Virtual power plant resource control method, device, electronic equipment and storage medium
Through the comparison of prediction models and real-time data, the power resource data of virtual power plants is adjusted, and the on-grid power fluctuations caused by weather-induced weather in virtual power plants are solved, and the compliance capacity and resource utilization efficiency are improved.
Patent Information
- Application Number
- CN202411307220.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-19
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-19
AI Technical Summary
When virtual power plants introduce distributed photovoltaic power generation, the on-grid power fluctuations caused by weather, resulting in deviation assessment problems. The existing technology is difficult to effectively predict and regulate, which affects the performance of contracts.
By obtaining historical power resource data, using power generation and usage prediction model for prediction, combining the actual total resource allocation to determine the theoretical grid power and power, and comparing it with real-time power data, determining the resource regulation strategy of power equipment, and adjusting the power resource data to Improve the ability to fulfill contracts.
It effectively reduces the risk of deviation assessment of distributed photovoltaics and improves the performance capacity and power resource utilization efficiency of virtual power plants.
Smart Images

Figure CN118826177B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of smart grid technology, and in particular to a virtual power plant resource control method, device, electronic device and storage medium. Background Art
[0002] As a new energy management model, virtual power plants use advanced information and communication technologies and software systems to efficiently aggregate and optimize the coordination of distributed energy resources. They can improve the utilization efficiency of renewable energy by introducing distributed photovoltaics. However, the introduction of distributed power will lead to greater deviations in assessments. Summary of the invention
[0003] In view of this, the purpose of this application is to propose a virtual power plant resource control method, device, electronic device and storage medium to solve the above-mentioned technical problems.
[0004] Based on the above purpose, the first aspect of the present application provides a virtual power plant resource control method, including:
[0005] Acquire historical power resource data of the connected virtual power plant at various historical moments, and obtain predicted power resource configuration data based on the historical power resource data using a pre-trained power generation and consumption prediction model;
[0006] Obtaining the actual total amount of resource allocation within the resource allocation cycle, and determining the theoretical online power consumption for each day based on the predicted power resource allocation data and the actual total amount of resource allocation within the resource allocation cycle;
[0007] Determine the theoretical grid-connected power based on the predicted power resource configuration data and the theoretical grid-connected power of each day;
[0008] Acquire the real-time power consumption data of the power equipment and the actual power generation power of the distributed photovoltaic field station connected to the virtual power plant, and use the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic field station to determine the resource regulation strategy of the power equipment, and adjust the power resource data of the power equipment according to the resource regulation strategy.
[0009] Based on the same inventive concept, the second aspect of the present application provides a virtual power plant resource control device, including:
[0010] A prediction module is configured to obtain historical power resource data of the connected virtual power plant at various historical moments, and obtain predicted power resource configuration data based on the historical power resource data using a pre-trained power generation and consumption prediction model;
[0011] A module for determining theoretical online power consumption on each day is configured to obtain the actual total amount of resource configuration within the resource configuration cycle, and determine the theoretical online power consumption on each day based on the predicted power resource configuration data and the actual total amount of resource configuration within the resource configuration cycle;
[0012] A theoretical grid-connected power determination module is configured to determine the theoretical grid-connected power based on the predicted power resource configuration data and the theoretical grid-connected power of each day;
[0013] The adjustment module is configured to obtain the real-time power consumption data of the power equipment and the actual power generation power of the distributed photovoltaic field station connected to the virtual power plant, and use the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic field station to determine the resource regulation strategy of the power equipment, and adjust the power resource data of the power equipment according to the resource regulation strategy.
[0014] Based on the same inventive concept, the third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described in the first aspect above when executing the computer program.
[0015] Based on the same inventive concept, the fourth aspect of the present application provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method described in the first aspect above.
[0016] From the above, it can be seen that the virtual power plant resource control method, device, electronic device and storage medium provided by the present application, the historical power resource data of the user side at each historical moment, is connected to the virtual power plant through the side terminal via the secure access area, and the power generation and consumption prediction model is used to carry out data prediction based on the power generation and consumption prediction model to obtain the predicted power resource configuration data, and then the actual total resource configuration amount within the resource configuration cycle is combined to perform intraday prediction to determine the theoretical online power of each day, and then the theoretical online power is determined based on the predicted power resource configuration data and the theoretical online power of each day. The real-time power consumption data and the sum of the theoretical online power are compared with the actual power generation power of the distributed photovoltaic station to determine the resource control strategy of the corresponding power equipment, so as to carry out power resource data control on the power equipment corresponding to the distributed photovoltaic, so as to improve the performance of the virtual power plant and reduce deviation assessment. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0018] Figure 1 A flowchart of a virtual power plant resource control method according to an embodiment of the present application;
[0019] Figure 2 This is a structural block diagram of a virtual power plant resource control device according to an embodiment of the present application;
[0020] Figure 3 A schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0021] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.
[0022] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0023] It is understandable that before using the technical solutions of each embodiment of the present application, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.
[0024] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to the electronic device, application, server, storage medium or other software or hardware that performs the operation of the technical solution of the present application according to the prompt message.
[0025] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.
[0026] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation method of this application. Other methods that meet relevant laws and regulations may also be applied to the implementation method of this application.
[0027] This application found that distributed photovoltaic power generation is affected by climatic conditions, such as light intensity and temperature, which may affect the operation and power generation of photovoltaic equipment. Distributed photovoltaics lack effective and flexible ex ante forecasting capabilities due to their small size and scattered layout. On the other hand, virtual power plants introduce distributed photovoltaics in the process of electricity fulfillment. Due to the self-generation and self-use surplus grid-connected operation mode and the influence of weather, they will face fluctuations in grid-connected electricity, which may cause distributed photovoltaics to face more serious deviation assessments.
[0028] As the total amount of distributed photovoltaics increases year by year, subsequent virtual power plants that introduce distributed photovoltaics will inevitably face deviation assessment problems in the process of electricity contract fulfillment.
[0029] Among them, deviation assessment refers to when the actual power generation or actual power consumption is greater than the agreed contract power, it is called positive deviation power; when the actual power generation or actual power consumption is less than the agreed contract power, it is called negative deviation power. Users need to make an advance estimate of their agreed power, and then sign a green power contract with the power user. When the actual green power is inconsistent with the power agreed in the contract, there is a deviation, which is the deviation power. If the deviation power exceeds the prescribed deviation range, there will be a certain penalty for the deviation power, which is the deviation assessment.
[0030] Green electricity, also known as green electricity, refers to electricity converted from renewable energy sources (such as wind energy, solar energy, hydropower, biomass energy, etc.) Compared with traditional fossil fuels (such as coal, oil, and natural gas), these energies are clean, renewable, and environmentally friendly.
[0031] Distributed photovoltaic refers specifically to photovoltaic power generation facilities that are built near user sites, with the characteristics of self-generation and self-use on the user side, surplus electricity being connected to the grid, and balanced and regulated in the distribution system.
[0032] Virtual power plant refers to the use of advanced information and communication technologies and software systems to efficiently aggregate and optimize distributed energy resources such as distributed power sources, energy storage systems, controllable loads, electric vehicles, etc. It can realize the dynamic allocation, potential mining, load forecasting and real-time control of distributed energy.
[0033] An embodiment of the present application provides a method for regulating and controlling resources of a virtual power plant. The historical power resource data of the user side at each historical moment is connected to the virtual power plant through a side terminal via a secure access area. The power generation and consumption prediction model is used to carry out data prediction based on the power generation and consumption prediction model to obtain predicted power resource configuration data. Then, the actual total amount of resource configuration within the resource configuration cycle is combined to perform intraday prediction to determine the theoretical online power of each day. Then, the theoretical online power is determined based on the predicted power resource configuration data and the theoretical online power of each day. The sum of the real-time power consumption data and the theoretical online power is compared with the actual power generation power of the distributed photovoltaic field to determine the resource regulation strategy of the corresponding power equipment, so as to regulate the power resource data of the power equipment corresponding to the distributed photovoltaic field, so as to improve the performance capability of the virtual power plant and reduce deviation assessment.
[0034] like Figure 1 As shown, the method of this embodiment includes:
[0035] Step 101, obtaining historical power resource data of the connected virtual power plant at various historical moments, and obtaining predicted power resource configuration data based on the historical power resource data using a pre-trained power generation and consumption prediction model.
[0036] In this step, the virtual power plant data processing module is used to pre-process the initial historical power resource data connected to the virtual power plant, and the abnormal points are marked to obtain the historical power resource data.
[0037] In actual projects, due to external reasons such as the processing capacity of the collection equipment and the communication network, problems such as data loss and noise usually occur. In order to support the data requirements of the subsequent virtual power plant power / load forecasting module, the acquired initial historical power resource data needs to be processed for abnormal points. For missing data, since the equipment operation data is time series data, the autoregressive integrated moving average (ARIMA) model is used to supplement the missing data.
[0038] For the noise data, the weighted moving average method is used for smoothing. This method optimizes the traditional moving average method by assigning different weights to each data point in the rolling window. The weight is set by the distance between the time point and the current point. The data closer to the current point is given a higher weight, which effectively removes the noise. The new energy power generation prediction component is used, combined with the processed photovoltaic historical power generation data and the meteorological data of the distributed photovoltaic location, and the power generation and consumption prediction model is used to predict the online power of the new energy unit to obtain the predicted power resource configuration data.
[0039] Step 102, obtaining the actual total amount of resource configuration within the resource configuration cycle, and determining the theoretical online power for each day based on the predicted power resource configuration data and the actual total amount of resource configuration within the resource configuration cycle.
[0040] In this step, confirm the electricity request period and the electricity request amount. Since green electricity requests belong to the category of medium- and long-term electricity requests, the electricity request period covers years (multiple years), months (multiple months), and intra-month (ten-day, weekly, and daily rolling). In order to accumulate participation experience and optimize participation strategies, the early stage focuses on participating in monthly and intra-month electricity requests. Although the request methods for green electricity requests are different, they all need to complete the confirmation of information such as the requested electricity consumption and the requested electricity time period before the request. Taking the participation in the monthly green electricity request as an example, the system uses the following process to specify the electricity request strategy:
[0041] (1) Obtain meteorological data of the distributed photovoltaic units, call the prediction model of the distributed photovoltaic units participating in the green power request (i.e., the power generation and consumption prediction model) to perform predictions, obtain the power generation prediction data and power consumption prediction data, and form a power generation prediction data curve and a power consumption prediction data curve based on time series respectively.
[0042] (2) Taking 15 minutes as a metering point, calculate the photovoltaic grid-connected electricity in each period of one day, and introduce the time-sharing resource consumption of the local area during the execution period. The specific calculation formula is as follows:
[0043]
[0044] Among them, yes Internet power consumption during the period, is the weight coefficient (i.e. the preset first weight coefficient). To avoid excessively high reported power consumption due to excessive forecast deviation, the value is set to 0.9. For distributed photovoltaic The power generation during the period (i.e. the power generation forecast data), For distributed photovoltaic locations The resource consumption of Internet requests at each moment, Green electricity environmental resource consumption (i.e., the amount of resource consumption that users need to bear for every kilowatt-hour of green electricity they use). For the location of distributed photovoltaic Time-sharing resource consumption of time periods, For distributed photovoltaic power equipment Power consumption forecast data for each time period, When the distributed photovoltaic grid-connected resource consumption plus the green electricity environmental resource consumption is less than Time-sharing resource consumption and distributed photovoltaic exist When the power in a time period is less than the power consumption of the corresponding power-applying equipment, the minimum online power weight coefficient (i.e. the preset second weight coefficient) is set. This coefficient is designed as a backup online capacity to prevent large fluctuations in online power consumption in other time periods. The value here is 0.05.
[0045] (3) The distributed photovoltaic After calculating the online power consumption of the time period, the sum of other time periods throughout the day is calculated, and finally the current green power request for the whole day is obtained, and further summed up to obtain the total predicted resource allocation in the entire resource allocation cycle :
[0046]
[0047] in is the number of days in the resource allocation cycle, After the total time period of a certain day, the resource request time period and the requested electricity consumption are confirmed, the green electricity request declaration is completed and the green electricity performance contract is reached.
[0048] (4) After the performance contract is concluded, in order to effectively assess the deviation caused by the deviation, the monthly green electricity consumption in the electricity demand contract shall be first calculated.
[0049] Combined with the daily time period calculated in step (3) Electricity: Decompose the contracted electricity by day to obtain the theoretical online electricity for each day , the overall decomposition formula is as follows:
[0050]
[0051] in, For distributed photovoltaic stations The theoretical Internet power consumption allocated each day, To estimate the green power demand during the resource allocation cycle (i.e. the total predicted resource allocation during the resource allocation cycle), To estimate the power generation on a certain day (i.e. based on the The predicted power generation for the day), The actual power request amount during the resource configuration period (i.e., the actual total amount of resource configuration during the resource configuration period).
[0052] Step 103: determining the theoretical grid-connected power based on the predicted power resource configuration data and the theoretical grid-connected power of each day.
[0053] In this step, the theoretical grid-connected power can be quickly determined by predicting the power resource configuration data and combining the theoretical grid-connected power of each day.
[0054] Step 104, obtain the real-time power consumption data of the power equipment and the actual power generation power of the distributed photovoltaic field station connected to the virtual power plant, and use the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic field station to determine the resource regulation strategy of the power equipment, and adjust the power resource data of the power equipment according to the resource regulation strategy.
[0055] In this step, the real-time power consumption data and the sum of the theoretical grid-connected power are compared with the actual power generation power of the distributed photovoltaic field to determine the resource control strategy of the corresponding power equipment, so as to regulate the power resource data of the power equipment corresponding to the distributed photovoltaic, so as to improve the performance capability of the virtual power plant and reduce the deviation assessment.
[0056] Through the above scheme, the historical power resource data of the user side at each historical moment is connected to the virtual power plant through the edge terminal via the secure access area, and the power generation and consumption prediction model is used to carry out data prediction based on the power generation and consumption prediction model to obtain the predicted power resource configuration data, and then the actual total resource configuration amount within the resource configuration cycle is combined to make intraday predictions to determine the theoretical online power of each day, and then the theoretical online power is determined based on the predicted power resource configuration data and the theoretical online power of each day. The sum of the real-time power consumption data and the theoretical online power is compared with the actual power generation power of the distributed photovoltaic field to determine the resource regulation strategy of the corresponding power equipment, so as to regulate the power resource data of the power equipment corresponding to the distributed photovoltaic, so as to improve the performance of the virtual power plant and reduce deviation assessment.
[0057] In some embodiments, in step 101, the acquiring of historical power resource data of the connected virtual power plant at each historical moment includes:
[0058] Step A1, obtaining the initial historical power resource data of the connected virtual power plant at each historical moment, and determining the average value of the initial historical power resource data at each historical moment.
[0059] Step A2, based on the preset size of the moving window , initial historical power resource data at each historical moment and the average , the moving standard deviation is obtained by the following formula :
[0060]
[0061] in, Indicates the order of historical moments, Indicates the total duration of historical moments.
[0062] Step A3, using the moving standard deviation and the preset moving standard deviation speed Perform product processing to obtain the noise threshold .
[0063] Step A4, at each historical moment Initial historical power resource data Respectively with the noise threshold for comparison.
[0064] Step A5, in response to the initial historical power resource data Less than or equal to the noise threshold , determine the initial historical power resource data It is noise data, and the initial historical power resource data is obtained Corresponding preset historical moment Weight , based on the initial historical power resource data and the weights The weighted moving average is determined by the following formula :
[0065]
[0066] in, Indicates the order of historical moments, Indicates the total duration of historical moments. Represents the size of the preset moving window; replaces the initial historical power resource data with the weighted moving average value As the historical power resource data. Or,
[0067] Step A6, in response to the initial historical power resource data Greater than the noise threshold , determine the initial historical power resource data It is not noise data and does not perform the same as the initial historical power resource data. The process of determining the corresponding weighted moving average.
[0068] In the above scheme, the virtual power plant data processing module is used to pre-process the initial historical power resource data connected to the virtual power plant and mark the abnormal points.
[0069] In actual projects, due to external reasons such as the processing capacity of the collection equipment and the communication network, problems such as data loss and noise usually occur. In order to support the data requirements of the subsequent virtual power plant power / load forecasting module, the acquired initial historical power resource data needs to be processed for abnormal points. For missing data, since the equipment operation data is time series data, the autoregressive integrated moving average (ARIMA) model is used to supplement the missing data.
[0070] For noisy data, the weighted moving average method is used for smoothing. This method optimizes the traditional moving average method by assigning different weights to each data point in the rolling window. The weight is set by the distance between the time point and the current point. The data closer to the current point is given a higher weight, thereby effectively removing noise. The process steps are as follows:
[0071] (1) First, the moving standard deviation of the initial historical power resource data at each historical moment is calculated to identify outliers. Moving standard deviation It can be calculated using the following formula:
[0072]
[0073] in, is the size of the moving window, It is a window The average of all data points in .
[0074] (2) Secondly, set the noise threshold to identify noise. The noise threshold can be a multiple of the moving standard deviation, for example , where, combined with the photovoltaic curve characteristics, Set to a constant greater than 1, such as 2.0; for each time point ,if Greater than , then it is believed that It is a noise point;
[0075] (3) Again, for noise , using a weighted moving average to estimate its value. The weights can be assigned according to the distance of the time point, as shown below:
[0076]
[0077] in, It's time point The weight is defined as , the weight decreases as the time distance increases.
[0078] (4) Finally, the identified noise points Replaced by weighted moving average .
[0079] In some embodiments, the historical power resource data includes training resource data and predicted resource data.
[0080] In step 101, the power generation and consumption prediction model is trained through the following process:
[0081] Step B1, obtaining actual power resource configuration data corresponding to the training resource data, and constructing an initial model.
[0082] Step B2, inputting the training resource data into the initial model, and outputting the training predicted power resource configuration data through the initial model.
[0083] Step B3, determining a loss function according to the actual power resource configuration data and the training predicted power resource configuration data.
[0084] Step B4: training and adjusting the initial model according to the minimization result obtained in the process of minimizing the loss function to obtain the trained and adjusted initial model, and based on the actual power resource configuration data , and predictive power resource allocation data The indicator corresponding to the initial model after training and adjustment is determined by the following formula :
[0085]
[0086] in, Indicates actual power resource configuration data The number of groups of corresponding training resource data, Indicates Group training resource data, Indicates the number of data in each group of training resource data, Indicates the order of historical moments, Indicates the preset weight factor.
[0087] Step B5: In response to the indicator being less than a preset indicator threshold, continuously adjusting the trained and adjusted initial model. Or,
[0088] Step B6, in response to the indicator being greater than or equal to a preset indicator threshold, using the trained and adjusted initial model as a power generation and consumption prediction model.
[0089] In the above scheme, after the data is processed, the potential assessment module is called to train the initial model. The new energy power generation prediction component is used to combine the processed photovoltaic historical power generation data and the meteorological data of the distributed photovoltaic location, and the neural network model is used to train the distributed photovoltaic power generation model (i.e., the initial model) of the access point. The new energy grid-connected power prediction component is used to predict the grid-connected power of the new energy unit. The load prediction component is used to synchronously train the load prediction model of the power-consuming equipment where the distributed photovoltaic is located. After the model training is completed, some data (i.e., predicted resource data) is extracted from the historical power resource data (data where the training part is not executed) to evaluate the model accuracy of the trained and adjusted initial model.
[0090] Since the outliers were repaired during data preprocessing, the improved mean absolute percentage error was used as an indicator to evaluate the prediction accuracy. The specific formula is as follows:
[0091]
[0092] in, It is a set of selected validation data (i.e., the actual power resource configuration data). The number of groups of corresponding training resource data), Representative The validation set (i.e. group training resource data), is the actual value (i.e., actual power resource configuration data), is the predicted value (i.e. the predicted power resource configuration data), is the number of samples (i.e. the number of data in each set of training resource data), is the weight factor of the current value (i.e. the preset weight factor). If the value is a normal value (not processed abnormally), the weight is 1. If the value is a processed value, the weight is 0.7. The data in the prediction set is traversed to obtain the percentage error and then processed by weight to obtain the overall error rate. Finally, the accuracy of the model is obtained by subtracting the error rate from 1. After calculating the accuracy of multiple validation sets, the final prediction accuracy of the model is obtained by averaging.
[0093] If the accuracy is lower than 90% (i.e. the preset indicator threshold), adjust the model step size, number of hidden layers, number of training times and other related parameters, adjust the training set and test set sample data, and retrain the model until the accuracy reaches 90% or above.
[0094] In some embodiments, the predicted electric power resource configuration data includes: power generation prediction data and power consumption prediction data.
[0095] In step 102, the theoretical online power consumption on each day is determined based on the predicted power resource configuration data and the actual total resource configuration within the resource configuration cycle, including:
[0096] Step C1, based on the power generation prediction data and the power consumption forecast data The following formula is used to determine each historical moment Internet power :
[0097]
[0098] in, represents the preset first weight coefficient, represents the preset second weight coefficient, Indicates the order of historical moments, Indicates the historical moment The resource consumption of Internet requests is Indicates the consumption of green electricity environmental resources, Indicates the historical moment time-sharing resource consumption.
[0099] Step C2, using the various historical moments Internet power The total amount of predicted resource allocation within the resource allocation cycle is determined by the following formula :
[0100]
[0101] in, Indicates the number of days of the resource configuration cycle. Indicates the first sky, Indicates The total duration of the historical moments of the day.
[0102] Step C3, using the power generation prediction data and The total duration of the historical moments of the day is multiplied by the product to obtain Forecasted power generation for the day .
[0103] Step C4, based on Forecasted power generation for the day , the total amount of resource allocation predicted within the resource allocation cycle , the actual total amount of resource allocation during the resource allocation cycle The theoretical daily Internet access power is determined by the following formula :
[0104] .
[0105] In the above scheme, confirm the electricity request period and the electricity request amount. Since the green electricity request belongs to the category of medium- and long-term electricity request, the electricity request period covers years (multiple years), months (multiple months), and intra-month (ten-day, weekly, and daily rolling). In order to accumulate participation experience and optimize participation strategies, the early stage is mainly to participate in monthly and intra-month electricity requests. Although the request methods of green electricity requests are different, they all need to complete the confirmation of the requested electricity consumption, requested electricity period and other information before the request. Taking the participation in the monthly green electricity request as an example, the system uses the following process to specify the electricity request strategy:
[0106] (1) Obtain meteorological data of the distributed photovoltaic units, call the prediction model of the distributed photovoltaic units participating in the green power request (i.e., the power generation and consumption prediction model) to perform predictions, obtain the power generation prediction data and power consumption prediction data, and form a power generation prediction data curve and a power consumption prediction data curve based on time series respectively.
[0107] (2) Taking 15 minutes as a metering point, calculate the photovoltaic grid-connected electricity in each period of one day, and introduce the time-sharing resource consumption of the local area during the execution period. The specific calculation formula is as follows:
[0108]
[0109] Among them, yes Internet power consumption during the period, is the weight coefficient (i.e. the preset first weight coefficient). To avoid excessively high reported power consumption due to excessive forecast deviation, the value is set to 0.9. For distributed photovoltaic The power generation during the period (i.e. the power generation forecast data), For distributed photovoltaic locations The resource consumption of Internet requests at each moment, Green electricity environmental resource consumption (i.e., the amount of resource consumption that users need to bear for every kilowatt-hour of green electricity they use). For the location of distributed photovoltaic Time-sharing resource consumption of time periods, For distributed photovoltaic power equipment Power consumption forecast data for each time period, When the distributed photovoltaic grid-connected resource consumption plus the green electricity environmental resource consumption is less than Time-sharing resource consumption and distributed photovoltaic exist When the power in a time period is less than the power consumption of the corresponding power-applying equipment, the minimum online power weight coefficient (i.e. the preset second weight coefficient) is set. This coefficient is designed as a backup online capacity to prevent large fluctuations in online power consumption in other time periods. The value here is 0.05.
[0110] (3) The distributed photovoltaic After calculating the online power consumption of the time period, the sum of other time periods throughout the day is calculated, and finally the current green power request for the whole day is obtained, and further summed up to obtain the total predicted resource allocation in the entire resource allocation cycle :
[0111]
[0112] in is the number of days in the resource allocation cycle, After the total time period of a certain day, the resource request time period and the requested electricity consumption are confirmed, the green electricity request declaration is completed and the green electricity performance contract is reached.
[0113] (4) After the performance contract is concluded, in order to effectively assess the deviation caused by the deviation, the monthly green electricity consumption in the electricity demand contract shall be first calculated.
[0114] Combined with the daily time period calculated in step (3) Electricity: Decompose the contracted electricity by day to obtain the theoretical online electricity for each day , the overall decomposition formula is as follows:
[0115]
[0116] in, For distributed photovoltaic stations The theoretical Internet power consumption allocated each day, To estimate the green power demand during the resource allocation cycle (i.e. the total predicted resource allocation during the resource allocation cycle), To estimate the power generation on a certain day (i.e. based on the The predicted power generation for the day), The actual power request amount during the resource configuration period (i.e., the actual total amount of resource configuration during the resource configuration period).
[0117] In some embodiments, the predicted power resource configuration data includes: power generation prediction data.
[0118] Step 103 includes:
[0119] Based on the predicted power resource configuration data The theoretical daily Internet access power consumption The theoretical grid power is determined by the following formula :
[0120]
[0121] in, Indicates the order of historical moments, Represents the total number of historical moments.
[0122] In the above scheme, the theoretical Internet power consumption per day in the resource allocation cycle is obtained. ,pass Combined with forecasted power resource allocation data Calculate theoretical network power , the calculation formula is as follows:
[0123]
[0124] By predicting power resource allocation data , combined with the theoretical daily Internet consumption The theoretical Internet power can be quickly determined .
[0125] In some embodiments, the electrical equipment includes an electrical equipment and an energy storage equipment.
[0126] In step 104, the resource control strategy of the power equipment is determined by using the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic station, including:
[0127] Step D1, in response to the sum of the real-time power consumption data and the theoretical grid-connected power being less than or equal to the actual power generation power of the distributed photovoltaic station, determining that the resource regulation strategy of the power equipment is to charge the energy storage device.
[0128] Step D2, in response to the sum of the real-time power consumption data and the theoretical grid-connected power being greater than the actual power generation power of the distributed photovoltaic field station, and the theoretical grid-connected power being greater than the actual power generation power of the distributed photovoltaic field station, the resource control strategy of the power equipment is determined to determine the overall power control amount corresponding to the power consumption equipment and the energy storage equipment.
[0129] In the above scheme, the virtual power plant is used to monitor the operation of each photovoltaic field in real time on the execution day, and the virtual power plant optimization control strategy is used to adjust the grid-connected power in real time to improve the performance of the contract. The optimization control strategy of the virtual power plant participating in the green power request is as follows:
[0130] Obtain the actual power generation of distributed photovoltaic stations through real-time measurement of virtual power plants , Real-time power consumption data ;
[0131] If the real-time power consumption data within the time period Theoretical Internet Power The sum is less than the actual power generation of the distributed photovoltaic station , then evaluate the virtual power plant regulation cost (if the regulation cost is greater than the utility of the green power request, skip the regulation; if it is equal to or less than the utility of the green power request, start the regulation), charge the energy storage equipment, maximize the photovoltaic utilization rate, and prevent the abandonment of light; or,
[0132] If the real-time power consumption data within the time period Theoretical Internet Power The sum is greater than the actual power generation of the distributed photovoltaic station , and theoretically the Internet power Greater than the actual power generation of distributed photovoltaic stations , there is a power generation shortage. At this time, in order to increase the amount of power connected to the grid and minimize the impact on the production of power-consuming equipment, the virtual power plant starts optimization regulation to determine the overall power regulation amount corresponding to the power-consuming equipment and energy storage equipment, such as calling central air conditioning, lighting, and energy storage in turn to reduce the adjustable load.
[0133] In some embodiments, the electrical equipment includes air conditioning equipment and landscape lighting equipment.
[0134] In step D2, determining the overall power control amount corresponding to the power-consuming device and the energy storage device includes:
[0135] Step E1, obtaining resource allocation data corresponding to the air conditioning equipment and the preset maximum resource allocation data threshold .
[0136] Step E2, based on the resource allocation data corresponding to the air conditioning equipment and the preset maximum resource allocation data threshold , the resource allocation data adjustment function is determined by the following formula :
[0137] .
[0138] Step E3, obtaining the center value of the comfortable temperature range corresponding to the air conditioning equipment , the current temperature corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment .
[0139] Step E4, based on the center value of the comfortable temperature range corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment , the temperature regulation function is determined by the following formula :
[0140] .
[0141] Step E5, adjusting the function based on the resource allocation data and the temperature regulation function The relationship function corresponding to the air conditioning equipment is determined by the following formula :
[0142]
[0143] in, represents the preset third weight coefficient, Indicates the preset fourth weight coefficient.
[0144] Step E6: Obtain the rated power of the air conditioner and the minimum power of the air conditioning equipment .
[0145] Step E7, based on the relationship function , the rated power of the air conditioning equipment and the minimum power of the air conditioning equipment The power increase is determined by the following formula :
[0146] .
[0147] Step E8: Obtain the real-time power of the air conditioning equipment , based on the power increment and the minimum power of the air conditioning equipment Determined by the following formula The power control amount of the air conditioning equipment at the moment ;
[0148] .
[0149] Step E9: Obtain the power required to be adjusted for the landscape lighting equipment , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment .
[0150] Step E10, based on the power required to be adjusted for the landscape lighting equipment , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment , determined by the following formula The current load difference corresponding to the landscape lighting equipment at the moment :
[0151] .
[0152] Step E11, obtain Output power of the landscape lighting equipment at the moment .
[0153] Step E12, based on The current load difference corresponding to the landscape lighting equipment at the moment ,exist The current load difference corresponding to the landscape lighting equipment at the moment , the power regulation amount of the landscape lighting equipment is determined by the following formula :
[0154]
[0155] in, Indicates the preset attenuation factor.
[0156] Step E13, obtain The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge rate of the energy storage device .
[0157] Step E14, based on The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge power of the energy storage device , the power regulation amount of the energy storage device is determined by the following formula :
[0158] .
[0159] Step E15, obtain Output power of the air conditioning equipment at the time and Output power of the energy storage device at the moment .
[0160] Step E16, based on The power control amount of the air conditioning equipment at the moment , Output power of the air conditioning equipment at the time ,based on The power control amount of the landscape lighting equipment at the moment , Output power of the landscape lighting equipment at the moment ,based on The power control amount of the energy storage device at the moment and Output power of the energy storage device at the moment The overall power control amount is determined by the following formula :
[0161] .
[0162] In the above scheme, if the real-time power consumption data within the time period Theoretical Internet Power The sum is greater than the actual power generation of the distributed photovoltaic station , and theoretically the Internet power Greater than the actual power generation of distributed photovoltaic stations , there is a power generation shortage. At this time, in order to increase the amount of power connected to the grid and minimize the impact on the production of power-consuming equipment, the virtual power plant starts optimization regulation to determine the overall power regulation amount corresponding to the power-consuming equipment and energy storage equipment. For example, central air conditioning, lighting, and energy storage are called in turn to reduce the adjustable load.
[0163]
[0164] in, Represents the overall control amount, Indicates the power control amount of the air conditioning equipment. Indicates the power regulation amount of landscape lighting equipment, Indicates the power regulation amount of the energy storage device. The specific regulation strategies of each resource are as follows:
[0165] The air conditioning adjustment model is constructed under the premise of considering the density and comfort of people. The specific model is constructed as follows: is the adjustment function of personnel density (i.e., resource allocation data adjustment function), is the conditioning function of temperature:
[0166]
[0167]
[0168]
[0169] in, Represents the density of people in the factory / shopping mall (number of people / unit area) (i.e., resource allocation data corresponding to air-conditioning equipment); Represents the maximum comfortable personnel density within the industry and commerce (i.e., the preset maximum resource allocation data threshold); Represents the current temperature in the factory / shopping mall (i.e. the current temperature corresponding to the air-conditioning equipment); Indicates the center value of the most comfortable temperature range (i.e. the center value of the comfortable temperature range corresponding to the air conditioning equipment). Usually the best temperature for industry and commerce is set at 26 degrees. For comfortable temperature range (e.g. ± ), usually set to 2; is a weight coefficient (i.e., a preset third weight coefficient) for adjusting the influence of the personnel density on the power regulation. is a weight coefficient (ie, a preset fourth weight coefficient) for adjusting the effect of temperature on power regulation.
[0170] The air conditioning adjustable power calculation function based on the above relationship function is constructed as follows, where is the relation function constructed above, is the rated power of current industrial and commercial air conditioners (i.e. the rated power of air conditioning equipment), Indicates the minimum power that can be set for the central air conditioner (i.e. the minimum power of the air conditioner) to ensure basic comfort and to ensure that the adjustment power does not drop to Below, the following conditions are used for constraints:
[0171]
[0172]
[0173] For industrial and commercial landscape lighting, the virtual power plant uses a responsive power adjustment strategy for landscape lighting equipment to complete the required power adjustment when the usage conditions are met. The specific adjustment strategy is as follows:
[0174]
[0175]
[0176] in, represent The output power of landscape lighting equipment at all times; represent The output power of landscape lighting equipment at all times; at the same time, in order to ensure the smooth operation of lighting equipment adjustment, the introduction (0< <1) Attenuation factor to smooth power adjustment; Indicates the current load difference; Indicates that power needs to be adjusted; Indicates the minimum power limit of the landscape lighting system to ensure basic lighting needs.
[0177] For energy storage equipment, a regulation strategy is constructed to meet the regulation requirements, output power of energy storage equipment, charging and discharging efficiency, and charging and discharging rate limits. The virtual power plant task scheduling module is used to achieve 15-minute regulation control. The specific regulation strategy is as follows:
[0178]
[0179] in represent Output power of energy storage device at any moment; Indicates the current load difference; Indicates the real-time power of the current energy storage device; Indicates the discharge efficiency of the energy storage device; Indicates the maximum discharge rate of the energy storage device.
[0180] According to the control requirements, each resource generates a corresponding adjustment instruction. After the adjustment is completed, it is confirmed whether the control requirements are met. If not, the relevant resources are controlled again.
[0181] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.
[0182] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0183] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a virtual power plant resource control device.
[0184] refer to Figure 2 , the virtual power plant resource control device comprises:
[0185] The prediction module 201 is configured to obtain historical power resource data of the connected virtual power plant at various historical moments, and obtain predicted power resource configuration data based on the historical power resource data using a pre-trained power generation and consumption prediction model;
[0186] The daily theoretical online power determination module 202 is configured to obtain the actual total amount of resource configuration within the resource configuration cycle, and determine the theoretical online power for each day based on the predicted power resource configuration data and the actual total amount of resource configuration within the resource configuration cycle;
[0187] Theoretical grid power determination module 203 is configured to determine the theoretical grid power based on the predicted power resource configuration data and the theoretical grid power of each day;
[0188] The adjustment module 204 is configured to obtain the real-time power consumption data of the power equipment and the actual power generation power of the distributed photovoltaic field station connected to the virtual power plant, and use the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic field station to determine the resource regulation strategy of the power equipment, and adjust the power resource data of the power equipment according to the resource regulation strategy.
[0189] In some embodiments, the prediction module 201 is specifically configured to:
[0190] Obtaining initial historical power resource data of the connected virtual power plant at each historical moment, and determining an average value of the initial historical power resource data at each historical moment;
[0191] The size of the moving window based on the preset , initial historical power resource data at each historical moment and the average , the moving standard deviation is obtained by the following formula :
[0192]
[0193] in, Indicates the order of historical moments, Indicates the total duration of historical moments;
[0194] Using the moving standard deviation and the preset moving standard deviation speed Perform product processing to obtain the noise threshold ;
[0195] At every historical moment Initial historical power resource data Respectively with the noise threshold Make a comparison;
[0196] In response to the initial historical power resource data Less than or equal to the noise threshold , determine the initial historical power resource data It is noise data, and the initial historical power resource data is obtained Corresponding preset historical moment Weight , based on the initial historical power resource data and the weights The weighted moving average is determined by the following formula :
[0197]
[0198] in, Indicates the order of historical moments, Indicates the total duration of historical moments. Represents the size of the preset moving window; replaces the initial historical power resource data with the weighted moving average value as the historical power resource data; or,
[0199] In response to the initial historical power resource data Greater than the noise threshold , determine the initial historical power resource data It is not noise data and does not perform the same as the initial historical power resource data. The process of determining the corresponding weighted moving average.
[0200] In some embodiments, the virtual power plant resource control device further includes a training module, and the training module is specifically configured to:
[0201] Acquire actual power resource configuration data corresponding to the training resource data and construct an initial model;
[0202] Inputting the training resource data into the initial model, and outputting the training predicted power resource configuration data through the initial model;
[0203] Determine a loss function according to the actual power resource configuration data and the training predicted power resource configuration data;
[0204] The initial model is trained and adjusted according to the minimization result obtained in the process of minimizing the loss function to obtain the trained and adjusted initial model, and based on the actual power resource configuration data , and predictive power resource allocation data The indicator corresponding to the initial model after training and adjustment is determined by the following formula :
[0205]
[0206] in, Indicates actual power resource configuration data The number of groups of corresponding training resource data, Indicates Group training resource data, Indicates the number of data in each group of training resource data, Indicates the order of historical moments, Indicates the preset weight factor;
[0207] In response to the indicator being less than a preset indicator threshold, continuously adjusting the trained and adjusted initial model; or,
[0208] In response to the indicator being greater than or equal to a preset indicator threshold, the trained and adjusted initial model is used as a power generation and consumption prediction model.
[0209] In some embodiments, the predicted power resource configuration data includes: power generation prediction data and power consumption prediction data;
[0210] The daily theoretical online power consumption determination module 202 is specifically configured as follows:
[0211] Based on the power generation prediction data and the power consumption forecast data The following formula is used to determine each historical moment Internet power :
[0212]
[0213] in, represents the preset first weight coefficient, represents the preset second weight coefficient, Indicates the order of historical moments, Indicates the historical moment The resource consumption of Internet requests is Indicates the consumption of green electricity environmental resources, Indicates the historical moment Time-sharing resource consumption;
[0214] Using the various historical moments Internet power The total amount of predicted resource allocation within the resource allocation cycle is determined by the following formula :
[0215]
[0216] in, Indicates the number of days of the resource configuration cycle. Indicates the first sky, Indicates The total length of the historical moments of the day;
[0217] Using the power generation prediction data and The total duration of the historical moments of the day is multiplied by the product to obtain Forecasted power generation for the day ;
[0218] Based on Forecasted power generation for the day , the total amount of resource allocation predicted within the resource allocation cycle , the actual total amount of resource allocation during the resource allocation cycle The theoretical daily Internet access power is determined by the following formula :
[0219] .
[0220] In some embodiments, the predicted power resource configuration data includes: power generation prediction data;
[0221] The theoretical online power determination module 203 is specifically configured as follows:
[0222] Based on the predicted power resource configuration data The theoretical daily Internet access power consumption The theoretical grid power is determined by the following formula :
[0223]
[0224] in, Indicates the order of historical moments, Represents the total number of historical moments.
[0225] In some embodiments, the power equipment includes power-consuming equipment and energy storage equipment;
[0226] The adjustment module 204 includes:
[0227] A first strategy determination unit is configured to determine that the resource control strategy of the power equipment is to charge the energy storage device in response to the sum of the real-time power consumption data and the theoretical grid-connected power being less than or equal to the actual power generation power of the distributed photovoltaic station;
[0228] The second strategy determination unit is configured to determine the resource control strategy of the power equipment as determining the overall power control amount corresponding to the power consuming equipment and the energy storage equipment in response to the sum of the real-time power consumption data and the theoretical grid-connected power being greater than the actual power generation power of the distributed photovoltaic field station, and the theoretical grid-connected power being greater than the actual power generation power of the distributed photovoltaic field station.
[0229] In some embodiments, the electrical equipment includes air conditioning equipment and landscape lighting equipment;
[0230] The second strategy determination unit is specifically configured to:
[0231] Obtain resource allocation data corresponding to the air conditioning equipment and the preset maximum resource allocation data threshold ;
[0232] Based on the resource allocation data corresponding to the air conditioning equipment and the preset maximum resource allocation data threshold , the resource allocation data adjustment function is determined by the following formula :
[0233] ;
[0234] Get the center value of the comfortable temperature range corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment ;
[0235] Based on the center value of the comfortable temperature range corresponding to the air conditioning equipment , the current temperature corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment , the temperature regulation function is determined by the following formula :
[0236] ;
[0237] Adjusting functions based on the resource allocation data and the temperature regulation function The relationship function corresponding to the air conditioning equipment is determined by the following formula :
[0238]
[0239] in, represents the preset third weight coefficient, represents a preset fourth weight coefficient;
[0240] Get the rated power of the air conditioner and the minimum power of the air conditioning equipment ;
[0241] Based on the relationship function , the rated power of the air conditioning equipment and the minimum power of the air conditioning equipment The power increase is determined by the following formula :
[0242] ;
[0243] Get the real-time power of the air conditioning equipment , based on the power increment and the minimum power of the air conditioning equipment Determined by the following formula The power control amount of the air conditioning equipment at the moment ;
[0244] ;
[0245] Obtain the power required to be adjusted for the landscape lighting device , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment ;
[0246] Based on the power required to be adjusted for the landscape lighting equipment , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment , determined by the following formula The current load difference corresponding to the landscape lighting equipment at the moment :
[0247]
[0248] Get Output power of the landscape lighting equipment at the moment ;
[0249] Based on The current load difference corresponding to the landscape lighting equipment at the moment ,exist The current load difference corresponding to the landscape lighting equipment at the moment , the power regulation amount of the landscape lighting equipment is determined by the following formula :
[0250]
[0251] in, Indicates the preset attenuation factor;
[0252] Get The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge rate of the energy storage device ;
[0253] based on The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge power of the energy storage device , the power regulation amount of the energy storage device is determined by the following formula :
[0254] ;
[0255] Get Output power of the air conditioning equipment at the time and Output power of the energy storage device at the moment ;
[0256] based on The power control amount of the air conditioning equipment at the moment , Output power of the air conditioning equipment at the time ,based on The power control amount of the landscape lighting equipment at the moment , Output power of the landscape lighting equipment at the moment ,based on The power control amount of the energy storage device at the moment and Output power of the energy storage device at the moment The overall power control amount is determined by the following formula :
[0257] .
[0258] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.
[0259] The device of the above embodiment is used to implement the corresponding virtual power plant resource control method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.
[0260] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the virtual power plant resource control method described in any of the above embodiments is implemented.
[0261] Figure 3 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 301, a memory 302, an input / output interface 303, a communication interface 304, and a bus 305. The processor 301, the memory 302, the input / output interface 303, and the communication interface 304 are connected to each other in communication within the device through the bus 305.
[0262] The processor 301 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.
[0263] The memory 302 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 302 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 302 and are called and executed by the processor 301.
[0264] The input / output interface 303 is used to connect the input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.
[0265] The communication interface 304 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0266] The bus 305 comprises a pathway for transmitting information between various components of the device (eg, the processor 301 , the memory 302 , the input / output interface 303 , and the communication interface 304 ).
[0267] It should be noted that, although the above device only shows the processor 301, the memory 302, the input / output interface 303, the communication interface 304 and the bus 305, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.
[0268] The electronic device of the above-mentioned embodiment is used to implement the corresponding virtual power plant resource control method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.
[0269] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the virtual power plant resource control method described in any of the above embodiments.
[0270] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.
[0271] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the virtual power plant resource control method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0272] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.
[0273] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power / ground connections to the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device may be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application are to be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0274] Although the present application has been described in conjunction with specific embodiments of the present application, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.
[0275] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.
Claims
1. A virtual power plant resource control method, It is characterized in that include: Acquire historical power resource data of the connected virtual power plant at various historical moments, and obtain predicted power resource configuration data based on the historical power resource data using a pre-trained power generation and consumption prediction model; Obtaining the actual total amount of resource allocation within the resource allocation cycle, and determining the theoretical online power consumption for each day based on the predicted power resource allocation data and the actual total amount of resource allocation within the resource allocation cycle; Determine the theoretical grid-connected power based on the predicted power resource configuration data and the theoretical grid-connected power of each day; Acquire the real-time power consumption data of the power equipment and the actual power generation power of the distributed photovoltaic field station connected to the virtual power plant, and use the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic field station to determine the resource regulation strategy of the power equipment, and adjust the power resource data of the power equipment according to the resource regulation strategy; The electric power equipment includes electric power equipment and energy storage equipment; The method of determining a resource control strategy for power equipment by using the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic station includes: In response to the sum of the real-time power consumption data and the theoretical grid-connected power being less than or equal to the actual power generation power of the distributed photovoltaic station, determining that the resource regulation strategy of the power equipment is to charge the energy storage device; In response to the sum of the real-time power consumption data and the theoretical grid-connected power being greater than the actual power generation power of the distributed photovoltaic field station, and the theoretical grid-connected power being greater than the actual power generation power of the distributed photovoltaic field station, the resource control strategy of the power equipment is determined to be the overall power control amount corresponding to the power consumption equipment and the energy storage equipment; The electrical equipment includes air conditioning equipment and landscape lighting equipment; The determining of the overall power control amount corresponding to the power-consuming device and the energy storage device includes: Obtain resource allocation data corresponding to the air conditioning equipment and the preset maximum resource allocation data threshold ; Based on the resource allocation data corresponding to the air conditioning equipment and the preset maximum resource allocation data threshold , the resource allocation data adjustment function is determined by the following formula : ; Get the center value of the comfortable temperature range corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment ; Based on the center value of the comfortable temperature range corresponding to the air conditioning equipment , the current temperature corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment , the temperature regulation function is determined by the following formula : ; Adjusting functions based on the resource allocation data and the temperature regulation function The relationship function corresponding to the air conditioning equipment is determined by the following formula : in, represents the preset third weight coefficient, represents a preset fourth weight coefficient; Get the rated power of the air conditioner and the minimum power of the air conditioning equipment ; Based on the relationship function , the rated power of the air conditioning equipment and the minimum power of the air conditioning equipment The power increase is determined by the following formula : ; Get the real-time power of the air conditioning equipment , based on the power increment and the minimum power of the air conditioning equipment Determined by the following formula The power control amount of the air conditioning equipment at the moment ; ; Obtain the power required to be adjusted for the landscape lighting device , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment ; Based on the power required to be adjusted for the landscape lighting equipment , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment , determined by the following formula The current load difference corresponding to the landscape lighting equipment at the moment : Get Output power of the landscape lighting equipment at the moment ; Based on The current load difference corresponding to the landscape lighting equipment at the moment ,exist The current load difference corresponding to the landscape lighting equipment at the moment , the power regulation amount of the landscape lighting equipment is determined by the following formula : in, Indicates the preset attenuation factor; Get The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge power of the energy storage device ; based on The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge rate of the energy storage device , the power regulation amount of the energy storage device is determined by the following formula : ; Get Output power of the air conditioning equipment at the time and Output power of the energy storage device at the moment ; based on The power control amount of the air conditioning equipment at the moment , Output power of the air conditioning equipment at the time ,based on The power control amount of the landscape lighting equipment at the moment , Output power of the landscape lighting equipment at the moment ,based on The power control amount of the energy storage device at the moment and Output power of the energy storage device at the moment The overall power control amount is determined by the following formula : 。 2. The method according to claim 1, It is characterized in that The obtaining of historical power resource data of the virtual power plant at each historical moment includes: Obtaining initial historical power resource data of the connected virtual power plant at each historical moment, and determining an average value of the initial historical power resource data at each historical moment; The size of the moving window based on the preset , initial historical power resource data at each historical moment and the average , the moving standard deviation is obtained by the following formula : in, Indicates the order of historical moments, Indicates the total duration of historical moments; Using the moving standard deviation and the preset moving standard deviation speed Perform product processing to obtain the noise threshold ; At every historical moment Initial historical power resource data Respectively with the noise threshold Make a comparison; In response to the initial historical power resource data Less than or equal to the noise threshold , determine the initial historical power resource data It is noise data, and the initial historical power resource data is obtained Corresponding preset historical moment Weight , based on the initial historical power resource data and the weights The weighted moving average is determined by the following formula : in, Indicates the order of historical moments, Indicates the total duration of historical moments. Represents the size of the preset moving window; replaces the initial historical power resource data with the weighted moving average value as the historical power resource data; or, In response to the initial historical power resource data Greater than the noise threshold , determine the initial historical power resource data It is not noise data and does not perform the same as the initial historical power resource data. The process of determining the corresponding weighted moving average.
3. The method according to claim 1, It is characterized in that The historical power resource data includes training resource data and forecast resource data; The power generation and consumption prediction model is trained through the following process: Acquire actual power resource configuration data corresponding to the training resource data and construct an initial model; Inputting the training resource data into the initial model, and outputting the training predicted power resource configuration data through the initial model; Determine a loss function according to the actual power resource configuration data and the training predicted power resource configuration data; The initial model is trained and adjusted according to the minimization result obtained in the process of minimizing the loss function to obtain the trained and adjusted initial model, and based on the actual power resource configuration data , and predictive power resource allocation data The indicator corresponding to the initial model after training and adjustment is determined by the following formula : in, Indicates actual power resource configuration data The number of groups of corresponding training resource data, Indicates Group training resource data, Indicates the number of data in each group of training resource data, Indicates the order of historical moments, Indicates the preset weight factor; In response to the indicator being less than a preset indicator threshold, continuously adjusting the trained and adjusted initial model; or, In response to the indicator being greater than or equal to a preset indicator threshold, the trained and adjusted initial model is used as a power generation and consumption prediction model.
4. The method according to claim 1, It is characterized in that The predicted power resource configuration data includes: power generation prediction data and power consumption prediction data; The determining of the theoretical online power consumption on each day based on the predicted power resource configuration data and the actual total amount of resource configuration within the resource configuration cycle includes: Based on the power generation prediction data and the power consumption forecast data The following formula is used to determine each historical moment Internet power : in, represents the preset first weight coefficient, represents the preset second weight coefficient, Indicates the order of historical moments, Indicates the historical moment The resource consumption of Internet requests is Indicates the consumption of green electricity environmental resources, Indicates the historical moment Time-sharing resource consumption; Using the various historical moments Internet power The total amount of predicted resource allocation within the resource allocation cycle is determined by the following formula : in, Indicates the number of days of the resource configuration cycle. Indicates the first sky, Indicates The total length of the historical moments of the day; Using the power generation prediction data and The total duration of the historical moments of the day is multiplied by the product to obtain Forecasted power generation for the day ; Based on Forecasted power generation for the day , the total amount of resource allocation predicted within the resource allocation cycle , the actual total amount of resource allocation during the resource allocation cycle The theoretical daily Internet access power is determined by the following formula : 。 5. The method according to claim 1, It is characterized in that The predicted power resource configuration data includes: power generation prediction data; The determining of the theoretical online power based on the predicted power resource configuration data and the theoretical online power of each day includes: Based on the predicted power resource configuration data The theoretical daily Internet access power consumption The theoretical grid power is determined by the following formula : in, Indicates the order of historical moments, Represents the total number of historical moments.
6. A virtual power plant resource control device, It is characterized in that include: A prediction module is configured to obtain historical power resource data of the connected virtual power plant at various historical moments, and obtain predicted power resource configuration data based on the historical power resource data using a pre-trained power generation and consumption prediction model; A module for determining theoretical online power consumption on each day is configured to obtain the actual total amount of resource configuration within the resource configuration cycle, and determine the theoretical online power consumption on each day based on the predicted power resource configuration data and the actual total amount of resource configuration within the resource configuration cycle; A theoretical grid-connected power determination module is configured to determine the theoretical grid-connected power based on the predicted power resource configuration data and the theoretical grid-connected power of each day; The regulation module is configured to obtain real-time power consumption data of the power equipment and the actual power generation power of the distributed photovoltaic field station connected to the virtual power plant, and use the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic field station to determine the resource regulation strategy of the power equipment, and regulate the power resource data of the power equipment according to the resource regulation strategy; the power equipment includes power equipment and energy storage equipment; the resource regulation strategy of the power equipment is determined by using the sum of the real-time power consumption data and the theoretical grid-connected power and the actual power generation power of the distributed photovoltaic field station, and is used to respond to the real-time power consumption data and the sum of the theoretical grid-connected power. If the actual power generation power of the distributed photovoltaic station is less than or equal to the actual power generation power of the distributed photovoltaic station, the resource control strategy of the power equipment is determined to be charging the energy storage device; in response to the sum of the real-time power consumption data and the theoretical grid-connected power being greater than the actual power generation power of the distributed photovoltaic station, and the theoretical grid-connected power is greater than the actual power generation power of the distributed photovoltaic station, the resource control strategy of the power equipment is determined to be determining the overall power control amount corresponding to the power-consuming equipment and the energy storage device; the power equipment includes air-conditioning equipment and landscape lighting equipment; the overall power control amount corresponding to the power-consuming equipment and the energy storage device is determined to obtain resource allocation data corresponding to the air-conditioning equipment and the preset maximum resource allocation data threshold ; Based on the resource allocation data corresponding to the air conditioning equipment and the preset maximum resource allocation data threshold , the resource allocation data adjustment function is determined by the following formula : ; Get the center value of the comfortable temperature range corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment ; Based on the center value of the comfortable temperature range corresponding to the air conditioning equipment , the current temperature corresponding to the air conditioning equipment , the comfortable temperature variation range corresponding to the air conditioning equipment , the temperature regulation function is determined by the following formula : ; Adjusting functions based on the resource allocation data and the temperature regulation function The relationship function corresponding to the air conditioning equipment is determined by the following formula : in, represents the preset third weight coefficient, represents a preset fourth weight coefficient; Get the rated power of the air conditioner and the minimum power of the air conditioning equipment ; Based on the relationship function , the rated power of the air conditioning equipment and the minimum power of the air conditioning equipment The power increase is determined by the following formula : ; Get the real-time power of the air conditioning equipment , based on the power increment and the minimum power of the air conditioning equipment Determined by the following formula The power control amount of the air conditioning equipment at the moment ; ; Obtain the power required to be adjusted for the landscape lighting device , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment ; Based on the power required to be adjusted for the landscape lighting equipment , Output power of the landscape lighting equipment at the moment and the minimum power limit of the landscape lighting equipment , determined by the following formula The current load difference corresponding to the landscape lighting equipment at the moment : Get Output power of the landscape lighting equipment at the moment ; Based on The current load difference corresponding to the landscape lighting equipment at the moment ,exist The current load difference corresponding to the landscape lighting equipment at the moment , the power regulation amount of the landscape lighting equipment is determined by the following formula : in, Indicates the preset attenuation factor; Get The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge power of the energy storage device ; based on The current load difference of the energy storage device at the time , The real-time power of the energy storage device at the moment , the discharge efficiency of the energy storage device and the maximum discharge rate of the energy storage device , the power regulation amount of the energy storage device is determined by the following formula : ; Get Output power of the air conditioning equipment at the time and Output power of the energy storage device at the moment ; based on The power control amount of the air conditioning equipment at the moment , Output power of the air conditioning equipment at the time ,based on The power control amount of the landscape lighting equipment at the moment , Output power of the landscape lighting equipment at the moment ,based on The power control amount of the energy storage device at the moment and Output power of the energy storage device at the moment The overall power control amount is determined by the following formula : 。 7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, It is characterized in that When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.
8. A non-transitory computer-readable storage medium storing computer instructions, It is characterized in that The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Electric power peak regulation method, device and equipment and storage medium
CN115864460A
Multi-energy virtual power plant peak regulation optimization method and system
CN116632938A
Virtual power plant resource optimization scheduling method, apparatus and device, and storage medium
CN117077974A
Method and device for controlling optical storage direct-flexible micro-grid based on AI (Artificial Intelligence) prediction
CN117810974A
Virtual aggregation system and method for regional energy source complex
WO2021244000A1
