Power supply response method based on superior power grid power supply gap and related equipment

Abstract

The invention belongs to the technical field of distribution network management and control, and particularly relates to a power supply response method and related equipment based on a superior power grid power supply gap, and the method comprises the steps: predicting the operation data of a distribution network based on a preset training model, and obtaining a prediction result; external regulation and control information and power supply gap information of the superior power grid are acquired, a first power regulation response strategy of the distribution network is generated according to the external regulation and control information and the prediction result, and a second power regulation response strategy of the distribution network is generated according to the power supply gap information of the superior power grid and the prediction result; and generating a corresponding regulation and control instruction based on the first power adjustment response strategy or the second power adjustment response strategy of the distribution network, and sending the regulation and control instruction to the load side for short-term power utilization response of the power grid. The cost of the system can be reduced, more accurate decision support can be provided for the master station system, the coordination and the power supply regulation capability of the system are improved, and a guarantee is provided for supply and demand balance, safety and stability of a power grid.

Description

Technical Field

[0001] The present invention belongs to the technical field of distribution network control, and specifically relates to a power supply response method based on a power supply gap of a superior power grid and related equipment. Background Art

[0002] In recent years, the power supply system has often suffered from multiple points of external forces, resulting in serious power supply gaps. In this regard, it is necessary to timely and reasonably allocate power emergency materials to restore power supply as soon as possible to provide strong guarantees. In order to cope with short-term power shortages, the power system will provide more backup resources and frequency modulation resources through generators, which will seriously waste resources. In particular, due to the influence of various factors such as coal market fluctuations, power market reforms and abnormally high temperatures in summer, the power supply is unbalanced. Once it exceeds the limit significantly, it is difficult to form effective pressure reduction measures in a short period of time, which brings huge challenges to emergency peak regulation.

[0003] In response to short-term power shortages, virtual power plant technology has been proposed in existing technologies. Virtual power plant technology can integrate decentralized new energy and load resources, improve their ability to participate in market transactions and auxiliary services, and provide flexibility and reliability for the power grid. However, virtual power plant technology mainly relies on information and communication technology, and requires the establishment of complex data collection, transmission and processing systems, which increases the cost and risk of the system. It also aggregates and manages new energy power generation equipment and load resources, ignoring the actual situation of the power supply shortage in the power grid. It will be biased in the formulation of power supply regulation strategies, resulting in poor system regulation capabilities. Summary of the invention

[0004] The purpose of the present invention is to solve the problem of short-term power shortage of power grid by virtual power plant technology in the prior art, which depends on information communication technology, needs to establish complex data acquisition, transmission and processing system, increases the cost of the system, and ignores the actual situation of power grid shortage, resulting in poor system regulation ability. A power supply response method based on the power supply shortage of the upper power grid and related equipment are proposed. The method directly exchanges data between the master station system and the load side, formulates strategies and controls the electric energy resources on the load side through the master station system, and does not need to establish complex data acquisition, transmission and processing systems, thereby reducing the cost of the system; by constructing a prediction model to predict the output of load and new energy, respectively combining external control information and power supply shortage information of the upper power grid to determine the power adjustment response strategy to deal with the power supply shortage, and provide decision support for the master station system. In this way, not only can the power adjustment response strategy be determined in combination with the actual situation of the power supply shortage, but also the power adjustment response strategy can be determined in combination with external control information, which is conducive to selecting different strategies for different situations, thereby generating different control instructions and sending them to the load side to control various devices on the load side to respond to power supply, improve the coordination and power supply regulation ability of the system, and provide guarantee for the supply and demand balance and safety and stability of the power grid.

[0005] In a first aspect, an embodiment of the present invention provides a power supply response method based on a power supply gap of an upper-level power grid, comprising the following steps: predicting the operation data of a distribution network based on a preset training model to obtain a prediction result, wherein the preset training model is obtained by iterative training based on historical operation data of the distribution network; The master station system obtains external control information and power supply gap information of the upper power grid, generates a first power adjustment response strategy of the distribution network according to the external control information and the prediction result, and generates a second power adjustment response strategy of the distribution network according to the power supply gap information of the upper power grid and the prediction result; Based on the first power adjustment response strategy or the second power adjustment response strategy of the distribution network, a corresponding control instruction is generated and sent to the load side for short-term power consumption response of the power grid.

[0006] Furthermore, the operation data of the distribution network is predicted based on the preset training model to obtain the prediction result, including: Acquire the historical operation data of the distribution network within a preset historical period, wherein the historical operation data includes load-related data and new energy output-related data; A quantile regression prediction model is constructed, and the load-related data is regressed through the quantile regression prediction model, and the new energy output-related data is regressed through the quantile regression prediction model to determine the load prediction result and the new energy output prediction result after regression.

[0007] Further, the constructing of the quantile regression prediction model, regressing the load-related data through the quantile regression prediction model, regressing the new energy output-related data through the quantile regression prediction model, and determining the load prediction result and the new energy output prediction result after regression, includes: Performing data preprocessing on the load-related data and the new energy output-related data to construct a load prediction data set and a new energy output prediction data set, wherein the load-related data includes historical load data, weather data, and holiday data, and the new energy output-related data includes historical new energy output data, weather data, and seasonal data; A quantile regression prediction model is constructed, and regression prediction is performed on the load prediction data set through the quantile regression prediction model to obtain a load prediction result corresponding to the quantile; regression prediction is performed on the new energy output prediction data set through the quantile regression prediction model to obtain a new energy output prediction result.

[0008] Furthermore, the first power adjustment response strategy includes a first load distribution adjustment strategy and a first new energy output adjustment strategy. The master station system obtains external control information and power supply gap information of the upper power grid, and generates a first power adjustment response strategy of the distribution network according to the external control information and the prediction result, including: The master station system obtains the external regulation information, which includes market price information and electricity incentive mechanism; According to the load forecast result, the market price information and the electricity consumption incentive mechanism, strategy matching is performed, and the first load distribution adjustment strategy of the distribution network is generated by optimizing through a particle swarm optimization algorithm with the objective function of minimizing net load fluctuation and maximizing controllable load benefit; According to the new energy output prediction result, strategy matching is performed with any one of the market price information and the electricity consumption incentive mechanism, and the objective function is minimized net load fluctuation and maximized controllable load benefit. The particle swarm optimization algorithm is used for optimization to generate the first new energy output adjustment strategy for the distribution network.

[0009] Furthermore, the second power adjustment response strategy includes a second load distribution adjustment strategy and a second new energy output adjustment strategy, and the second power adjustment response strategy of the distribution network is generated according to the power supply gap information of the upper power grid and the prediction result, including: The master station system obtains the power supply gap information sent by the upper power grid, wherein the power supply gap information includes the power supply gap quantity of the upper power grid and the location of the fault point of the upper power grid; According to the power supply gap of the upper power grid, the location of the fault point of the upper power grid and the load forecast result, strategy matching is performed, and the objective function is minimized net load fluctuation and maximized controllable load benefit. The particle swarm optimization algorithm is used for optimization to generate the second load distribution adjustment strategy of the distribution network; According to the power supply gap of the upper power grid, the location of the fault point of the upper power grid and the prediction result of the new energy output, strategy matching is performed, and the objective function is minimized net load fluctuation and maximized controllable load benefit. The particle swarm optimization algorithm is used for optimization to generate the second new energy output adjustment strategy for the distribution network.

[0010] Furthermore, the first power adjustment response strategy or the second power adjustment response strategy based on the distribution network generates a corresponding control instruction and sends it to the load side for short-term power consumption response of the power grid, including: Obtaining the active participation of the load side in power consumption regulation, and determining the scope of power outage according to the location of the fault point of the upper-level power grid; if the active participation of the load side meets the set participation threshold, then generating a corresponding first regulation instruction based on the first load distribution adjustment strategy and the first new energy output adjustment strategy and sending it to the load side, and controlling the distributed photovoltaic equipment, distributed energy storage equipment and load devices on the load side to execute the short-term power consumption response of the power grid according to the first regulation instruction; If the power outage range reaches the preset power outage range threshold, a corresponding second control instruction is generated based on the second load distribution adjustment strategy and the second new energy output adjustment strategy and sent to the load side to control the distributed photovoltaic equipment, distributed energy storage equipment and load devices on the load side, and execute the short-term power consumption response of the power grid according to the second control instruction.

[0011] Further, after the first power adjustment response strategy or the second power adjustment response strategy based on the distribution network generates a corresponding control instruction and sends it to the load side for short-term power consumption response of the power grid, the method further includes: Obtain load data and new energy output data before and after the strategy adjustment, calculate the load change amplitude and the new energy output change amplitude; determine the response evaluation result according to the load change amplitude, the new energy output change amplitude and the strategy response time.

[0012] In a second aspect, an embodiment of the present invention further provides a power supply response device based on a power supply gap of an upper-level power grid, the device comprising: A data acquisition module, used to predict the operation data of the distribution network based on a preset training model to obtain a prediction result, wherein the preset training model is obtained by iterative training based on the historical operation data of the distribution network; A strategy generation module, used for the master station system to obtain external control information and power supply gap information of the upper power grid, generate a first power adjustment response strategy of the distribution network according to the external control information and the prediction result, and generate a second power adjustment response strategy of the distribution network according to the power supply gap information of the upper power grid and the prediction result; A strategy response module is used to generate corresponding control instructions based on the first power adjustment response strategy or the second power adjustment response strategy of the distribution network and send them to the load side for short-term power consumption response of the power grid.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the power supply response method based on the power supply gap of the upper-level power grid as described in the first aspect are implemented.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power supply response method based on the power supply gap of the upper-level power grid as described in the first aspect are implemented.

[0015] The beneficial effects achieved by the present invention are as follows: by directly performing data interaction between the master station system and the load side, the master station system formulates strategies and controls the electric energy resources on the load side, without the need to establish complex data collection, transmission and processing systems, thereby reducing the cost of the system; by constructing a prediction model to predict the load and new energy output, the power adjustment response strategy for responding to the power supply gap is determined by combining external control information and the power supply gap information of the superior power grid, so as to provide decision support for the master station system. In this way, not only can the power adjustment response strategy be determined in combination with the actual situation of the power supply gap, but the power adjustment response strategy can also be determined in combination with external control information, which is conducive to selecting different strategies for responding to different situations, thereby generating different control instructions and sending them to the load side to control various devices on the load side to respond to power supply, thereby improving the coordination and power supply regulation capabilities of the system, and providing guarantees for the supply and demand balance and safety and stability of the power grid.

[0016] The above invention content is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0018] Figure 1 It is a flow chart of a power supply response method based on a power supply gap of a superior power grid provided in an embodiment of the present invention.

[0019] Figure 2 It is a structural schematic diagram of a power supply response device based on a power supply gap of a superior power grid provided in an embodiment of the present invention.

[0020] Figure 3 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0022] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the drawings; the process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0023] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. It should also be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0024] It should be understood that, in the present invention, "multiple" refers to two or more than two. "And / or" is merely a variable relationship that describes associated objects, indicating that three relationships may exist. "Including A, B and C" means that A, B and C are all included, "Including A, B or C" means that one of A, B and C is included, and "Including A, B and / or C" means that any one or any two or three of A, B and C are included. In the present invention, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean that B is determined only based on A, but B can also be determined based on A and / or other information.

[0025] Embodiment 1 Please refer to Figure 1 , Figure 1 1 is a flow chart of a power supply response method based on a power supply gap of a superior power grid provided by an embodiment of the present invention. The power supply response method based on a power supply gap of a superior power grid specifically includes the following steps: S1. Predict the operation data of the distribution network based on a preset training model to obtain a prediction result. The preset training model is obtained by iterative training based on the historical operation data of the distribution network.

[0026] In this embodiment, the power supply response method based on the power supply gap of the upper power grid can be executed in the master station system. The master station system can refer to the control center of the distribution automation system, which is used to monitor and control the operation of the distribution network. Based on the master station system, the operation status monitoring of the distribution network can be realized, so the historical operation data of a certain period of time in history can be obtained in the master station system, including obtaining normal operation data, abnormal fault data, etc. The upper level of the master station system also includes an upper distribution automation system, and distributed new energy is connected to the distribution network. The master station system can communicate with multiple sides of the source network load storage to realize data interaction with each side of the source network load storage to monitor and control the operation of the distribution network in real time, ensure the stability of the distribution network operation, and interact with the upper distribution automation system at the same time. Data can be received from the upper distribution automation system. Various data or instructions sent by the upper distribution automation system can be received. After obtaining the historical operation data, a training model can be constructed based on the historical operation data, and then the operation data of the distribution network in a certain period of time in the future can be predicted based on the trained training model, for example: predicting the load in the next 2 hours, predicting the output of new energy in the next week, etc.

[0027] Specifically, step S1 includes: S11. Obtain historical operation data of the distribution network within a preset historical period, where the historical operation data includes load-related data and new energy output-related data; S12. Construct a quantile regression prediction model, regress the load-related data through the quantile regression prediction model, regress the new energy output-related data according to the quantile regression prediction model, and determine the load forecast results and new energy output forecast results after regression according to the quantiles. The load forecast results include the load estimated value corresponding to the quantile, and the new energy output forecast results include the new energy output estimated value corresponding to the quantile.

[0028] Among them, considering that the main purpose in this embodiment is to target short-term electricity shortages, the prediction method may include short-term prediction and ultra-short-term prediction, and the corresponding preset historical time period may be 1 week, 1 hour, etc. Consider the impact of different factors on the load, for example: when the weather cools down, the load-side electricity usage increases; when there are holidays, corporate electricity consumption decreases, etc. In order to improve the accuracy of the prediction, the above-mentioned load-related data includes historical load data and weather data and holiday data that affect the load data, and the above-mentioned new energy output-related data also includes historical new energy output data, weather data, and seasonal data. Different seasons provide different new energy sources for electricity, for example: in summer and autumn, there is sufficient sunlight and high wind speed, and the power supply is mainly provided by photovoltaic and wind power; in winter, there is insufficient sunlight and the climate is cold, and the power supply is mainly provided by hydropower.

[0029] Specifically, the master station system can obtain historical load data and new energy output data from the corresponding data storage in the master station system, and the master station system can access the meteorological monitoring system to request the meteorological monitoring system to send weather data and seasonal data within a preset historical period. The master station system can also access the terminals of relevant departments, holiday service providers, calendar service providers, etc. to obtain the latest holiday data.

[0030] Specifically, the quantreg package of R language or the statsmodels package of Python can be used to construct a quantile regression prediction model, and the load-related data and the new energy output-related data can be regressed and predicted respectively through the quantile regression prediction model to obtain the load prediction results and the new energy output prediction results. For example, the master station system obtains the load-related data and the new energy output-related data of the past half an hour and 2 hours, and regresses the obtained load-related data and the new energy output-related data respectively through the above quantile regression prediction model. Based on the regression situation, the most likely maximum value, minimum value and prediction range of the load and new energy output in the next hour are predicted. Among them, the quantile refers to the distribution position of the data, for example: 0.25 represents the quartile position, and 0.5 represents the median position.

[0031] More specifically, the above step S12 includes: performing data preprocessing on load-related data and new energy output-related data to construct a load prediction data set and a new energy output prediction data set; constructing a quantile regression prediction model, performing regression prediction on the load prediction data set through the quantile regression prediction model to obtain the load prediction result of the corresponding quantile, and performing regression prediction on the new energy output prediction data set through the quantile regression prediction model to obtain the new energy output prediction result.

[0032] Specifically, the above-mentioned data preprocessing may include data cleaning, missing value processing, outlier processing, etc. The preprocessed load-related data is constructed as a load forecasting data set, and the preprocessed new energy output-related data is constructed as a new energy output forecasting data set. Possibly, the load forecasting data set and the new energy output forecasting data set can also be divided into a training set, a validation set, and a prediction set, respectively. A quantile regression prediction model for load forecasting is constructed based on the training set of the load forecasting data set, and then the model is verified through the validation set of the load forecasting data set. During the verification process, the root mean square error, mean absolute error, etc. can be used as reference indicators for model verification. When the error is lower than the set error threshold, it is considered to pass the verification. For example, the calculated mean absolute error is 0.215, and the set error threshold is 0.25, then the verification is passed. Then the quantile regression prediction model for load forecasting that has passed the verification is used to predict the prediction set, and the load prediction result is output. The prediction of new energy output is the same, which will not be repeated here.

[0033] In this embodiment, by constructing a quantile regression prediction model, short-term and ultra-short-term load forecasts are performed based on historical load data, weather data, and holiday data, and short-term and ultra-short-term new energy output forecasts are performed based on historical new energy output data, weather data, and seasonal data. It is possible to understand the expected changes in load demand and new energy power supply in the future, and the quantile regression prediction model is suitable for modeling the uncertainty in load forecasting and new energy output forecasting, and can capture the changes in load demand and new energy output at different quantiles, and provide load forecast results and new energy output forecast results at different quantiles, which is conducive to a more comprehensive evaluation of load demand and new energy output under different situations, and improves the accuracy and reliability of the prediction.

[0034] S2. The master station system obtains external control information and power supply gap information of the upper power grid, generates a first power adjustment response strategy for the distribution network according to the external control information and the prediction results, and generates a second power adjustment response strategy for the distribution network according to the power supply gap information and the prediction results of the upper power grid.

[0035] Among them, the external control information may refer to information that affects the power consumption in addition to the operating information of the master station system. The above-mentioned power supply gap information may refer to the information sent to the master station system by the upper power grid of the distribution network where the master station system is located when a short-term power supply difficulty occurs due to an abnormal event. In the present application, different power adjustment response strategies can be generated according to the external control information and the power supply gap information of the upper power grid.

[0036] Specifically, step S2 includes: S21, the master station system obtains external control information, which includes market price information and electricity incentive mechanism; S22, matching strategies according to load forecast results, market price information and power consumption incentive mechanism, taking minimum net load fluctuation and maximum controllable load benefit as objective functions, optimizing through particle swarm optimization algorithm, and generating the first load distribution adjustment strategy of the distribution network; S23. Match the strategy according to the new energy output forecast result with the market price information and any one of the electricity consumption incentive mechanisms, take the minimum net load fluctuation and the maximum controllable load benefit as the objective function, optimize through the particle swarm optimization algorithm, and generate the first new energy output adjustment strategy for the distribution network.

[0037] Specifically, the first power adjustment response strategy includes a first load distribution adjustment strategy and a first new energy output adjustment strategy, and the external control information includes market price information and power incentive mechanism. Among them, market price information can refer to the electricity price data provided by the electricity supplier, and the power incentive mechanism can be a power mechanism formulated according to the principle of peak shaving and valley filling, such as encouraging users to reduce load power consumption during peak power consumption periods and providing users with a certain amount of power supply discounts. Market price information and power incentive mechanisms are used to guide users to change their power consumption behavior or power consumption during specific periods, so as to achieve participation in market transactions and ancillary services.

[0038] Therefore, for load adjustment, the first load distribution adjustment strategy can be determined in combination with the load forecast results, market price information and electricity incentive mechanism. The first load distribution adjustment strategy can be formulated by taking the minimum net load fluctuation and the maximum controllable load benefit as the objective function and updating it through the particle swarm optimization algorithm. Similarly, the method of formulating the first new energy output adjustment strategy is the same as the method of formulating the first load distribution adjustment strategy, but it is combined with the new energy output forecast results. Among them, the net load can refer to the total load of the distribution network minus the total capacity of the power supply, that is, the power grid needs to purchase from the external power supply; the controllable load benefit can refer to the cost saved by the operation of the power system due to the controllable load in the power system. The controllable load includes the power load management system, the load control device, etc. The following is explained based on the formulation of the first load distribution adjustment strategy. When updating through the particle swarm optimization algorithm, it is necessary to meet the constraints of the load forecast results, market price information and the electricity incentive mechanism. When updating through the particle swarm optimization algorithm, the load is used as the variable to be optimized. In this embodiment, the constructed objective function is shown in the following formula (1): f(x)= w1×g(x)+ w2×h(x) (1) Among them, w1 and w2 are the weight coefficients of net load fluctuation and controllable load benefit respectively, g(x) is the net load fluctuation, h(x) is the controllable load benefit, and the sum of w1 and w2 is equal to 1. Among them, g(x) can be evaluated by means of mean value, variance, standard deviation, etc.

[0039] More specifically, the optimization is performed through the particle swarm optimization algorithm. First, the initial particle swarm is randomly generated, and each particle represents a possible first load distribution adjustment strategy; the fitness of each first load distribution adjustment strategy is evaluated according to the value of the above objective function; the individual and group optimal positions are updated: for each first load distribution adjustment strategy, its individual optimal position is updated according to its current fitness value and the historical optimal fitness value, and the group optimal position is updated according to the fitness values ​​of all first load distribution adjustment strategies; the speed and position of each first load distribution adjustment strategy are updated. Repeat the speed and position update until the termination conditions are met, such as reaching the maximum number of iterations, the objective function value is close enough to the optimal solution, etc. According to the final particle position and fitness value, the optimal first load distribution adjustment strategy is obtained to achieve the goal of minimizing net load fluctuations and maximizing controllable load benefits. Similarly, the method of obtaining the optimal first new energy output adjustment strategy is similar to the method of obtaining the optimal first load distribution adjustment strategy, which will not be repeated here.

[0040] More specifically, the above step S2 further includes: S24, the master station system obtains the power supply gap information sent by the upper power grid, the power supply gap information includes the power supply gap quantity of the upper power grid and the location of the fault point of the upper power grid; S25, matching strategies according to the power supply gap of the upper power grid, the location of the fault point of the upper power grid and the load forecast results, taking the minimum net load fluctuation and the maximum controllable load benefit as the objective function, optimizing through the particle swarm optimization algorithm, and generating the second load distribution adjustment strategy of the distribution network; S26. According to the power supply gap of the upper power grid, the location of the fault point of the upper power grid and the prediction results of the new energy output, the strategy is matched, and the objective function is minimized by the particle swarm optimization algorithm to generate the second new energy output adjustment strategy of the distribution network.

[0041] In this embodiment, in addition to determining the power adjustment strategy in combination with market price information and power incentive mechanism, a second power adjustment response strategy can also be formulated in combination with the power supply gap quantity of the upper power grid and the location of the upper power grid fault point, and the second power adjustment response strategy includes a second load distribution adjustment strategy and a second new energy output adjustment strategy. The master station system obtains the power supply gap information issued by the upper power grid, extracts the power supply gap quantity of the upper power grid and the location of the upper power grid fault point in the power supply gap information, wherein the power outage area corresponding to the different locations of the upper power grid fault point is different, which can be used to determine the power outage range of the upper power grid.

[0042] More specifically, the strategy is matched according to the power supply gap of the upper power grid, the location of the fault point of the upper power grid and the load forecast results, and the net load fluctuation is minimized and the controllable load benefit is maximized as the objective function. The particle swarm optimization algorithm is used for optimization, and the method of generating the second load distribution adjustment strategy of the distribution network refers to the method of generating the first load distribution adjustment strategy mentioned above, and only the market price information and the power consumption incentive mechanism are replaced with the power supply gap of the upper power grid and the location of the fault point of the upper power grid to formulate the strategy. Among them, the second load distribution adjustment strategy of the distribution network can be a load adjustment strategy formulated according to the power supply gap of the upper power grid and the location of the fault point of the upper power grid under the premise of meeting the minimum net load fluctuation and the maximum controllable load benefit. For example, the location of the fault point of the upper power grid is the main transformer A1, and the power supply gap of the upper power grid is determined to be 1000 kWh according to the power supply range and fault period of the main transformer A1, and then the net load fluctuation is minimized and the controllable load benefit is maximized, and the power supply gap is determined based on the power supply gap of the upper power grid. How to supply the gap power through the distribution network, etc.. Similarly, the second new energy output adjustment strategy of the distribution network can also be formulated based on the same principle.

[0043] In this embodiment, by using artificial intelligence, taking the minimum net load fluctuation and the maximum controllable load benefit as the objective function, the particle swarm optimization algorithm is used to optimize the strategy, and decision support is provided for the main station system. For the situation of short-term power supply gap, it is more conducive to obtaining the optimal first power adjustment response strategy and the second power adjustment response strategy under the premise of ensuring the objective function. In addition, the distributed energy storage device is used as one of the important load-side resources. According to its charging and discharging state and capacity limit, the new energy output curve can be smoothed through the charging and discharging operation of the distributed energy storage device, so as to compensate for the new energy output fluctuation by using the distributed energy storage device to reduce the impact on the operation of the power grid. Furthermore, not only the power supply gap factor of the upper power grid is considered to achieve an orderly response to the operation of the power grid, but also the market price information and the power consumption incentive mechanism are combined for optimization and scheduling. Different strategies can be called to respond in different situations. In this way, it is more conducive to strengthening the balance of supply and demand and the guarantee of safety and stability of the power grid, and improving the coordination and adaptability of the system.

[0044] S3. Generate corresponding control instructions based on the first power adjustment response strategy or the second power adjustment response strategy of the distribution network and send them to the load side for short-term power consumption response of the power grid.

[0045] Among them, the first power adjustment response strategy or the second power adjustment response strategy can be selected according to the power outage area and the user's participation in the regulation to generate a regulation instruction and send it to the load side to control the equipment on the load side to respond to the short-term power consumption of the power grid. Among them, the load side includes distributed photovoltaic equipment, distributed energy storage equipment and load devices. In addition to considering distributed photovoltaic equipment and load devices on the load side, distributed energy storage equipment is also considered. When performing distribution network operation regulation, the charging and discharging status and capacity limit of distributed energy storage equipment are used. Through the charging and discharging operation of distributed energy storage equipment, the new energy output curve can be smoothed, the fluctuation of new energy output can be compensated, and the stability of distribution network operation can be improved.

[0046] Specifically, the above step S3 includes: S31, obtaining the active participation of the load side in power consumption regulation, and determining the scope of power outage according to the location of the fault point of the upper power grid; S32: If the active participation degree of the load side meets the set participation degree threshold, a corresponding first control instruction is generated based on the first load distribution adjustment strategy and the first new energy output adjustment strategy and sent to the load side to control the distributed photovoltaic equipment, distributed energy storage equipment and load device on the load side to execute the short-term power consumption response of the power grid according to the first control instruction; S33. If the power outage range reaches the preset power outage range threshold, a corresponding second control instruction is generated based on the second load distribution adjustment strategy and the second new energy output adjustment strategy and sent to the load side to control the distributed photovoltaic equipment, distributed energy storage equipment and load devices on the load side, and execute the short-term power consumption response of the power grid according to the second control instruction.

[0047] Specifically, users on the load side can actively participate in the process of power consumption regulation, or they can passively receive access requests from the master station system. The active participation of users on the load side is obtained. When the active participation meets the set participation threshold, it is considered that the premise of voluntary participation of users is met. In this regard, the master station system can generate a first regulation instruction based on the first load distribution adjustment strategy and the first new energy output adjustment strategy and send it to the corresponding distributed photovoltaic equipment, distributed energy storage equipment and load devices on the load side to control the distributed photovoltaic equipment, distributed energy storage equipment and load devices, and execute the short-term power consumption response of the power grid according to the first regulation instruction, that is, combine market price information and power consumption incentive mechanism to guide load-side users to change their power consumption behavior or power consumption in a specific period of time, so as to adjust the short-term power consumption of the power grid from the perspective of market transactions and auxiliary services.

[0048] As another possible implementation method, when the fault point is a substation, the power outage range can be determined according to the location of the fault point of the superior power grid. When the power outage range reaches the preset power outage range threshold, it is considered that the premise of a large-scale power outage at the substation is met. In this regard, the master station system generates a corresponding second control instruction based on the second load distribution adjustment strategy and the second new energy output adjustment strategy and sends it to the load side, and controls the load side to execute the short-term power consumption response of the power grid according to the second control instruction. That is, the master station system automatically generates the load adjustment and new energy adjustment requirements of the main transformer supply area according to the power supply gap of the superior power grid and the location of the fault point of the superior power grid, generates a power grid operation mode strategy corresponding to the power outage range, and sends the second control instruction to the load side and obtains feedback information on the user's consent to the power supply control. After obtaining the feedback information, the user adjusts the photovoltaic output according to the second load distribution adjustment strategy and the second new energy output adjustment strategy generated by the master station system to ensure normal power supply to the power grid.

[0049] In this embodiment, by selecting an adjustment strategy based on actual conditions, it is more conducive to accurately adjusting the load of power distribution and the output of new energy sources according to actual conditions, thereby ensuring the stability of the distribution network.

[0050] Furthermore, after the above step S3, the method further includes step S4: obtaining a response result of the load side, and performing a response evaluation according to the response result. S4 specifically includes: S41, obtaining load data and new energy output data before and after the strategy adjustment, and calculating the load change amplitude and the new energy output change amplitude; S42. Determine a response evaluation result according to the load change amplitude, the new energy output change amplitude and the strategy response time.

[0051] Among them, the load change amplitude may refer to the load data change amplitude before and after the load side responds, the new energy output change amplitude may refer to the new energy output change amplitude before and after the load side responds, and the above-mentioned strategy response time may refer to the time from receiving the first control instruction or the second control instruction to the actual response completion. The response evaluation result is determined based on the load change amplitude, the new energy output change amplitude and the strategy response time. The response evaluation result can be a numerical value. Different numerical values ​​correspond to different response levels. The higher the response level, the faster the response speed. If the response speed is slow, it can be used as a parameter to adjust the response strategy to optimize the strategy.

[0052] In the embodiment of the present invention, there is no need to establish a complex data acquisition, transmission and processing system. It is only necessary to exchange data and transmit signals between the master station system and the load side. By simplifying data interaction, efficient management of load side resources is achieved, reducing the cost of the system. At the same time, a quantile regression prediction model is constructed to predict load and new energy output. In the prediction process, weather data, holiday data, and seasonal data are combined for comprehensive short-term and ultra-short-term predictions, and the prediction accuracy is higher. By utilizing artificial intelligence, with the minimum net load fluctuation and the maximum controllable load benefit as the objective function, the particle swarm optimization algorithm is used to optimize the strategy, so as to provide decision support for the master station system. In the case of short-term power supply gaps, it is more conducive to ensuring the objective function. The optimal power adjustment response strategy can be obtained under the premise; and the distributed energy storage device is used as one of the important load-side resources. According to the charging and discharging state and capacity limitation of the distributed energy storage device, the new energy output curve can be smoothed through the charging and discharging operation of the distributed energy storage device, and the distributed energy storage device can be used to effectively compensate for the new energy output fluctuation, thereby reducing the impact of the fluctuation on the distribution network operation; and the present invention not only considers the power supply gap factor of the superior power grid to achieve an orderly response to the power grid operation, but also combines the market price information and the electricity consumption incentive mechanism for optimized scheduling. Different strategies can be called to respond in different situations, which is more conducive to strengthening the supply and demand balance and safety and stability of the power grid and improving the coordination and adaptability of the system.

[0053] Embodiment 2 refer to Figure 2 As shown, Figure 2 A schematic diagram of the structure of a power supply response device based on a power supply gap of a superior power grid provided in an embodiment of the present invention, wherein the device M20 includes: The data acquisition module M201 is used to predict the operation data of the distribution network based on a preset training model to obtain a prediction result. The preset training model is obtained by iterative training based on the historical operation data of the distribution network; The strategy generation module M202 is used for the master station system to obtain external control information and power supply gap information of the upper power grid, generate a first power adjustment response strategy of the distribution network according to the external control information and the prediction results, and generate a second power adjustment response strategy of the distribution network according to the power supply gap information and the prediction results of the upper power grid; The strategy response module M203 is used to generate corresponding control instructions based on the first power adjustment response strategy or the second power adjustment response strategy of the distribution network and send them to the load side for short-term power consumption response of the power grid.

[0054] The power supply response device based on the power supply gap of the upper power grid provided in the embodiment of the present invention can implement each process in the power supply response method based on the power supply gap of the upper power grid and can achieve the same beneficial effect. To avoid repetition, it will not be described here.

[0055] The embodiment of the present invention also provides a computer device, please refer to Figure 3 , Figure 3 : is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention, and the computer device D30 includes: a processor D301, a memory D302, and a computer program stored in the memory D302 and executable on the processor D301. The processor D301 calls the computer program stored in the memory D302 to execute each step of the power supply response method based on the power supply gap of the upper power grid provided in the embodiment of the present invention, and can achieve the same technical effect, refer to the description in the above embodiment, and will not be repeated here.

[0056] It should be pointed out that those skilled in the art can understand that the electronic device in the embodiment of the present invention is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc. The electronic device can be a computing device such as a desktop computer, a notebook, a handheld computer, and a cloud server. The electronic device can perform human-computer interaction through a keyboard, a mouse, a remote control, a touchpad, or a voice-controlled device.

[0057] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes and steps in the power supply response method based on the power supply gap of the superior power grid provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0058] It should be noted that the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Of course, the memory may also include both the internal storage unit of the electronic device and its external storage device. In this embodiment, the memory is generally used to store operating devices and various application software installed in the electronic device, such as program codes of power supply response methods based on power supply gaps of the upper power grid, etc. In addition, the memory may also be used to temporarily store various types of data that have been output or are to be output.

[0059] A person of ordinary skill in the art may understand that the implementation of all or part of the processes in the power supply response method based on the power supply gap of the superior power grid in the above-mentioned embodiment may be completed by instructing the relevant hardware through a computer program, and the program may be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the various embodiments of the power supply response method based on the power supply gap of the superior power grid.

[0060] The specific implementation described above is a preferred implementation of the power supply response method based on the power supply gap of the upper power grid of the present invention, and it is not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to this specific implementation. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A power supply response method based on power supply gap of the upper power grid, characterized in that: The following steps are involved: Predicting the operation data of the distribution network based on a preset training model to obtain a prediction result, wherein the preset training model is obtained by iterative training based on the historical operation data of the distribution network; The master station system obtains external control information and power supply gap information of the upper power grid, generates a first power adjustment response strategy of the distribution network according to the external control information and the prediction result, and generates a second power adjustment response strategy of the distribution network according to the power supply gap information of the upper power grid and the prediction result; Based on the first power adjustment response strategy or the second power adjustment response strategy of the distribution network, a corresponding control instruction is generated and sent to the load side for short-term power consumption response of the power grid.

2. The power supply response method based on the power supply gap of the upper power grid according to claim 1 is characterized in that: The operation data of the distribution network is predicted based on the preset training model to obtain the prediction result, including: Acquire the historical operation data of the distribution network within a preset historical period, wherein the historical operation data includes load-related data and new energy output-related data; A quantile regression prediction model is constructed, and the load-related data is regressed through the quantile regression prediction model, and the new energy output-related data is regressed through the quantile regression prediction model to determine the load prediction result and the new energy output prediction result after regression.

3. The power supply response method based on the power supply gap of the upper power grid according to claim 2 is characterized in that: The constructing of the quantile regression prediction model, regressing the load-related data through the quantile regression prediction model, regressing the new energy output-related data through the quantile regression prediction model, and determining the load prediction result and the new energy output prediction result after regression, includes: Performing data preprocessing on the load-related data and the new energy output-related data to construct a load prediction data set and a new energy output prediction data set, wherein the load-related data includes historical load data, weather data, and holiday data, and the new energy output-related data includes historical new energy output data, weather data, and seasonal data; A quantile regression prediction model is constructed, and regression prediction is performed on the load prediction data set through the quantile regression prediction model to obtain a load prediction result corresponding to the quantile; regression prediction is performed on the new energy output prediction data set through the quantile regression prediction model to obtain a new energy output prediction result.

4. The power supply response method based on the power supply gap of the upper power grid according to claim 2 is characterized in that: The first power adjustment response strategy includes a first load distribution adjustment strategy and a first new energy output adjustment strategy. The master station system obtains external control information and power supply gap information of the upper power grid, and generates a first power adjustment response strategy of the distribution network according to the external control information and the prediction result, including: The master station system obtains the external regulation information, which includes market price information and electricity incentive mechanism; performs strategy matching according to the load forecast result, the market price information and the electricity incentive mechanism, takes the minimum net load fluctuation and the maximum controllable load benefit as the objective function, optimizes through the particle swarm optimization algorithm, and generates the first load distribution adjustment strategy of the distribution network; According to the new energy output prediction result, strategy matching is performed with the market price information and one of the electricity consumption incentive mechanisms, and the objective function is minimized net load fluctuation and maximized controllable load benefit. The particle swarm optimization algorithm is used for optimization to generate the first new energy output adjustment strategy for the distribution network.

5. The power supply response method based on the power supply gap of the upper power grid according to claim 2 is characterized in that: The second power adjustment response strategy includes a second load distribution adjustment strategy and a second new energy output adjustment strategy, and the second power adjustment response strategy of the distribution network is generated according to the power supply gap information of the upper power grid and the prediction result, including: Obtain the power supply gap information sent by the upper power grid, wherein the power supply gap information includes the power supply gap quantity of the upper power grid and the location of the fault point of the upper power grid; According to the power supply gap of the upper power grid, the location of the fault point of the upper power grid and the load forecast result, strategy matching is performed, and the objective function is minimized net load fluctuation and maximized controllable load benefit. The particle swarm optimization algorithm is used for optimization to generate the second load distribution adjustment strategy of the distribution network; According to the power supply gap of the upper power grid, the location of the fault point of the upper power grid and the prediction result of the new energy output, strategy matching is performed, and the objective function is minimized net load fluctuation and maximized controllable load benefit. The particle swarm optimization algorithm is used for optimization to generate the second new energy output adjustment strategy for the distribution network.

6. The power supply response method based on the power supply gap of the upper power grid according to claim 4 is characterized in that: The first power adjustment response strategy or the second power adjustment response strategy based on the distribution network generates a corresponding control instruction and sends it to the load side for short-term power consumption response of the power grid, including: Obtaining the active participation of the load side in power consumption regulation and control, and determining the scope of power outage according to the location of the fault point of the upper-level power grid; If the active participation degree of the load side meets the set participation degree threshold, a corresponding first control instruction is generated based on the first load distribution adjustment strategy and the first new energy output adjustment strategy and sent to the load side to control the distributed photovoltaic equipment, distributed energy storage equipment and load devices on the load side to execute the short-term power consumption response of the power grid according to the first control instruction; If the power outage range reaches the preset power outage range threshold, a corresponding second control instruction is generated based on the second load distribution adjustment strategy and the second new energy output adjustment strategy and sent to the load side to control the distributed photovoltaic equipment, distributed energy storage equipment and load devices on the load side to execute the short-term power consumption response of the power grid according to the second control instruction.

7. The power supply response method based on the power supply gap of the upper power grid according to claim 6 is characterized in that: After the first power adjustment response strategy or the second power adjustment response strategy based on the distribution network generates a corresponding control instruction and sends it to the load side for short-term power consumption response of the power grid, the method further includes: Obtain load data and new energy output data before and after the strategy adjustment, calculate the load change amplitude and the new energy output change amplitude; determine the response evaluation result according to the load change amplitude, the new energy output change amplitude and the strategy response time.

8. A power supply response device based on the power supply gap of the upper power grid, characterized in that: The device comprises: A data acquisition module, used to predict the operation data of the distribution network based on a preset training model to obtain a prediction result, wherein the preset training model is obtained by iterative training based on the historical operation data of the distribution network; A strategy generation module, used for the master station system to obtain external control information and power supply gap information of the upper power grid, generate a first power adjustment response strategy of the distribution network according to the external control information and the prediction result, and generate a second power adjustment response strategy of the distribution network according to the power supply gap information of the upper power grid and the prediction result; A strategy response module is used to generate corresponding control instructions based on the first power adjustment response strategy or the second power adjustment response strategy of the distribution network and send them to the load side for short-term power consumption response of the power grid.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the power supply response method based on the power supply gap of the upper-level power grid as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the power supply response method based on the power supply gap of the upper power grid are implemented as described in any one of claims 1 to 7.

Images