A rule engine-based power transaction settlement strategy intelligent configuration method

Abstract

The application provides a rule engine-based power transaction settlement strategy intelligent configuration method, which comprises the following steps: obtaining transaction data and external factors from a power transaction market, performing pretreatment operations such as data cleaning, standardization and normalization on the obtained data, inputting the pretreated data into a machine learning model to generate a machine learning strategy, performing weight addition on the machine learning strategy and an expert strategy formed by combining business rules and experience in an expert knowledge base to generate a final power transaction settlement strategy, writing the generated power transaction settlement strategy into a constructed rule engine library to form a dynamically adjustable settlement strategy rule library, and writing the generated power transaction settlement strategy into the constructed rule engine library to form the dynamically adjustable settlement strategy rule library. The application not only improves the configuration efficiency of the power transaction settlement strategy, but also enhances the adaptability and timeliness of the strategy, and is particularly suitable for coping with complex power transaction environments with dynamic market changes.

Description

Technical Field

[0001] The present invention relates to the field of power trading, and in particular to a method for intelligently configuring power trading settlement strategies based on a rule engine. The method aims to improve the efficiency and adaptability of power trading settlement strategy configuration by using a rule engine and an intelligent algorithm. Background Art

[0002] With the gradual opening up and increasing marketization of the power market, the development of power trading settlement strategies has become increasingly complex due to the presence of various trading formats, including spot and medium- and long-term transactions. Traditional power trading settlement strategies often rely on empirical rules and manual configuration, resulting in low efficiency, untimely policy updates, and difficulty adapting to rapid market changes and complex and volatile trading environments.

[0003] In the existing technology, although there are automated configuration methods based on data analysis, most of them lack the full utilization of expert knowledge and real-time feedback, resulting in insufficient flexibility and accuracy of the strategy. Summary of the Invention

[0004] The present invention proposes an intelligent configuration method for power trading settlement strategies based on a rule engine. This method generates configuration strategies by learning from market data and, in combination with an expert knowledge base, dynamically adjusts and optimizes power trading settlement strategies, thereby improving the efficiency, adaptability, and timeliness of strategy configuration.

[0005] A method for intelligently configuring power transaction settlement strategies based on a rule engine includes the following steps:

[0006] Data preparation and feature engineering: Acquire transaction data and external factors from the power trading market. The transaction data includes historical electricity prices, transaction volumes, and power demand. The external factors include power dispatch information, user electricity usage records, relevant policies and regulations, and meteorological data. The collected data is cleaned, outlier processed, and standardized.

[0007] Machine learning model training: Using preprocessed data, a machine learning model is used to train the power trading settlement strategy and generate a machine learning strategy;

[0008] Intelligent configuration strategy: The machine learning strategy is weighted and summed with the expert strategy formed by business rules and experience in the expert knowledge base to generate the final power transaction settlement strategy. The weighted sum is used to dynamically adjust the relative weights of the expert strategy and the machine learning strategy based on market feedback and actual demand.

[0009] Update and optimize the rule engine library: Write the generated power transaction settlement strategy into the constructed rule engine library to form a settlement strategy rule library that can be dynamically adjusted;

[0010] Real-time monitoring and feedback: By real-time monitoring of dynamic changes in the power market and combining market feedback data, the power trading settlement strategies in the settlement strategy rule base are dynamically adjusted and optimized. The adjusted power trading settlement strategies are then input into the rule engine and machine learning model for updating and optimization.

[0011] Furthermore, the machine learning model includes a LightGBM model or a deep neural network model.

[0012] Furthermore, the machine learning model adopts the LightGBM model, and the machine learning model training specifically includes:

[0013] Step 2.1. Model initialization: Use the LightGBM library to build the LightGBM model, define the loss function mean square error (MSE), the evaluation indicator root mean square error (RMSE), and the model parameters. The maximum number of leaves per tree in the model parameters is 31, the tree depth is -1, the learning rate is 0.05, and the total number of trees is 1000. Other parameters use the default recommended values; the loss function mean square error (MSE) is defined as follows:

[0014]

[0015] Among them, y i is the actual value, i.e. the actual electricity price or actual transaction volume in the electricity market, is the model prediction value, that is, the electricity price or transaction volume predicted by LightGBM; n is the total number of data points; the mean square error (MSE) is an indicator that measures the difference between the model prediction value and the actual value. It reflects the overall level of prediction error by averaging the square of the difference between the predicted value and the actual value of each data point; the smaller the MSE value, the more accurate the model prediction; the evaluation indicator root mean square error (RMSE) is defined as follows:

[0016]

[0017] RMSE is the square root of MSE, which is used to more intuitively represent the size of the error;

[0018] Step 2.2, model training: input the preprocessed training data into the LightGBM model, gradually build a set of decision trees through the gradient boosting algorithm, optimize the loss function, and during the training process, the model automatically processes category features, calculates the importance of features, and generates prediction values ​​based on multiple decision trees;

[0019] Step 2.3, Model Tuning: Use cross-validation and grid search to adjust the model's hyperparameters, including learning rate, maximum depth, number of leaf nodes, and subsampling rate, to improve the model's generalization ability and prediction accuracy;

[0020] Step 2.4, Model Validation: Evaluate model performance on the validation set, record prediction error and feature importance, and retrain or fine-tune the model as needed.

[0021] Furthermore, the machine learning model adopts the LightGBM model, and the intelligent configuration strategy specifically includes:

[0022] Step 3.1. Initialize weights: Let the weight of LightGBM prediction be ω L , the weight of the expert knowledge base prediction value is ω E , set the initial weights ω of the LightGBM model and the expert knowledge base L =0.5,ω E =0.5;

[0023] Step 3.2, fuzzy rule setting: Set fuzzy rules based on the market environment and transaction data, define the fuzzy sets of market changes and strategy effects and the corresponding membership functions. The membership function uses the Sigmoid function, which is defined as:

[0024]

[0025] Among them, FB L It is an indicator related to LightGBM prediction obtained from market feedback. The indicators related to LightGBM prediction include prediction error and accuracy. α is a parameter that controls the rate of change of weights, which is determined based on historical data optimization. Th is the threshold for weight adjustment, which is determined based on actual market feedback and strategy requirements.

[0026] Step 3.3: Construct a fuzzy inference system: Construct a fuzzy inference system based on the fuzzy rules defined in step 3.2. The fuzzy inference system dynamically adjusts the weight of the expert knowledge base prediction value according to real-time market feedback data. E and the weight ω of the LightGBM prediction value L , wherein the real-time market feedback data includes forecast error, rate of return, and stability;

[0027] Step 3.4, weight adjustment: Whenever the system obtains new market feedback data, calculate the effect of the current strategy and adjust the weight through the fuzzy inference system built in step 3.3. When the market volatility is large, increase the weight of the LightGBM prediction value ω L When the market is stable, increase the weight of the expert knowledge base prediction value;

[0028] Step 3.5, strategy execution: Generate the final strategy based on the adjusted weights. The calculation of the final strategy combines the LightGBM prediction value and the expert knowledge base recommendation value. The calculation formula is:

[0029]

[0030] The final strategy is input into the rule engine for execution, and the strategy execution effect is monitored in real time, with continuous fuzzy reasoning and weight adjustment.

[0031] Furthermore, the rule engine library supports modular design based on LiteFlow, and can dynamically add or update rule modules to adapt to market changes and strategic requirements.

[0032] Furthermore, the expert knowledge base includes the medium- and long-term trading rules, spot trading rules, retail rules, historical violation events, technical equipment knowledge and abnormal event handling experience of the electricity market, and can be dynamically updated and expanded.

[0033] Furthermore, the machine learning strategy is weighted and summed with the expert strategy formed by the business rules and experience in the expert knowledge base, and an adaptive fuzzy weighted algorithm is used to weight the expert strategy and the machine learning strategy, and the weights of the two are dynamically adjusted to adapt to the complex changes in the power market and generate the final power transaction settlement strategy.

[0034] An electronic device comprising: a computer-readable storage medium and a processor;

[0035] The computer-readable storage medium is used to store executable instructions;

[0036] The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the intelligent configuration method of power transaction settlement strategy based on the rule engine.

[0037] A non-transitory computer-readable storage medium stores a computer program, which, when executed by a processor, implements the intelligent configuration method for power transaction settlement strategy based on a rule engine.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. Intelligent configuration: Combining machine learning with expert knowledge, it automatically generates power trading and settlement strategies, reduces manual intervention, and improves configuration efficiency and accuracy.

[0040] 2. Dynamic adjustment: Dynamic configuration and real-time adjustment of strategies are achieved through the rule engine, which enhances the flexibility and adaptability of strategies.

[0041] 3. Self-optimization: Through real-time monitoring and feedback, strategies can self-learn and optimize, continuously improving the scientificity and rationality of electricity trading. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1It is a diagram of the overall implementation steps of the present invention.

[0043] Figure 2 This is a system structure diagram of the present invention.

[0044] Figure 3 This is a flow chart of a method for intelligently configuring power transaction settlement strategies based on a rule engine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0046] See also Figure 1-3 The embodiment of the present invention provides a method for intelligently configuring power transaction settlement strategies based on a rule engine, comprising the following steps:

[0047] Step 1: Data preparation and feature engineering

[0048] Step 1 corresponds to Figure 1 The data collection and data preprocessing part specifically includes: Step 1.1, data collection: collecting transaction data and external factors from the power market. The transaction data includes historical electricity prices, transaction volumes, and power demand. The external factors include power dispatch information, user electricity consumption records, relevant policies and regulations, and meteorological data.

[0049] Step 1.2: Data Preprocessing: Perform data cleaning, outlier handling, missing value filling, and normalization on the collected multi-dimensional data. For time series data, extract temporal features (such as hourly, daily, weekly, and monthly) and construct lag features to capture temporal dependencies.

[0050] Step 1.3, feature selection: Based on business understanding and correlation analysis, select features that have a significant impact on the power transaction settlement strategy from the data preprocessed in step 1.2 as training data to form Figure 2 The CSV file shown below can reduce model complexity and improve computational efficiency.

[0051] Step 2: LightGBM model training

[0052] Step 2 corresponds to Figure 1 The LightGBM model part specifically includes:

[0053] Step 2.1, model initialization: Use the LightGBM library to build the LightGBM model. The model structure is as follows Figure 2 As shown in the dotted box in the figure, the loss function mean square error (MSE), the evaluation indicator root mean square error (RMSE), and the model parameters are defined. The maximum number of leaves per tree in the model parameters is 31, the tree depth is -1, the learning rate is 0.05, and the total number of trees is 1000. Other parameters use the default recommended values. The loss function mean square error MSE is defined as follows:

[0054]

[0055] Among them, y i is the actual value, i.e. the actual electricity price or actual transaction volume in the electricity market, is the model prediction value, that is, the electricity price or transaction volume predicted by LightGBM. n is the total number of data points. The mean square error (MSE) is an indicator that measures the difference between the model prediction value and the actual value. It reflects the overall level of prediction error by averaging the square of the prediction error (the difference between the predicted value and the actual value) of each data point. The smaller the MSE value, the more accurate the model prediction. The evaluation indicator root mean square error RMSE is defined as follows:

[0056]

[0057] RMSE is the square root of MSE and is used to more intuitively represent the magnitude of the error because it is in the same units as the original data. It provides a more understandable measure of model error, especially in the electricity market, for comparing the difference between model predictions and actual electricity prices or trading volumes.

[0058] Step 2.2, Model Training: Input the preprocessed training data into the LightGBM model, and gradually build a set of decision trees using the gradient boosting algorithm to optimize the loss function. During the training process, the model automatically processes category features, calculates feature importance, and generates predictions based on multiple decision trees.

[0059] Step 2.3, Model Tuning: Use cross-validation and grid search to adjust the model's hyperparameters, such as learning rate, maximum depth, number of leaf nodes, subsampling rate, etc., to improve the model's generalization ability and prediction accuracy.

[0060] Step 2.4, Model Validation: Evaluate model performance on the validation set, record prediction error and feature importance, and retrain or fine-tune the model as needed.

[0061] Step 3: Intelligent configuration strategy:

[0062] To combine expert knowledge with the prediction results of the machine learning model (i.e., the machine learning strategy) to form the final configuration strategy, an adaptive fuzzy weighting algorithm is used. This algorithm can dynamically adjust the weights between the expert strategy and the machine learning strategy to ensure the optimal combination of strategies under different market environments. Step 3 specifically includes:

[0063] Step 3.1. Initialize weights: Let the weight of LightGBM prediction be ω L , the weight of the expert knowledge base prediction value is ω E , set the initial weights ω of the LightGBM model and the expert knowledge base L =0.5,ω E =0.5, the weight can be initially set based on the performance of historical data.

[0064] Step 3.2, fuzzy rule setting: Set fuzzy rules based on the market environment and trading data, define fuzzy sets of indicators such as market changes and strategy effects (such as high, medium, and low) and corresponding membership functions. The membership function uses the Sigmoid function, which is defined as:

[0065]

[0066] Among them, FB L It is an indicator related to LightGBM prediction obtained from market feedback (such as prediction error, accuracy, etc.), α is a parameter that controls the rate of change of weights, which is usually determined based on historical data optimization; Th is the threshold for weight adjustment, which is determined based on actual market feedback and strategy requirements.

[0067] Step 3.3: Construct a fuzzy inference system: Based on the fuzzy rules defined in step 3.2, a fuzzy inference system is constructed. The system can dynamically adjust the weight of the expert knowledge base prediction value according to real-time market feedback data (forecast error, rate of return, stability). E and the weight ω of the LightGBM prediction value L .

[0068] Step 3.4, weight adjustment: Whenever the system obtains new market feedback data, calculate the effect of the current strategy and adjust the weight through the fuzzy inference system built in step 3.3. When the market volatility is large, increase the weight of the LightGBM prediction value ω L ; When the market is stable, increase the weight of the expert knowledge base prediction value.

[0069] Step 3.5, Strategy Execution: Generate the final strategy based on the adjusted weights. The calculation of the final strategy combines the LightGBM prediction value and the expert knowledge base recommendation value, and the calculation formula is:

[0070]

[0071] The final strategy is input into the rule engine for execution, and the strategy execution effect is monitored in real time, with continuous fuzzy reasoning and weight adjustment.

[0072] Step 4: Update and optimize the rule engine library

[0073] Once a strategy is generated, the system incorporates it into the rule engine library and, through integration with the real-time monitoring system, continuously obtains market feedback. Based on this feedback, the system conducts online learning and optimization of the strategy, forming a closed-loop mechanism for continuous self-optimization. Guided by real-time monitoring, the strategies in the rule engine library can automatically adjust to the ever-changing market environment. The rule engine library supports a modular design based on LiteFlow, enabling the dynamic addition or update of rule modules to adapt to market changes and strategy requirements.

[0074] Step 5: Real-time monitoring and feedback

[0075] The rule engine monitors the changes in the power market in real time and collects relevant feedback data, such as actual electricity prices, transaction volume, revenue and other key indicators. Figure 1 The intelligent configuration strategy and data preprocessing module in the system are compared and analyzed with pre-set key performance indicators (such as prediction error, yield, stability, etc.). The LightGBM model and fuzzy inference system are used to dynamically adjust the parameter configuration and weight distribution of the strategy to continuously optimize the strategy performance.

[0076] The smaller the strategy's prediction error, the higher its yield, and the greater its stability, the more reasonable the strategy is and the better it can adapt to changes in the electricity market. The rules engine continuously monitors strategy execution, promptly identifies issues, and makes optimization adjustments, forming a closed-loop mechanism of self-learning and optimization. This ensures that the strategy remains optimal, generating stable and reliable returns for electricity trading participants.

[0077] The present invention proposes to automatically generate and optimize settlement strategies by combining machine learning models with expert knowledge bases, which can dynamically adapt to market changes and improve the efficiency and accuracy of electricity transactions.

[0078] Another aspect of the present invention provides an electronic device comprising: a computer-readable storage medium and a processor;

[0079] The computer-readable storage medium is used to store executable instructions;

[0080] The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the intelligent configuration method of power transaction settlement strategy based on the rule engine.

[0081] Another aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent configuration method for power transaction settlement strategy based on a rule engine.

[0082] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0083] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0084] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

[0087] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for intelligent configuration of power transaction settlement strategy based on rule engine, characterized in that: The following steps are involved: Data preparation and feature engineering: Acquire transaction data and external factors from the power trading market. The transaction data includes historical electricity prices, transaction volumes, and power demand. The external factors include power dispatch information, user electricity usage records, relevant policies and regulations, and meteorological data. The collected data is cleaned, outlier processed, and standardized. Machine learning model training: Using preprocessed data, a machine learning model is used to train the power trading settlement strategy and generate a machine learning strategy; Intelligent configuration strategy: The machine learning strategy is weighted and summed with the expert strategy formed by business rules and experience in the expert knowledge base to generate the final power transaction settlement strategy. The weighted sum is used to dynamically adjust the relative weights of the expert strategy and the machine learning strategy based on market feedback and actual demand. Update and optimize the rule engine library: Write the generated power transaction settlement strategy into the constructed rule engine library to form a settlement strategy rule library that can be dynamically adjusted; Real-time monitoring and feedback: By real-time monitoring of dynamic changes in the power market and combining market feedback data, the power trading settlement strategies in the settlement strategy rule base are dynamically adjusted and optimized. The adjusted power trading settlement strategies are then input into the rule engine and machine learning model for updating and optimization.

2. The method according to claim 1, characterized in that The machine learning model includes a LightGBM model or a deep neural network model.

3. The method according to claim 2, characterized in that The machine learning model adopts the LightGBM model, and the machine learning model training specifically includes: Step 2.

1. Model initialization: Use the LightGBM library to build the LightGBM model, define the loss function mean square error (MSE), the evaluation indicator root mean square error (RMSE), and the model parameters. The maximum number of leaves per tree in the model parameters is 31, the tree depth is -1, the learning rate is 0.05, and the total number of trees is 1000. Other parameters use the default recommended values; the loss function mean square error (MSE) is defined as follows: ； in, is the actual value, that is, the actual electricity price or actual transaction volume in the electricity market, is the model prediction value, that is, the electricity price or transaction volume predicted by LightGBM; is the total number of data points; the mean square error (MSE) is an indicator that measures the difference between the model's predicted value and the actual value. It reflects the overall level of prediction error by averaging the square of the difference between the predicted value and the actual value of each data point; the smaller the MSE value, the more accurate the model's prediction; the evaluation indicator root mean square error (RMSE) is defined as follows: ； RMSE is the square root of MSE, which is used to more intuitively represent the size of the error; Step 2.2, model training: input the preprocessed training data into the LightGBM model, gradually build a set of decision trees through the gradient boosting algorithm, optimize the loss function, and during the training process, the model automatically processes category features, calculates the importance of features, and generates prediction values ​​based on multiple decision trees; Step 2.3, Model Tuning: Use cross-validation and grid search to adjust the model's hyperparameters, including learning rate, maximum depth, number of leaf nodes, and subsampling rate, to improve the model's generalization ability and prediction accuracy; Step 2.4, Model Validation: Evaluate model performance on the validation set, record prediction error and feature importance, and retrain or fine-tune the model as needed.

4. The method according to claim 3, characterized in that The machine learning model adopts the LightGBM model, and the intelligent configuration strategy specifically includes: Step 3.

1. Initialize weights: Let the weight of LightGBM prediction be , the weight of the expert knowledge base prediction value is , set the initial weights of the LightGBM model and expert knowledge base =0.5, =0.5; Step 3.2, fuzzy rule setting: Set fuzzy rules based on the market environment and transaction data, define the fuzzy sets of market changes and strategy effects and the corresponding membership functions. The membership function uses the Sigmoid function, which is defined as: ； in, It is an indicator related to LightGBM prediction obtained from market feedback. The indicators related to LightGBM prediction include prediction error, accuracy, The parameters for controlling the rate of change of weights are determined based on historical data optimization; It is the threshold for weight adjustment, which is determined based on actual market feedback and strategy requirements; Step 3.3: Build a fuzzy inference system: Build a fuzzy inference system based on the fuzzy rules defined in step 3.

2. The fuzzy inference system dynamically adjusts the weights of the expert knowledge base prediction values ​​based on real-time market feedback data. and the weights of LightGBM predictions , wherein the real-time market feedback data includes forecast error, rate of return, and stability; Step 3.4, weight adjustment: Whenever the system obtains new market feedback data, calculate the effect of the current strategy and adjust the weight through the fuzzy inference system built in step 3.

3. When the market volatility is large, increase the weight of the LightGBM prediction value When the market is stable, increase the weight of the expert knowledge base prediction value; Step 3.5, strategy execution: Generate the final strategy based on the adjusted weights. The calculation of the final strategy combines the LightGBM prediction value and the expert knowledge base prediction value. The calculation formula is: ； The final strategy is input into the rule engine for execution, and the strategy execution effect is monitored in real time, with continuous fuzzy reasoning and weight adjustment.

5. The method according to claim 1, wherein The rule engine library supports modular design based on LiteFlow and can dynamically add or update rule modules to adapt to market changes and strategic requirements.

6. The method according to claim 1, characterized in that The expert knowledge base includes medium- and long-term trading rules, spot trading rules, retail rules, historical violation events, technical equipment knowledge and abnormal event handling experience of the electricity market, and can be dynamically updated and expanded.

7. The method according to claim 1, characterized in that The machine learning strategy is weighted and summed with the expert strategy formed by the business rules and experience in the expert knowledge base. An adaptive fuzzy weighted algorithm is used to weight the expert strategy and the machine learning strategy, and the weights of the two are dynamically adjusted to adapt to the complex changes in the power market and generate the final power transaction settlement strategy.

8. An electronic device, characterized in that: include: Computer-readable storage medium and processor; The computer-readable storage medium is used to store executable instructions; The processor is used to read the executable instructions stored in the computer-readable storage medium and execute the intelligent configuration method of power transaction settlement strategy based on the rule engine according to any one of claims 1 to 7.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for intelligently configuring power transaction settlement strategies based on a rule engine according to any one of claims 1 to 7 is implemented.

Images