generation is predicted based on the envelope constraint and the historical wind and solar power generation data and the predicted wind and solar power generation data; The uncertainty range of wind and solar power generation is calculated as: ; = + ; [ *(1- ), *(1+ )]; Where: is the uncertainty interval; is the wind and solar power generation data in period t, is the predicted wind and solar power generation data for period t; is the photovoltaic power generation data in period t; is the wind power generation data in period t; It is the uncertainty range of the scenery predicted at the next moment.

[0034] S4, in the control module of the virtual power plant, obtain the uncertainty range of wind and solar power generation at the current moment, judge whether the predicted load demand data at the current moment falls into the uncertainty range of wind and solar power generation, and the virtual power plant makes corresponding decisions based on the judgment results; the uncertainty range of wind and solar power generation represents that wind and solar power generation will fall into this range under different circumstances. Therefore, according to whether the load falls into it, it can be preliminarily judged whether the load demand can be met and whether electric vehicles need to be introduced. The principles of equality constraints and inequality constraints are mainly adopted. The equality constraint is that the output power of wind and solar power generation + battery discharge power = load demand power + battery charging power. Inequality constraints can be used to ensure that the operating power of the equipment is within its capacity range: wind power generation output power ≤ wind turbine rated power; photovoltaic power generation output power ≤ photovoltaic power generation system installation capacity × maximum output power per unit area.

[0035] If it is determined that it does not fall into the category, the virtual power plant will mobilize electric vehicle batteries to store or release energy; specifically, it includes: When it is determined that the predicted load data is greater than the upper limit of the wind and solar uncertainty range and there is no charging demand, the virtual power plant discharges the battery whose available capacity is less than the discharge threshold; When it is determined that the predicted load data is less than the upper limit of the wind and solar uncertainty range, the virtual power plant charges the batteries whose available capacity is greater than the energy storage threshold; When it is determined that the predicted load data is greater than the upper limit of the wind and solar uncertainty range and there is a demand for charging, the virtual power plant will change the charging time of the electric vehicle to the time when the load is in the off-peak period. Electric vehicle users can change the time by adjusting the electricity price, etc. Since the total capacity and available capacity of each electric vehicle are different, the discharge threshold and energy storage threshold can be compared using a dynamic ratio of the total capacity of each electric vehicle. For example, the discharge threshold can be 50% of the total capacity and the energy storage threshold can be 95% of the total capacity.

[0036] When it is determined to fall into the range, the virtual power plant adjusts the charging information of the electric vehicle according to the predicted charging data and the preset threshold value, and the preset threshold value includes a first threshold value and a second threshold value, the first threshold value is close to the lower limit of the wind and solar uncertainty range, and the second threshold value is close to the upper limit of the wind and solar uncertainty range; in step S4, when it is determined to fall into the range, the virtual power plant adjusts the charging information of the electric vehicle according to the predicted charging data and the preset threshold value, specifically including: When it is determined that the grid load data is between the lower limit of the wind and solar uncertainty range and the first threshold, the virtual power plant increases the charging power of the electric vehicle to reduce the charging time; this indicates that the grid load demand is small, and there is a greater possibility that wind and solar power generation is greater than the grid load, so the wind and solar power generation and grid load can be balanced by increasing the charging power of the car.

[0037] When it is determined that the grid load data is between the second threshold and the upper limit of the wind and solar uncertainty range, the virtual power plant reduces the charging power of the electric vehicle and / or disperses the charging time. This indicates that the grid load demand is large, and there is a high possibility that wind and solar power generation is less than the grid load. Therefore, the wind and solar power generation and grid load can be balanced by reducing the charging power of the car. In this embodiment, the difference between the upper and lower limits of the wind and solar uncertainty range is denoted as a, the first threshold is the lower limit of the wind and solar uncertainty range plus 0.05a, and the second threshold is the upper limit of the wind and solar uncertainty range minus 0.05a.

[0038] In summary, by linking the uncertainty of wind and solar power generation with electric vehicle batteries, electric vehicles can be flexibly dispatched when load demands vary, ensuring stable power supply under different circumstances.

[0039] Example 2 The difference between this embodiment and Embodiment 1 is that this embodiment provides a virtual power plant optimization scheduling device for electric vehicles, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the memory is coupled to the processor, and the processor implements the above-mentioned virtual power plant optimization scheduling method for electric vehicles when executing the computer program.

[0040] Example 3 The difference between this embodiment and embodiment 1 is that this embodiment provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned virtual power plant optimization scheduling method for combined electric vehicles.

[0041] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. As for the method disclosed in the embodiment, since it corresponds to the system disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0042] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0043] The above disclosure is only a preferred embodiment of the present invention, but the present invention is not limited thereto. Any non-creative changes that can be thought of by a person skilled in the art, as well as several improvements and modifications made without departing from the principle of the present invention, should fall within the protection scope of the present invention.

Claims

1. A virtual power plant optimization scheduling method for electric vehicles, It is characterized in that The following steps are involved: S1, build a virtual power plant based on wind and solar power generation equipment, load demand and electric vehicle clusters, and obtain historical wind and solar power generation data, historical grid load data, electric vehicle historical charging data and electric vehicle capacity data. The virtual power plant includes a prediction module and a control module; S2, in the prediction module of the virtual power plant, Establish a wind and solar power generation prediction model, with historical wind and solar power generation data as input and predicted wind and solar power generation data as output; Establish a load demand forecasting model, with historical grid load data as input and predicted grid load data as output; Establish a charging prediction model, with the electric vehicle historical charging data as input and the predicted charging data as output; S3, in the prediction module of the virtual power plant, the uncertainty range of wind and solar power generation is predicted based on the envelope constraint and the historical wind and solar power generation data and the predicted wind and solar power generation data; S4, in the control module of the virtual power plant, the uncertainty range of wind and solar power generation at the current moment is obtained, and it is determined whether the predicted load demand data at the current moment falls within the uncertainty range of wind and solar power generation. The virtual power plant makes corresponding decisions based on the determination result; When it is determined that it does not fall into the category, the virtual power plant mobilizes electric vehicle batteries to store or release energy; When it is determined to fall into the limit, the virtual power plant adjusts the charging information of the electric vehicle based on the predicted charging data and the preset threshold.

2. The virtual power plant optimization scheduling method of the combined electric vehicle according to claim 1, It is characterized in that The historical wind and solar power generation data include wind power generation data, photovoltaic power generation data and meteorological data at different times; the historical power grid load data include power grid load data at different times, and all power grid load data are divided into peak period load, stable period load and valley period load; the charging data include charging demand, charging power data and charging time data; the electric vehicle capacity data include the battery capacity of different electric vehicles and the available battery capacity at different times.

3. The virtual power plant optimization scheduling method of the combined electric vehicle according to claim 2, It is characterized in that In step S3, the uncertainty range of wind and solar power generation is predicted to include: ; = + ; [ *(1- ), *(1+ )]; Where: is the uncertainty interval; is the wind and solar power generation data in period t, is the predicted wind and solar power generation data for period t; is the photovoltaic power generation data in period t; is the wind power generation data in period t; It is the uncertainty range of the scenery predicted at the next moment.

4. The virtual power plant optimization scheduling method of the combined electric vehicle according to claim 2, It is characterized in that In step S4, when it is determined that the condition does not fall into the range, the virtual power plant mobilizes the electric vehicle battery to store or release energy, specifically including: When it is determined that the predicted load data is greater than the upper limit of the wind and solar uncertainty range and there is no charging demand, the virtual power plant discharges the battery whose available capacity is less than the discharge threshold; When it is determined that the predicted load data is less than the upper limit of the wind and solar uncertainty range, the virtual power plant charges the batteries whose available capacity is greater than the energy storage threshold.

5. The virtual power plant optimization scheduling method of the combined electric vehicle according to claim 4, It is characterized in that When it is determined that the predicted load data is greater than the upper limit of the wind and solar uncertainty range and there is a demand for charging, the virtual power plant will change the charging time of the electric vehicle to the time when the load is in the off-peak period.

6. The virtual power plant optimization scheduling method of the combined electric vehicle according to claim 1, It is characterized in that The preset threshold includes a first threshold and a second threshold, the first threshold is close to the lower limit of the wind and light uncertainty range, and the second threshold is close to the upper limit of the wind and light uncertainty range; In step S4, when it is determined to fall into the threshold, the virtual power plant adjusts the charging information of the electric vehicle according to the predicted charging data and the preset threshold, specifically including: When it is determined that the grid load data is between the lower limit of the wind and solar uncertainty range and the first threshold, the virtual power plant increases the charging power of the electric vehicle to reduce the charging time; When it is determined that the grid load data is between the second threshold and the upper limit of the wind and solar uncertainty range, the virtual power plant reduces the charging power of the electric vehicle and / or disperses the charging time.

7. The virtual power plant optimization scheduling method of the electric vehicle combination according to claim 1, It is characterized in that The prediction model training in step S2 includes: Build training and validation sets based on historical data; Train the model based on the training set to complete the initial training of the model; The model is verified based on the validation set, with the input being the historical data at a certain moment and the output being the predicted data at the next moment; The mean square error loss function is used to calculate the loss value between the predicted data at the next moment and the historical data at the next moment of the historical data at one moment. When the loss value is judged to be greater than the preset threshold, the model parameters are adjusted. When the loss value is judged to be less than the preset threshold, the prediction model is obtained.

8. The virtual power plant optimization dispatching method of the combined electric vehicle according to claim 7, It is characterized in that The prediction models all adopt the autoregressive moving average model; before model training, it is necessary to: Determine the model order: based on the autocorrelation function and partial autocorrelation function of the time series; Determine model parameters: Use the least squares method to estimate the parameters of the model and determine the value of the parameter by minimizing the sum of squared errors between the actual data and the data predicted by the model.

9. A virtual power plant optimization dispatching device combined with electric vehicles, It is characterized in that It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the memory is coupled to the processor, and when the processor executes the computer program, it implements the virtual power plant optimization scheduling method for combined electric vehicles as described in any one of claims 1 to 8.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the virtual power plant optimization scheduling method for combined electric vehicles as described in any one of claims 1 to 8.

Citation Information

Cited By

  • Renewable energy intelligent scheduling method and system

    CN120237624A