Load control method, device, equipment, storage medium and program product based on source-grid-load-storage

Abstract

The present invention relates to the technical field of power regulation, and discloses a load regulation method, device, equipment, storage medium and program product based on source-grid-load-storage, the method comprising: obtaining historical load data of a region to be regulated, the historical load data comprising historical power load data and historical power generation load data of the region to be regulated; based on the historical power load data, predicting power load prediction data of the region to be regulated within a preset time in the future; based on the historical power generation load data, predicting power generation load prediction data of the region to be regulated within a preset time in the future; based on the power load prediction data and the power generation load prediction data, determining load data to be called within a preset time in the future in the region to be regulated and determining the calling power and calling time period of the load data to be called. The present invention can make the most of the power resources within the region to be regulated, reduce the power cost, and avoid the phenomenon of wasting power resources.

Description

Technical Field

[0001] The present invention relates to the field of power control technology, and in particular to a load control method, device, equipment, storage medium and program product based on source-grid-load-storage. Background Art

[0002] With the continuous development of power systems, power load control technology has become an important means of power system operation and management. It is mainly used to manage and adjust the load of power systems to ensure the stable operation of power systems and meet user needs.

[0003] However, current power load control technologies are usually regulated from a global perspective of the national or regional power grid. Operators of the national or regional power grid will use various load control technologies to balance supply and demand based on actual conditions to ensure the stable operation of the power system.

[0004] For manufacturing enterprises, clusters or parks that have their own power generation systems, if they still use traditional global power load control technology, they will not be able to maximize the use of power resources within the cluster or park, resulting in waste of power resources and increased electricity costs. Summary of the Invention

[0005] In view of this, the present invention provides a load control method, device, equipment, storage medium and program product based on source-grid-load-storage to solve the problem that the power load control technology in the prior art is not suitable for local control, resulting in increased electricity costs.

[0006] In a first aspect, the present invention provides a load control method based on source-grid-load-storage, the method comprising:

[0007] Obtain historical load data and tiered electricity price data for the area to be regulated, where the historical load data includes historical electricity load data and historical power generation load data for the area to be regulated;

[0008] Based on historical electricity load data, predict the electricity load forecast data of the area to be regulated within a preset time in the future;

[0009] Based on historical power generation load data, predict the power generation load forecast data of the area to be regulated within a preset time in the future;

[0010] Based on the electricity load forecast data and the power generation load forecast data, determine the load data to be called in the area to be regulated within a preset time in the future, where the load data to be called is the load that needs to be called from outside the area to be regulated;

[0011] Based on the tiered electricity price data, the capacity of the energy storage equipment in the area to be regulated, the load data to be called, and a pre-established objective function, the call power and call time period of the load data to be called are determined so that the electricity fee in the area to be regulated is minimized. The objective function is a relationship function related to the discharge power of the energy storage equipment, the charging power of the energy storage equipment, the power generation of the power generation equipment in the area to be regulated, the load data to be called, the tiered electricity price data, and the call time period.

[0012] Based on the forecast results, appropriate load control decisions can be made. Based on these load control decisions, appropriate control measures can be implemented through smart energy meters, demand response systems, and other means. For example, during peak photovoltaic power generation periods, energy storage devices can be used to discharge electricity and implement power restrictions to reduce grid load. During low photovoltaic power generation periods, energy storage devices can be charged and demand response measures can be implemented to increase grid load. Furthermore, during the implementation of load control, continuous feedback and adjustment of system decisions are required. The forecast results and control measures can be revised and optimized based on actual conditions to achieve better load control results. This maximizes the utilization of power resources within the controlled area, reduces electricity costs, and prevents waste of power resources.

[0013] In some optional embodiments, the historical electricity load data includes one-to-one corresponding collected load data collected by each electric energy meter in the area to be regulated. Based on the historical electricity load data, the electricity load forecast data of the area to be regulated within a preset future time is predicted, including:

[0014] Determine the sliding window size;

[0015] Starting from the start time of each collected load data, the collected load data is divided according to the sliding window size to obtain the sliding window data arranged according to the time series;

[0016] Add up the sliding window data of the same time period in all collected load data to obtain the sum of the load data corresponding to each time period;

[0017] Divide the total load data by the sliding window size to determine the average power value corresponding to each time period;

[0018] Determine the electrical equipment corresponding to the collected load data;

[0019] The average power value is matched with the active power of the corresponding electrical equipment according to the time period to obtain energy consumption power data;

[0020] The energy consumption power data is used as training data, and the future preset time is input into the pre-established power load forecasting model to output the predicted average power value for each time period within the future preset time, and the predicted average power value is used as the power load forecast data.

[0021] In this embodiment, by using historical electricity load data and sliding window and time series analysis for data processing, the accuracy of the training data can be improved, and future electricity load conditions can be predicted more accurately, which is conducive to planning and scheduling power resources in the area to be regulated and improving the utilization rate of power resources in the area to be regulated.

[0022] In an optional embodiment, the historical power generation load data includes a collection time and a power generation load corresponding to the collection time. Based on the historical power generation load data, power generation load forecast data of the area to be regulated within a preset time in the future is predicted, including:

[0023] Determine the historical weather information corresponding to the collection time;

[0024] Determine the forecast weather information corresponding to a preset time in the future;

[0025] Historical weather information and historical power generation load data are used as training data, and future preset time and predicted weather information are input into a pre-established power generation load forecasting model to output the average power generation within the future preset time, and the average power generation is used as the power generation load forecast data.

[0026] Incorporating weather information into forecasting models can improve forecast accuracy.

[0027] In an optional embodiment, based on the power load forecast data and the power generation load forecast data, determining the load data to be called in the area to be regulated within a preset future time includes:

[0028] The predicted average power value in the electricity load forecast data is subtracted from the power generation load forecast data to determine the load data to be called in the area to be regulated within a preset time in the future.

[0029] This can maximize the use of electricity resources within the area to be regulated, reduce electricity costs, and avoid waste of electricity resources.

[0030] In an optional embodiment, before determining the load data to be called for the area to be regulated within a preset future time based on the power load forecast data and the power generation load forecast data, the method further includes:

[0031] Determining the minimum charge and discharge power of the energy storage device based on the power load forecast data and the power generation load forecast data; wherein the energy storage device is used to store the electric energy generated by the power generation equipment in the area to be regulated and to provide electric energy to the electric equipment in the area to be regulated;

[0032] Determining a maximum charge and discharge duration based on the energy storage device capacity and the minimum charge and discharge power;

[0033] The load data to be called for the area to be regulated within the future preset time is determined according to the minimum charge and discharge power, the maximum charge and discharge time, the power load forecast data, and the power generation load forecast data.

[0034] Energy storage devices can rapidly adjust grid loads through rapid charge and discharge control. They can optimize system configuration and make decisions based on the grid's operating status, user electricity demand, and the performance of various distributed energy resources, maximizing the use of power resources. This also maximizes the use of power resources within the area being regulated, reducing electricity costs without wasting power.

[0035] The maximum charge and discharge time is determined based on the capacity of the energy storage device and the minimum charge and discharge power. This can more effectively improve the energy utilization rate and thus save energy to a certain extent.

[0036] In an optional implementation, the objective function is:

[0037]

[0038] in, is the discharge capacity of the energy storage device, P1 is the preset electricity price, is the percentage of the energy storage device's discharge capacity in the i-th period, The charging capacity of the energy storage device, is the percentage of the power generation of the power generation equipment to the capacity of the energy storage equipment in the i-th period, The amount of electricity generated by the power generation equipment, is the load data to be called, P(i) is the unit price of the i-th period in the ladder electricity price data, α and β are weight coefficients, i is a variable, and n is the total number of periods.

[0039] In a second aspect, the present invention provides a load control device based on source-grid-load-storage, comprising:

[0040] An acquisition module is used to obtain historical load data and tiered electricity price data of the area to be regulated, where the historical load data includes historical electricity load data and historical power generation load data of the area to be regulated;

[0041] The electricity consumption data prediction module is used to predict the electricity consumption load forecast data of the area to be regulated within a preset time in the future based on historical electricity consumption load data;

[0042] The power generation data prediction module is used to predict the power generation load forecast data of the area to be regulated within a preset time in the future based on historical power generation load data;

[0043] A determination module is used to determine the load data to be called in the area to be regulated within a preset time in the future based on the power load forecast data and the power generation load forecast data, where the load data to be called is the load that needs to be called from outside the area to be regulated;

[0044] An optimization module is configured to determine, based on the tiered electricity price data, the capacity of the energy storage device in the area to be regulated, the load data to be called, and a pre-established objective function, the calling power and calling time period of the load data to be called, so that the electricity fee in the area to be regulated is minimized, wherein the objective function is a relationship function related to the discharged power of the energy storage device, the charged power of the energy storage device, the generated power of the power generation equipment in the area to be regulated, the load data to be called, the tiered electricity price data, and the calling time period.

[0045] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to thereby execute the load control method based on source-grid-load-storage according to the first aspect or any corresponding embodiment thereof.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, which are used to enable a computer to execute the load control method based on source-grid-load-storage according to the above-mentioned first aspect or any corresponding embodiment thereof.

[0047] In a fifth aspect, the present invention provides a computer program product comprising computer instructions, the computer instructions being used to enable a computer to execute the load control method based on source-grid-load-storage according to the first aspect or any corresponding embodiment thereof.

[0048] It should be noted that the source-grid-load-storage-based load control device, computer device, and computer-readable storage medium provided by the present invention correspond to the aforementioned source-grid-load-storage-based load control method. Therefore, for the beneficial effects of the source-grid-load-storage-based load control device, computer device, and computer-readable storage medium, please refer to the description of the corresponding beneficial effects of the source-grid-load-storage-based load control method above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 1 is a flow chart of a load control method based on source-grid-load-storage according to an embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of an average power curve according to an embodiment of the present invention;

[0052] Figure 3 2 is a structural block diagram of a load control device based on source, grid, load and storage according to an embodiment of the present invention;

[0053] Figure 4 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0055] Source, grid, load and storage integrates all aspects of the power system, including power generation, transmission, distribution and consumption, to achieve unified management and optimized scheduling of power resources.

[0056] Traditional load regulation technologies involve the management and control of all aspects of power generation, transmission, and distribution from a dispatching center. For example, during peak demand periods, the dispatching center can increase power supply by adjusting the operating status of power plants, increasing the capacity of transmission lines, and activating energy storage devices. During low demand periods, grid load can be reduced by adjusting power plant output, controlling the load on transmission lines, and utilizing energy storage devices for charging. This can effectively improve the efficiency and reliability of the power system, address various emergencies and load fluctuations, and ensure safe and stable operation. However, traditional load regulation technologies typically focus on global control and are unable to adapt to localized control based on the generation and consumption of electricity in a specific area.

[0057] Therefore, the present invention introduces load control technology into the power generation and energy storage links, utilizes the integrated operation of the four modules of "source, grid, load and storage", adjusts the power consumption of power generation equipment and load users, and balances local power supply and demand according to changes in power demand. On the premise of ensuring the stable operation of the power system, it fully utilizes the power resources in the local area.

[0058] According to an embodiment of the present invention, an embodiment of a load regulation method based on source-grid-load-storage is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0059] In this embodiment, a load control method based on source, grid, load and storage is provided, which can be executed by devices such as servers, terminals, and mobile terminals. Figure 1 Flowchart of the load control method based on source, grid, load and storage according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0060] Step S101: Acquire historical load data and tiered electricity price data of the area to be regulated, where the historical load data includes historical electricity load data and historical power generation load data of the area to be regulated.

[0061] In this embodiment, the production park is taken as an example of the area to be regulated. Generally, the production park includes many areas such as production workshops, office buildings, and dormitory buildings. Each area will be equipped with a total electricity meter. In each area, multiple subordinate electricity meters will be configured according to the load conditions. Each electricity meter is used to collect load data for the corresponding area. During the data collection stage, the network service interface can be used to collect the metering data of each electricity meter. It can also be used to establish data docking with the production management system to move the equipment production data in the production management system to the asset database of the power system. All communication devices are connected through the Internet of Things platform, and all data are collected into the data collection database. The data is classified and sorted according to different equipment types and related protocols such as 645. Among them, equipment production data includes equipment factory data, such as equipment model parameters, power parameters, built-in parameters, etc., and equipment production data also includes production data, etc.

[0062] The load data collected by each electric energy meter and the production data of the electric equipment in the area collected by each electric energy meter can be used as historical load data.

[0063] In addition, general production parks will also be equipped with power generation equipment such as photovoltaic panels for power generation, and the generated electricity will be stored for use in the production park. The electricity generated by the photovoltaic panels every day can be used as historical power generation load data.

[0064] Next, data preprocessing can be performed: cleaning, organizing, and standardizing the collected field data. This includes removing outliers, filling missing values, and removing noise to obtain relatively complete and accurate data. Outliers can be identified and removed using statistical methods, such as the 3σ principle or robust statistics. Missing values ​​can be filled using interpolation methods, such as linear or polynomial interpolation. Finally, the data is normalized to unify data of different dimensions and scales to a single standard, facilitating subsequent feature extraction and model training.

[0065] Take the tiered electricity price in a certain area as an example, as shown in Table 1:

[0066] Table 1

[0067]

[0068] Step S102 , based on the historical power load data, predict the power load forecast data of the area to be regulated within a preset time in the future, that is, the power load required by the production park in the next hour or day can be predicted.

[0069] Step S103 predicts the power generation load for the area to be regulated within a preset timeframe based on historical power generation load data. This means that the power generation load that the production park's power generation equipment can generate within the next hour or day can be predicted. This can be achieved by using the Photovoltaic Library for Incidence (PVLib) in the Python library, a library for modeling and predicting solar photovoltaic system performance, to accurately predict photovoltaic power generation based on information such as the production park's weather conditions, the location of the photovoltaic panels, and the park's power grid structure.

[0070] Step S104, based on the power load forecast data and the power generation load forecast data, determine the load data to be called in the area to be regulated within a preset time in the future, where the load data to be called is the load that needs to be called from outside the area to be regulated.

[0071] In some optional implementations, the predicted average power value in the power load forecast data can be subtracted from the power load forecast data to determine the load data to be called up within a preset future timeframe in the area to be regulated. The load data to be called up can be the amount of electricity to be called up from the utility grid. In other words, the power load forecast data can be offset from the power load forecast data to determine the load data to be called up. Based on the forecast results, appropriate load regulation decisions can be made. This maximizes the utilization of power resources within the area to be regulated, reduces electricity costs, and prevents waste of power resources.

[0072] Step S105: Based on the tiered electricity price data, the capacity of the energy storage equipment in the area to be regulated, the load data to be called, and a pre-established objective function, the call power and call time period of the load data to be called are determined so that the electricity fee in the area to be regulated is minimized. The objective function is a relationship function related to the discharge power of the energy storage equipment, the charge power of the energy storage equipment, the power generation of the power generation equipment in the area to be regulated, the load data to be called, the tiered electricity price data, and the call time period.

[0073] Specifically, the optimal charging and discharging power and charging and discharging time of the energy storage device can be determined through an optimization function, that is, an objective function, using iterative calculations.

[0074] In some optional implementations, the objective function is:

[0075]

[0076] in, is the discharge capacity of the energy storage device, P1 is the preset electricity price, is the percentage of the energy storage device's discharge capacity in the i-th period, The charging capacity of the energy storage device, is the percentage of the power generation of the power generation equipment to the capacity of the energy storage equipment in the i-th period, The amount of electricity generated by the power generation equipment, is the load data to be called, P(i) is the unit price of the i-th period in the ladder electricity price data, α and β are weight coefficients, i is a variable, and n is the total number of periods.

[0077] Specifically, a preset time, such as a day, can be divided into several time periods n in advance, and the time period unit price corresponding to each time period can be determined. Then, these time periods can be traversed in sequence. The objective function can be solved by methods such as gradient descent and genetic algorithms. Through iterative calculation, the optimal energy storage device charge and discharge power and charge and discharge time period can be found to minimize the electricity cost of the area to be regulated. In general, the electricity cost is the product of the electricity price and the power, and the power is the product of the power and the duration, that is, the power can be reflected by the power. After determining the charge and discharge power of the device and the charge and discharge time period, the charge and discharge power can be determined, and the determined charge and discharge time period can be used as the call period in this embodiment, that is, the time period for calling power from the mains.

[0078] The objective function's P1 can be any utility price, such as the utility peak, to adapt the electricity bill calculation. The energy storage device's discharge capacity, the energy storage device's charge capacity, the power generation equipment's generation capacity, and the time period unit price are all decision variables. Through continuous iteration, the objective function's minimum value, i.e., the minimum electricity bill, is ultimately determined.

[0079] Let's take a simple example. For example, if the predicted power load for the next day is 500 kW and the predicted power generation load for the next day is 400 kW, then 100 kW of load will need to be transferred from an external source, meaning that 100 kW of load can be supplied from the utility grid. Furthermore, the target power and time period for the load to be transferred can be determined based on the objective function. For example, during the low-cost electricity period (11:00 PM - 8:00 AM) the previous night, 100 kW of load can be transferred from the utility grid at 20 kW using an energy storage device and stored in a storage device for future use, thereby reducing electricity costs. If the predicted power load for the next day is 500 kW and the predicted power generation load is 600 kW, the load to be transferred is 0, eliminating the need to transfer load from outside the control area, and the remaining load is stored.

[0080] Based on the forecast results, appropriate load control decisions can be made. Based on these load control decisions, appropriate control measures can be implemented through smart energy meters, demand response systems, and other means. For example, during peak photovoltaic power generation periods, energy storage devices can be used to discharge electricity and implement power restrictions to reduce grid load. During low photovoltaic power generation periods, energy storage devices can be charged and demand response measures can be implemented to increase grid load. Furthermore, during the implementation of load control, continuous feedback and adjustment of system decisions are required. The forecast results and control measures can be revised and optimized based on actual conditions to achieve better load control results. This maximizes the utilization of power resources within the controlled area, reduces electricity costs, and prevents waste of power resources.

[0081] In some optional embodiments, the historical electricity load data includes one-to-one corresponding collected load data collected by each electric energy meter in the area to be regulated. The above step S102, i.e., predicting electricity load forecast data of the area to be regulated within a preset future time based on the historical electricity load data, includes:

[0082] Step S1021: Determine the sliding window size. An appropriate sliding window size may be selected, for example, a sliding window size of 1 minute.

[0083] Step S1022: Starting from the start time of each load data collection, the collected load data is divided according to the sliding window size to obtain sliding window data arranged according to the time series. In other words, starting from the start time of the load data collection, the data of the sliding window size can be sequentially taken for processing.

[0084] In step S1023, the sliding window data of the same time period in all collected load data are added together to obtain the total load data corresponding to each time period. In other words, for each sliding window, the data of the sliding windows of the same time period can be added together to obtain the total load data of the sliding window.

[0085] Step S1024 : Divide the total load data by the sliding window size to determine the average power value corresponding to each time period, that is, determine the average power value corresponding to each sliding window.

[0086] Specifically, for the load data collected by each electric energy meter, assume that the power consumption is collected once every minute, recorded as E(t), where t represents time (minutes). The sliding window method is used to calculate the average power, and the sliding window size is T minutes. Let P(t,T) represent the average power within T minutes starting from time t. Then the average power of the sliding window corresponding to the same time period is:

[0087]

[0088] in, Indicates the power consumption collected at time point m (minutes).

[0089] Reference Figure 2 As shown in FIG, an average power curve is fitted according to the average power values ​​corresponding to each time period determined one by one.

[0090] Step S1025: Determine the electrical equipment corresponding to the collected load data. As shown above, each energy meter is used to collect load data in a fixed area, and thus can also determine the electrical equipment used in the area.

[0091] Step S1026: The average power value is matched with the active power of the corresponding electrical equipment in a one-to-one manner according to the time period to obtain energy consumption power data.

[0092] The average power value of each time period can be aligned with the active power of the electrical equipment corresponding to the time period. This allows the average power value to be associated with the electrical equipment, which is more helpful in identifying the energy consumption of the equipment.

[0093] In step S1027, the energy consumption power data is used as training data, and the future preset time is input into a pre-established power load prediction model to output the predicted average power value for each time period within the future preset time, and the predicted average power value and the active power corresponding to the predicted electrical equipment are used as power load prediction data.

[0094] The average power value within the sliding window size T and the active power of N electrical devices are aggregated and aligned according to the time scale. The above aggregated data is used as the input variable and the power load forecast curve can be obtained through autonomous learning training model. :

[0095]

[0096] Among them, k is a variable.

[0097] Specifically, a suitable training model can be selected first. Since the current data is time series data, prediction models for time series data include deep learning models such as long short-term memory networks or gated recurrent units, and traditional machine learning models such as support vector machines or random forests. Training is then performed based on the selected model, where the model must be able to accept input features and output predicted load values. Furthermore, the output predicted load values ​​can be evaluated and verified, and the model parameters and structure can be adjusted based on the evaluation results. Once the model performance meets the requirements, it can be deployed in real-world applications for load forecasting. At this point, a preset future time can be input into the established load forecasting model to output predicted load data for the preset future time.

[0098] In this embodiment, by using historical electricity load data and sliding window and time series analysis for data processing, the accuracy of the training data can be improved, and future electricity load conditions can be predicted more accurately, which is conducive to planning and scheduling power resources in the area to be regulated and improving the utilization rate of power resources in the area to be regulated.

[0099] In some optional embodiments, the historical power generation load data includes a collection time and a power generation load corresponding to the collection time. Step S103, i.e., predicting power generation load forecast data of the area to be regulated within a preset future time based on the historical power generation load data, includes:

[0100] Step S1031, determining the historical weather information corresponding to the collection time;

[0101] Step S1032, determining the forecast weather information corresponding to a preset time in the future;

[0102] In step S1033, historical weather information and historical power generation load data are used as training data, and future preset time and predicted weather information are input into a pre-established power generation load prediction model to output the average power generation within the future preset time, and the average power generation power is used as the power generation load prediction data.

[0103] Because weather significantly impacts photovoltaic power generation load, incorporating weather information into forecasting models can improve forecast accuracy. Furthermore, when forecasting power generation load data, in addition to considering weather conditions in the area to be regulated, information such as the location of photovoltaic panel installations and the park's power grid structure can also be integrated to achieve accurate predictions of photovoltaic power generation.

[0104] In some optional implementations, before determining the load data to be called for the area to be regulated within a preset future time based on the power load forecast data and the power generation load forecast data, the method further includes:

[0105] Determining the minimum charge and discharge power of the energy storage device based on the power load forecast data and the power generation load forecast data; wherein the energy storage device is used to store the power generated by the power generation equipment in the area to be regulated and to provide power to the power consumption equipment in the area to be regulated;

[0106] Determine the maximum charge and discharge time based on the capacity of the energy storage device and the minimum charge and discharge power;

[0107] The load data to be called in the area to be regulated within a preset time in the future is determined based on the minimum charge and discharge power, maximum charge and discharge time, power load forecast data and power generation load forecast data.

[0108] Energy storage devices can rapidly adjust grid loads through rapid charge and discharge control. They can optimize system configuration and make decisions based on the grid's operating status, user electricity demand, and the performance of various distributed energy resources, maximizing the utilization of power resources. During peak periods of power demand, energy storage devices can rapidly discharge to increase the grid's supply capacity and balance the load. During periods of low demand, energy storage devices can rapidly charge to store excess energy and reduce grid load. This maximizes the utilization of power resources within the area being regulated, reduces electricity costs, and eliminates the waste of power resources.

[0109] The minimum charge and discharge power and maximum charge and discharge time are used together with the power load forecast data and the power generation load forecast data to comprehensively determine the load data to be called in the area to be regulated within the preset time in the future. This can more effectively improve the utilization rate of electricity and thus save electricity to a certain extent.

[0110] In this embodiment, a load control device based on source, grid, load and storage is also provided. The device is used to implement the above-mentioned embodiments and preferred implementation methods. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0111] This embodiment provides a load control device based on source, grid, load and storage, such as Figure 3 Shown, including:

[0112] An acquisition module 201 is configured to acquire historical load data and tiered electricity price data for the area to be regulated, wherein the historical load data includes historical electricity load data and historical power generation load data for the area to be regulated;

[0113] The power consumption data prediction module 202 is used to predict the power consumption load forecast data of the area to be regulated within a preset time in the future based on the historical power consumption load data;

[0114] The power generation data prediction module 203 is used to predict the power generation load forecast data of the area to be regulated within a preset time in the future based on the historical power generation load data;

[0115] Determination module 204 is configured to determine the load data to be called for the area to be regulated within a preset future time period based on the power load forecast data and the power generation load forecast data. The load data to be called refers to the load that needs to be called from outside the area to be regulated. The module is configured to subtract the power generation load forecast data from the predicted average power value in the power load forecast data to determine the load data to be called for the area to be regulated within a preset future time period.

[0116] Optimization module 205 is used to determine the call power and call time period of the load data to be called based on the tiered electricity price data, the capacity of the energy storage equipment in the area to be regulated, the load data to be called, and a pre-established objective function, so as to minimize the electricity cost of the area to be regulated, wherein the objective function is a relationship function related to the discharge power of the energy storage equipment, the charge power of the energy storage equipment, the power generation power of the power generation equipment in the area to be regulated, the load data to be called, the tiered electricity price data, and the call time period.

[0117] In some optional implementations, the electricity consumption data prediction module 202 includes:

[0118] A sliding window determining unit, configured to determine a sliding window size;

[0119] A partitioning unit is used to partition the collected load data according to the sliding window size starting from the start time of each collected load data, and obtain the sliding window data arranged according to the time series;

[0120] A calculation unit, configured to add up the sliding window data of the same time period in all collected load data to obtain the sum of the load data corresponding to each time period;

[0121] An average power value determination unit, configured to divide the total load data by the sliding window size to determine an average power value corresponding to each time period;

[0122] An electrical equipment determination unit, configured to determine the electrical equipment corresponding to the collected load data;

[0123] An electrical equipment determination unit, configured to make a one-to-one correspondence between the average power value and the active power of the corresponding electrical equipment according to the time period to obtain energy consumption power data;

[0124] The electricity consumption prediction unit is used to use energy consumption power data as training data and input the future preset time into a pre-established electricity load prediction model to output the predicted average power value for each time period within the future preset time, and use the predicted average power value as electricity load prediction data.

[0125] In some optional implementations, the power generation data prediction module 203 includes:

[0126] A historical weather information determination unit, configured to determine the historical weather information corresponding to the collection time;

[0127] A forecast weather information determination unit, configured to determine forecast weather information corresponding to a preset future time;

[0128] The power generation prediction unit is used to use historical weather information and historical power generation load data as training data, and input future preset time and predicted weather information into a pre-established power generation load prediction model to output the average power generation within the future preset time, and use the average power generation power as the power generation load prediction data.

[0129] In some optional embodiments, the device further comprises:

[0130] The energy storage device determination module is used to determine the minimum charge and discharge power of the energy storage device based on the power load forecast data and the power generation load forecast data; wherein the energy storage device is used to store the electric energy generated by the power generation equipment in the area to be regulated and to provide electric energy to the power consumption equipment in the area to be regulated; the maximum charge and discharge duration is determined according to the capacity of the energy storage device and the minimum charge and discharge power, and the load data to be called in the area to be regulated within a preset time in the future is determined according to the minimum charge and discharge power, the maximum charge and discharge duration, the power load forecast data and the power generation load forecast data.

[0131] The source-grid-load-storage based load regulation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0132] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0133] The embodiment of the present invention also provides a computer device having the above Figure 4 The load control device based on source, grid, load and storage is shown.

[0134] See also Figure 4 , Figure 4 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 4 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4A processor 10 is taken as an example.

[0135] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0136] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0137] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0138] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0139] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0140] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0141] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0142] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A load control method based on source, grid, load and storage. It is characterized in that The method comprises: Acquire historical load data and tiered electricity price data of the area to be regulated, wherein the historical load data includes historical electricity load data and historical power generation load data of the area to be regulated; Based on the historical power load data, predict the power load forecast data of the area to be regulated within a preset time in the future; Based on the historical power generation load data, predict the power generation load forecast data of the area to be regulated within the future preset time; Based on the power load forecast data and the power generation load forecast data, determine the load data to be called in the area to be regulated within the future preset time, the load data to be called is the load that needs to be called from outside the area to be regulated; Based on the stepped electricity price data, the capacity of the energy storage device in the area to be regulated, the load data to be called, and a pre-established objective function, determine the calling power and calling period of the load data to be called, so that the electricity fee of the area to be regulated is the minimum, wherein the objective function is a relationship function related to the discharge power of the energy storage device, the charging power of the energy storage device, the power generation of the power generation device in the area to be regulated, the load data to be called, the stepped electricity price data, and the calling period; The historical power load data includes one-to-one corresponding collected load data collected by each electric energy meter in the area to be regulated, and the power load forecast data of the area to be regulated within the future preset time is predicted based on the historical power load data, including: Determine the sliding window size; Starting from the start time of each of the collected load data, dividing the collected load data according to the sliding window size to obtain sliding window data arranged according to the time series; Adding the sliding window data of the same time period in all the collected load data to obtain the sum of the load data corresponding to each time period; Divide the total of the load data by the sliding window size to determine the average power value corresponding to each time period; Determine the electrical equipment corresponding to the collected load data; The average power value is matched with the active power of the corresponding electrical equipment in a one-to-one manner according to the time period to obtain energy consumption power data; The energy consumption power data is used as training data, and the future preset time is input into a pre-established power load prediction model to output a predicted average power value for each time period in the future preset time, and the predicted average power value is used as the power load prediction data; The historical power generation load data includes a collection time and a power generation load corresponding to the collection time. The power generation load forecast data of the area to be regulated within the future preset time is predicted based on the historical power generation load data, including: Determine the historical weather information corresponding to the collection time; Determining the forecast weather information corresponding to the future preset time; The historical weather information and the historical power generation load data are used as training data, and the future preset time and the predicted weather information are input into a pre-established power generation load prediction model to output the average power generation within the future preset time, and the average power generation power is used as the power generation load prediction data.

2. The method according to claim 1, It is characterized in that The determining, based on the power load forecast data and the power generation load forecast data, the load data to be called for the area to be regulated within the future preset time includes: The predicted average power value in the power load prediction data is subtracted from the power generation load prediction data, so as to determine the load data to be called for the area to be regulated within the future preset time.

3. The method according to claim 1, It is characterized in that Before determining the load data to be called for the area to be regulated within the future preset time based on the power load forecast data and the power generation load forecast data, the method further includes: Based on the power load forecast data and the power generation load forecast data, determining the minimum charge and discharge power of the energy storage device; wherein the energy storage device is used to store the electric energy generated by the power generation device in the area to be regulated, and to provide electric energy to the power consumption equipment in the area to be regulated; Determining a maximum charge and discharge duration according to the energy storage device capacity and the minimum charge and discharge power; The load data to be called for the area to be regulated within the future preset time is determined according to the minimum charge and discharge power, the maximum charge and discharge time, the power consumption load forecast data and the power generation load forecast data.

4. The method according to claim 1, It is characterized in that The objective function is: in, is the discharge power of the energy storage device, P1 is the preset electricity price, is the percentage of the energy storage device discharge capacity in the i-th period to the energy storage device capacity, The charging amount of the energy storage device, is the percentage of the power generation of the power generation equipment in the i-th period to the capacity of the energy storage equipment, The amount of electricity generated by the power generation equipment, is the load data to be called, P(i) is the time period unit price of the i-th time period in the said ladder electricity price data, α and β are weight coefficients, i is a variable, and n is the total number of time periods.

5. A load control device based on source, grid, load and storage, It is characterized in that The device comprises: An acquisition module, used to acquire historical load data and tiered electricity price data of the area to be regulated, wherein the historical load data includes historical electricity load data and historical power generation load data of the area to be regulated; An electricity consumption data prediction module is used to predict the electricity consumption load prediction data of the area to be regulated within a preset time in the future based on the historical electricity consumption load data; A power generation data prediction module, used to predict the power generation load prediction data of the area to be regulated within the future preset time based on the historical power generation load data; Based on the power load forecast data and the power generation load forecast data, determine the load data to be called in the area to be regulated within the future preset time, the load data to be called is the load that needs to be called from outside the area to be regulated; An optimization module, for determining the calling power and calling period of the load data to be called based on the stepped electricity price data, the capacity of the energy storage device in the area to be regulated, the load data to be called, and a pre-established objective function, so that the electricity fee of the area to be regulated is the minimum, wherein the objective function is a relationship function related to the discharge power of the energy storage device, the charge power of the energy storage device, the power generation of the power generation device in the area to be regulated, the load data to be called, the stepped electricity price data, and the calling period; The historical power load data includes one-to-one corresponding collected load data collected by each electric energy meter in the area to be regulated, and the power consumption data prediction module includes: A sliding window determining unit, used to determine a sliding window size; a dividing unit, configured to divide the collected load data according to the size of the sliding window starting from the start time of each of the collected load data, so as to obtain the sliding window data arranged according to the time series; A calculation unit, used for adding the sliding window data of the same time period in all the collected load data to obtain the sum of the load data corresponding to each time period; An average power value determination unit, configured to divide the total of the load data by the sliding window size to determine an average power value corresponding to each time period; An electrical equipment determination unit, used to determine the electrical equipment corresponding to the collected load data; used to make a one-to-one correspondence between the average power value and the active power of the corresponding electrical equipment according to a time period to obtain energy consumption power data; An electricity consumption prediction unit, configured to use the energy consumption power data as training data, and input the future preset time into a pre-established electricity load prediction model to output a predicted average power value for each time period within the future preset time, and use the predicted average power value as the electricity load prediction data; The historical power generation load data includes a collection time and a power generation load corresponding to the collection time. The power generation data prediction module includes: A historical weather information determination unit, used to determine the historical weather information corresponding to the collection time; A forecast weather information determination unit, used to determine the forecast weather information corresponding to the future preset time; The power generation prediction unit is used to use the historical weather information and the historical power generation load data as training data, and input the future preset time and the predicted weather information into a pre-established power generation load prediction model to output the average power generation within the future preset time, and use the average power generation power as the power generation load prediction data.

6. A computer device, It is characterized in that include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the load control method based on source-grid-load-storage as described in any one of claims 1-4 by executing the computer instructions.

7. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the load control method based on source-grid-load-storage as described in any one of claims 1-4.

8. A computer program product, It is characterized in that It includes computer instructions, and the computer instructions are used to enable a computer to execute the load control method based on source-grid-load-storage according to any one of claims 1-4.

Images