Personalized power plant pricing strategy-based power grid optimization operation method and related device

Abstract

The invention provides a power grid optimization operation method based on a personalized power plant pricing strategy and a related device. The method comprises the following steps: collecting historical power consumption data of a user; carrying out aggregation processing on the historical electricity utilization data to obtain electricity utilization characteristic data representing electricity utilization characteristics of the user; clustering characteristic indexes are extracted from the electricity utilization characteristic data, and users are clustered according to the extracted clustering characteristic indexes; for each category of users, matching a corresponding personalized pricing strategy, and predicting power utilization responses of the users under different pricing strategies by using a pre-trained demand response prediction model; and according to the predicted power utilization response and the corresponding pricing strategy, optimizing the operation of the power system by adopting a load scheduling algorithm so as to achieve an expected optimization result. According to the method, the personalized pricing strategy is formulated by using the historical power consumption data of the user, and the demand response prediction and load scheduling algorithm is combined, so that the enthusiasm of the user to participate in the demand response is effectively improved, and meanwhile, the flexibility and efficiency of power grid operation are enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of demand response and load management of smart power plants, and specifically relates to a power grid optimization operation method and related devices based on a personalized power plant pricing strategy. Background Art

[0002] The current common pricing mechanisms for virtual power plants include fixed electricity prices, tiered electricity prices, time-segmented electricity prices and real-time electricity prices, each with its own characteristics and disadvantages.

[0003] The fixed electricity price mechanism is simple and easy to implement. All users pay the same electricity price during all time periods, which is easy for users to understand and manage. However, this mechanism lacks incentives and cannot encourage users to increase electricity consumption during low-demand periods or reduce electricity consumption during high-demand periods, thus failing to effectively balance the load on the power grid. It also fails to reflect the real-time cost of electricity production and market price changes, which can easily lead to waste of resources.

[0004] The tiered electricity price mechanism encourages users to save electricity by charging in stages, especially imposing price penalties on high-power users. However, this electricity price structure is relatively complex, difficult for users to understand and manage, and cannot reflect changes in electricity supply and demand in real time, and the response is not flexible enough.

[0005] The time-segmented electricity price mechanism sets different electricity prices according to different time periods of the day, and encourages users to use electricity during off-peak hours through high electricity prices during peak hours and low electricity prices during off-peak hours, thereby reducing the load pressure during peak hours. However, the time division is usually fixed and cannot reflect the dynamic changes in electricity supply and demand in real time. It is also difficult for some users to adjust their electricity usage habits to adapt to this time-period electricity price.

[0006] The real-time electricity price mechanism dynamically adjusts the electricity price according to the real-time supply and demand of the electricity market, and is usually updated every hour or less. This mechanism can accurately reflect the actual cost of electricity production and transmission and market price changes. However, the real-time electricity price fluctuates greatly, and it is difficult for users to predict and control the electricity cost. In addition, this mechanism has high technical requirements and requires the support of smart meters and real-time communication technology. The implementation cost is high and the technical maintenance is complex.

[0007] In general, these common pricing mechanisms have their own shortcomings in achieving a balance between electricity supply and demand and increasing user participation in demand response. Fixed electricity prices and tiered electricity prices lack real-time incentives for user behavior, time-segmented electricity price adjustments are not flexible enough, and real-time electricity prices fluctuate greatly and are highly technology-dependent. In order to overcome these shortcomings, it is necessary to design more flexible and personalized pricing strategies, such as personalized pricing incentive mechanisms based on user historical electricity consumption data, to better adapt to user needs and market changes. Summary of the invention

[0008] In view of this, the present invention introduces a method and related device for optimizing the operation of a power grid based on a personalized power plant pricing strategy, which formulates a personalized pricing strategy by analyzing the user's historical electricity consumption data, and provides differentiated price incentives according to the user's electricity consumption pattern and demand elasticity. For example, for users who are able to use electricity during off-peak hours, a lower electricity price is provided, while for users who use electricity during peak hours, a higher electricity price is set, thereby encouraging users to adjust their electricity consumption behavior.

[0009] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0010] In a first aspect, the present invention provides a method for optimizing power grid operation based on a personalized power plant pricing strategy, comprising the following steps:

[0011] Collect users' historical electricity consumption data;

[0012] Aggregate historical electricity consumption data to obtain electricity consumption characteristic data that characterizes the user's electricity consumption characteristics;

[0013] Extracting clustering feature indicators from the power consumption feature data, and clustering users according to the extracted clustering feature indicators;

[0014] For each category of users, a corresponding personalized pricing strategy is matched. The personalized pricing strategy is used to encourage users to optimize their electricity consumption under specific grid loads or electricity prices based on their electricity consumption data;

[0015] Use the pre-trained demand response prediction model to predict the user's electricity consumption response under different pricing strategies;

[0016] According to the predicted power consumption response and the corresponding pricing strategy, the load dispatch algorithm is used to optimize the operation of the power system to achieve the expected optimization results.

[0017] Furthermore, clustering characteristic indicators include peak power consumption period, total power consumption and load change, and the clustered users are divided into peak users, stable users and valley users based on the peak power consumption period, total power consumption and load change indicators.

[0018] Furthermore, for each category of users, a corresponding personalized pricing strategy is matched, including:

[0019] Assigning critical peak pricing strategies to peak users. Critical peak pricing strategies are used to incentivize users to reduce electricity consumption when the grid load is high.

[0020] Assigning time-zoned pricing strategies to smooth users. Time-zoned pricing strategies are used to incentivize users to use more electricity when costs are lower and reduce electricity use during peak hours.

[0021] Assign real-time pricing strategies to off-peak users, which are used to incentivize users to reduce electricity consumption during price peaks.

[0022] Furthermore, after collecting the historical electricity consumption data of the user, the historical electricity consumption data is preprocessed, and the preprocessing process includes:

[0023] Use the nearest neighbor filling method to fill in missing values ​​in historical electricity consumption data or delete records with missing values;

[0024] Use statistical methods such as standard deviation or box plots to detect and remove outliers in historical electricity consumption data;

[0025] All historical electricity consumption data are standardized using the Z-score method.

[0026] Furthermore, the expected optimization results include:

[0027] Cost minimization, demand response optimization or peak load reduction.

[0028] Furthermore, the pre-trained demand response prediction model is trained using a support vector machine algorithm.

[0029] In a second aspect, the present invention provides a power grid optimization operation device based on a personalized power plant pricing strategy, comprising:

[0030] Data collection module, used to collect historical electricity consumption data of users;

[0031] A feature collection module is used to aggregate historical power consumption data to obtain power consumption feature data that characterizes the power consumption characteristics of users;

[0032] A clustering module, used to extract clustering characteristic indicators from the power consumption characteristic data, and cluster users according to the extracted clustering characteristic indicators;

[0033] The personalized electricity price module is used to match the corresponding personalized pricing strategy for each category of users. The personalized pricing strategy is used to motivate users to optimize electricity consumption under specific grid loads or electricity prices based on their electricity consumption data;

[0034] A prediction module, used to predict the user's electricity consumption response under different pricing strategies using a pre-trained demand response prediction model;

[0035] The optimization operation module is used to optimize the operation of the power system using a load dispatch algorithm based on the predicted power consumption response and the corresponding pricing strategy to achieve the expected optimization results.

[0036] In a third aspect, the present invention provides a computer device, the device comprising a processor and a memory:

[0037] The memory is used to store the computer program and send the instructions of the computer program to the processor;

[0038] The processor executes a power grid optimization operation method based on a personalized power plant pricing strategy as described in the first aspect according to the instructions of the computer program.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a power grid optimization operation method based on a personalized power plant pricing strategy as in the first aspect.

[0040] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements a power grid optimization operation method based on a personalized power plant pricing strategy according to the first aspect.

[0041] In summary, the present invention provides a method and related device for optimizing the operation of a power grid based on a personalized power plant pricing strategy, including collecting historical power consumption data of users; aggregating the historical power consumption data to obtain higher-level power consumption feature data; extracting clustering feature indicators from the power consumption feature data, and clustering users according to the extracted clustering feature indicators; matching the corresponding personalized pricing strategy for each category of users, the personalized pricing strategy is used to motivate users to optimize power consumption under specific power grid loads or electricity prices based on their power consumption data; using a pre-trained demand response prediction model to predict the power consumption response of users under different pricing strategies; and using a load scheduling algorithm to optimize the operation of the power system based on the predicted power consumption response and the corresponding pricing strategy to achieve the expected optimization results. The present invention uses historical power consumption data of users to formulate personalized pricing strategies, and combines demand response prediction with load scheduling algorithms to achieve a more accurate balance between power supply and demand, effectively improve the enthusiasm of users to participate in demand response, and enhance the flexibility and efficiency of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A flowchart of a power grid optimization operation method based on a personalized power plant pricing strategy provided by an embodiment of the present invention;

[0044] Figure 2A block diagram of a power grid optimization operation device based on a personalized power plant pricing strategy provided by an embodiment of the present invention;

[0045] Figure 3 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1 This embodiment provides a method for optimizing the operation of a power grid based on a personalized power plant pricing strategy, comprising the following steps:

[0048] S1: Collect users’ historical electricity consumption data.

[0049] It should be noted that this step collects the user's electricity consumption records, including but not limited to daily electricity consumption, electricity consumption time period, seasonal electricity consumption pattern, etc. These data can be collected by deploying smart meters on the user side. In addition, these smart meters allow the frequency of data collection to be set according to the size of the time granularity (such as every minute, every hour), ensuring that subtle changes in the user's electricity consumption can be captured, and then the collected data is regularly uploaded to the virtual power plant big data analysis platform, including daily and hourly electricity consumption, as well as the electricity consumption of specific appliances.

[0050] S2: Aggregate the historical electricity consumption data to obtain electricity consumption characteristic data that characterizes the user's electricity consumption characteristics.

[0051] It should be noted that data is aggregated according to time windows (such as hours, days, and weeks) to generate higher-level power consumption features, such as total daily power consumption, hourly peak power consumption, etc. These aggregated data have higher value and can be directly used to extract features of user behavior patterns in machine learning, such as peak power consumption time periods, power consumption volatility, and the proportion of dispatchable loads.

[0052] S3: extracting clustering feature indicators from the power consumption feature data, and clustering the users according to the extracted clustering feature indicators.

[0053] It should be noted that clustering feature indicators refer to factors that can be used to distinguish different types of users, such as electricity consumption patterns, electricity consumption time preferences, etc. Through clustering algorithms (such as K-means), users with similar electricity consumption behaviors can be grouped together. This helps power companies customize different service strategies for different types of users.

[0054] S4: For each category of users, a corresponding personalized pricing strategy is matched. The personalized pricing strategy is used to encourage users to optimize electricity consumption under specific grid loads or electricity prices based on their electricity consumption data.

[0055] It should be noted that once users are classified, personalized electricity price strategies can be designed for each group of users. For example, for those users who use more electricity during off-peak hours, lower prices can be offered to encourage them to continue this behavior; while for those users who use more electricity during peak hours, higher electricity prices can be offered to encourage them to adjust their electricity usage time.

[0056] S5: Use the pre-trained demand response prediction model to predict the user's electricity consumption response under different pricing strategies.

[0057] It should be noted that the demand response prediction model is used to estimate how users change their electricity consumption behavior under different electricity price conditions. This model can be developed based on machine learning algorithms to predict future user behavior by learning from historical data.

[0058] S6: Based on the predicted power consumption response and the corresponding pricing strategy, a load dispatch algorithm is used to optimize the operation of the power system to achieve the expected optimization results.

[0059] It should be noted that this step is to optimize the operation of the power system based on the information obtained in the previous steps. By adjusting the power generation plan, the use of energy storage facilities, and the management of the transmission and distribution network, power companies can better respond to different power demands, reduce waste, and improve efficiency. The role of the load dispatch algorithm here is to determine the optimal resource allocation method so that the power supply can meet demand while maintaining cost-effectiveness.

[0060] This embodiment provides a method for optimizing the operation of a power grid based on a personalized power plant pricing strategy. By analyzing the user's historical electricity consumption data and formulating a personalized pricing strategy based on it, it can more effectively encourage users to use electricity during non-peak hours, thereby reducing the pressure on the power grid during peak hours and achieving a dynamic balance between power supply and demand. Using the demand response prediction model, power companies can predict the user's electricity consumption behavior under different pricing strategies in advance and optimize the operation of the power system accordingly. Through the load scheduling algorithm, the optimal configuration of power resources can be achieved, unnecessary energy waste can be reduced, and the operating efficiency of the entire power grid can be improved.

[0061] In one embodiment of the present invention, clustering characteristic indicators include peak power consumption period, total power consumption and load change, and clustered users are divided into peak users, stable users and valley users based on the peak power consumption period, total power consumption and load change indicators.

[0062] In this embodiment, when using the clustering algorithm to classify user patterns, the selected clustering features are three indicators: peak power consumption period, total power consumption, and load change. Then, users are divided into peak users, stable users, and valley users. The specific process of the algorithm is as follows:

[0063] First, select the appropriate number of clusters K: the elbow rule or silhouette coefficient method can be used to evaluate the clustering quality under different numbers of clusters and select the optimal number of clusters K.

[0064] Then initialize the cluster centers: randomly select or use the K-means++ method to optimize the initialization.

[0065] Then, we perform assignment and update: assign each user to the nearest cluster center according to its feature vector, and then update the center of each cluster.

[0066] It then iterates until convergence: the assignment and update steps are repeated until the change in cluster centers is very small or a preset number of iterations is reached.

[0067] Finally, the clustering result can be obtained: all users will be divided into different clusters, where each cluster represents a group of users with similar power consumption patterns and behavioral characteristics.

[0068] This embodiment uses a clustering algorithm to automatically classify users according to their electricity usage patterns, thereby improving the accuracy and efficiency of user classification and providing a scientific basis for personalized pricing by deeply exploring users' electricity usage characteristics and behavior patterns.

[0069] In one embodiment of the present invention, for each category of users, a corresponding personalized pricing strategy is matched, including:

[0070] (1) Assigning a critical peak pricing (CPP) strategy to peak users. The critical peak pricing strategy is used to encourage users to reduce electricity consumption when the grid load is high.

[0071] Peak users are characterized by high electricity consumption during periods of high grid load, which may cause grid overload and increase the marginal cost of electricity supply. The characteristic of critical peak pricing is that additional high prices are implemented when the load of the power system approaches or reaches the maximum capacity. Users will be notified of the occurrence of critical peak events in advance so that they can make adjustments. By implementing critical peak pricing, such users can be incentivized to reduce electricity consumption by significantly increasing electricity prices when the grid needs it most.

[0072] (2) Assigning a time-of-use pricing (TOU) strategy to stable users. The TOU pricing strategy is used to incentivize users to use more electricity when costs are lower and reduce electricity consumption during peak hours.

[0073] The electricity consumption pattern of stable users is relatively balanced, and the distribution of electricity consumption is relatively stable throughout the day. Time-zone pricing can encourage stable users to increase electricity consumption during periods with lower electricity prices, such as at night or during non-peak hours, by setting electricity prices for different time periods, thereby helping to further balance the load on the power grid. This pricing model can incentivize users to use more electricity when costs are lower, while suppressing electricity consumption during peak hours through high electricity prices, helping virtual power plants to better manage loads.

[0074] (3) Assign a real-time pricing (RTP) strategy to off-peak users. The real-time pricing strategy is used to encourage users to reduce electricity consumption during peak price periods.

[0075] The characteristic of off-peak users is that they consume more electricity during periods when the grid load is low. Real-time pricing can reflect the instant supply and demand status of the electricity market and provide dynamic price signals, so that off-peak users can optimize their electricity consumption plans by taking advantage of times when electricity prices are lower, such as at night or other non-peak hours. In addition, real-time pricing can incentivize such users to reduce electricity consumption during peak prices, which helps to better utilize electricity resources and reduce electricity waste.

[0076] This embodiment designs a personalized pricing mechanism based on user behavior and demand elasticity through historical electricity consumption data analysis to improve the accuracy and effectiveness of pricing strategies. In-depth research is conducted on users' electricity consumption behaviors and response patterns, and incentive mechanisms that meet users' actual needs and preferences are designed to improve the effectiveness of demand response and user participation. Through economic incentives and behavioral guidance, users are encouraged to actively participate in demand response and achieve a win-win situation.

[0077] In one embodiment of the present invention, in order to improve the quality of collected data, the power data needs to be cleaned and integrated.

[0078] For data with missing values, you can use the nearest neighbor filling method to fill it, or directly delete the missing data record.

[0079] For abnormal data, you can use statistical methods such as standard deviation or box plot to detect it, and then delete the record to ensure the accuracy of the data.

[0080] In addition, since the magnitude of electricity consumption data of different users may vary greatly, standardization is required. Therefore, Z-score can be used to standardize user data features to avoid the dominant role of some features in the clustering process.

[0081] In one embodiment of the present invention, a support vector machine (SVM) is selected to build a prediction model, and then the model is trained using training set data, and parameter tuning and cross-validation are performed. The performance of the model is then evaluated on the test set, mainly using the mean square error (MSE) indicator as the loss function. The trained model is then used to predict the user's electricity consumption response under different pricing mechanisms. The impact of the three pricing mechanisms on user electricity consumption behavior is analyzed.

[0082] In one embodiment of the present invention, when designing a load dispatch algorithm, the main goal is to optimize the operation of the power system according to the predicted electricity demand and pricing strategy to achieve cost minimization, demand response optimization or peak load reduction.

[0083] Cost minimization: Reduce overall electricity costs, especially during peak price hours.

[0084] Demand response optimization: Adjusting customer electricity usage behavior in response to price changes or grid demand.

[0085] Peak shaving: Reducing the load on the grid by spreading electricity demand during peak hours.

[0086] The first step is to define the decision variables, which usually include power output in each time period, the time to start or shut down large equipment, and load transfer decisions in the power system. After these variables are established, a dynamic programming algorithm is selected to optimize the values ​​of these decision variables. Dynamic programming can help determine how to adjust the generation and distribution of electricity at each point in time to adapt to changes in consumer demand or respond to different electricity price policies. Finally, tests are conducted to verify whether the algorithm can operate under various preset scenarios, such as high demand, low demand, equipment failure, etc. In addition, the stability and efficiency of the algorithm during continuous operation need to be checked. By simulating these different conditions, the adaptability and effectiveness of the algorithm to actual grid operations can be evaluated to ensure that the algorithm can meet the expected performance standards before actual deployment.

[0087] This embodiment combines the demand response prediction model and the optimal dispatch algorithm to achieve dynamic optimization of the power system load and improve the utilization efficiency of power resources. While meeting the power demand of users, it reduces the peak load of the power system, reduces the pressure on the power grid and reduces the operating cost.

[0088] Based on the same inventive concept, the embodiment of the present application also provides a power grid optimization operation device based on a personalized power plant pricing strategy for implementing the power grid optimization operation method based on a personalized power plant pricing strategy involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiment of the power grid optimization operation device based on a personalized power plant pricing strategy provided below can be referred to the limitations of the power grid optimization operation method based on a personalized power plant pricing strategy above, and will not be repeated here.

[0089] See also Figure 2 This embodiment provides a power grid optimization operation device based on a personalized power plant pricing strategy, including:

[0090] Data collection module, used to collect historical electricity consumption data of users;

[0091] A feature collection module is used to aggregate historical power consumption data to obtain power consumption feature data that characterizes the power consumption characteristics of users;

[0092] A clustering module, used to extract clustering characteristic indicators from the power consumption characteristic data, and cluster users according to the extracted clustering characteristic indicators;

[0093] The personalized electricity price module is used to match the corresponding personalized pricing strategy for each category of users. The personalized pricing strategy is used to motivate users to optimize electricity consumption under specific grid loads or electricity prices based on their electricity consumption data;

[0094] A prediction module, used to predict the user's electricity consumption response under different pricing strategies using a pre-trained demand response prediction model;

[0095] The optimization operation module is used to optimize the operation of the power system using a load dispatch algorithm based on the predicted power consumption response and the corresponding pricing strategy to achieve the expected optimization results.

[0096] In the clustering module, clustering characteristic indicators include peak power consumption period, total power consumption and load change. Based on the peak power consumption period, total power consumption and load change indicators, the clustered users are divided into peak users, stable users and valley users.

[0097] In the personalized electricity price module, for each category of users, a corresponding personalized pricing strategy is matched, including:

[0098] Assigning critical peak pricing strategies to peak users. Critical peak pricing strategies are used to incentivize users to reduce electricity consumption when the grid load is high.

[0099] Assigning time-zoned pricing strategies to smooth users. Time-zoned pricing strategies are used to incentivize users to use more electricity when costs are lower and reduce electricity use during peak hours.

[0100] Assign real-time pricing strategies to off-peak users, which are used to incentivize users to reduce electricity consumption during price peaks.

[0101] In the data collection module, after collecting the user's historical electricity consumption data, the historical electricity consumption data is also preprocessed. The preprocessing process includes:

[0102] Use the nearest neighbor filling method to fill in missing values ​​in historical electricity consumption data or delete records with missing values;

[0103] Use statistical methods such as standard deviation or box plots to detect and remove outliers in historical electricity consumption data;

[0104] All historical electricity consumption data are standardized using the Z-score method.

[0105] In the optimization run module, the expected optimization results include:

[0106] Cost minimization, demand response optimization or peak load reduction.

[0107] In the prediction module, the pre-trained demand response prediction model is trained using the support vector machine algorithm.

[0108] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0109] Reference Figure 3 An embodiment of the present invention further provides a computer device, comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, it implements a power grid optimization operation method based on a personalized power plant pricing strategy as described in any one of the above methods.

[0110] The computer device may be a desktop computer, a notebook, a PDA, a cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 3 It is only an example of a computer device and does not constitute a limitation of the computer device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0111] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0112] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may include both an internal storage unit and an external storage device of the computer device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is to be output.

[0113] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for optimizing operation of a power grid based on a personalized power plant pricing strategy as described in any one of the above methods is implemented.

[0114] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0115] An embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements a power grid optimization operation method based on a personalized power plant pricing strategy as described in any one of the above methods.

[0116] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0118] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing power grid operation based on personalized power plant pricing strategy, characterized in that: The steps include: Collect users' historical electricity consumption data; Aggregating the historical electricity consumption data to obtain electricity consumption characteristic data representing the electricity consumption characteristics of the user; Extracting clustering characteristic indicators from the power consumption characteristic data, and clustering the users according to the extracted clustering characteristic indicators; For each category of users, matching a corresponding personalized pricing strategy; The personalized pricing strategy is used to motivate the user to optimize electricity consumption under a specific grid load or electricity price based on the user's electricity consumption data; Predicting the power consumption response of the user under different pricing strategies using a pre-trained demand response prediction model; According to the predicted power consumption response and the corresponding pricing strategy, the load dispatch algorithm is used to optimize the operation of the power system to achieve the expected optimization results.

2. The method for optimizing power grid operation based on personalized power plant pricing strategy according to claim 1, characterized in that: The clustering characteristic indicators include peak power consumption period, total power consumption and load change. Based on the peak power consumption period, the total power consumption and the load change indicators, the clustered users are divided into peak users, stable users and valley users.

3. The method for optimizing power grid operation based on personalized power plant pricing strategy according to claim 2, characterized in that: For each category of users, a corresponding personalized pricing strategy is matched, including: Allocating a critical peak pricing strategy to the peak users; the critical peak pricing strategy is used to encourage users to reduce electricity consumption when the grid load is high; Assigning a time-zoned pricing strategy to the steady users; the time-zoned pricing strategy is used to incentivize users to use more electricity when costs are low and reduce electricity consumption during peak hours; A real-time pricing strategy is allocated to the off-peak users; the real-time pricing strategy is used to encourage users to reduce electricity consumption when prices are at peak times.

4. The method for optimizing power grid operation based on personalized power plant pricing strategy according to claim 1, characterized in that: After collecting the user's historical electricity consumption data, the historical electricity consumption data is preprocessed, and the preprocessing process includes: Filling missing values ​​in the historical electricity consumption data using a nearest neighbor filling method or deleting records of the missing values; Using statistical methods such as standard deviation or box plot to detect and delete outliers in the historical electricity consumption data; The historical electricity consumption data is standardized using the Z-score method.

5. The method for optimizing power grid operation based on personalized power plant pricing strategy according to claim 1, characterized in that: Expected optimization results include: Cost minimization, demand response optimization or peak load reduction.

6. The method for optimizing power grid operation based on personalized power plant pricing strategy according to claim 1, characterized in that: The pre-trained demand response prediction model is trained using the support vector machine algorithm.

7. A power grid optimization operation device based on personalized power plant pricing strategy, characterized in that: include: Data collection module, used to collect historical electricity consumption data of users; A feature collection module, used to aggregate the historical power consumption data to obtain power consumption feature data representing the power consumption features of the user; A clustering module, used to extract clustering characteristic indicators from the power consumption characteristic data, and cluster users according to the extracted clustering characteristic indicators; A personalized electricity price module is used to match a corresponding personalized pricing strategy for each category of users, wherein the personalized pricing strategy is used to motivate users to optimize electricity consumption under a specific grid load or electricity price based on their electricity consumption data; A prediction module is used to predict the user's electricity consumption response under different pricing strategies using a pre-trained demand response prediction model; The optimization operation module is used to optimize the operation of the power system using a load dispatch algorithm based on the predicted power consumption response and the corresponding pricing strategy to achieve the expected optimization results.

8. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a power grid optimization operation method based on a personalized power plant pricing strategy as described in any one of claims 1-6 according to the instructions of the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for optimizing the operation of a power grid based on a personalized power plant pricing strategy as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, a method for optimizing operation of a power grid based on a personalized power plant pricing strategy as described in any one of claims 1 to 6 is implemented.

Images