Acquisition method and device of electricity demand response probability and computer equipment

Abstract

The invention relates to an electricity demand response probability obtaining method and device and computer equipment. The method comprises the steps of obtaining an electricity price evaluation index, a comfort requirement index and an equipment operation index of an area where a to-be-evaluated user is located, and a commercial operation condition index corresponding to the to-be-evaluated user, and obtaining a subjective willingness influence coefficient of the to-be-evaluated user in power demand response according to the commercial operation condition index and the comfort requirement index, and according to the equipment operation index, obtaining an objective willingness degree influence coefficient of the to-be-evaluated user in the power demand response, and finally determining the probability that the to-be-evaluated user participates in the power demand response based on the electricity price evaluation index, the subjective willingness degree influence coefficient and the objective willingness degree influence coefficient. The multi-factor evaluation index of the area where the to-be-evaluated user is located is obtained, the probability that the user participates in the electricity demand response is calculated according to the multi-factor evaluation index, and the accuracy of the finally determined probability and the environmental adaptability are improved through diversification of data sources.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for obtaining electricity demand response probability. Background Art

[0002] The stability and reliability of the power system is the cornerstone of modern social and economic development. With the continuous growth of the global economy and the acceleration of urbanization, the demand for electricity has shown a significant growth trend. The traditional power system operation mode mainly relies on the construction of additional power generation facilities to meet the growing load demand.

[0003] The model of meeting load demand by increasing or decreasing power generation facilities has significant limitations in terms of resource utilization efficiency and environmental impact. To meet these challenges, demand-side management came into being. Its core is to achieve optimal allocation of power resources by changing the electricity consumption behavior of users. In the implementation of demand response, user participation willingness is a crucial factor, which directly determines whether the demand response strategy can be successfully implemented.

[0004] However, the current method of obtaining users' willingness to participate in electricity demand response has the problem of inaccurately obtaining users' willingness to participate in electricity demand response. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for obtaining the probability of electricity demand response, which can improve the accuracy of the obtained user's willingness to participate in electricity demand response, in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for obtaining a power demand response probability, comprising:

[0007] Obtain multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, commercial operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located;

[0008] According to the commercial operation status index and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated in the power demand response is obtained, and according to the equipment operation index, the objective willingness influence coefficient of the user to be evaluated in the power demand response is obtained;

[0009] Based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined.

[0010] In one embodiment, the business operation status indicators include event popularity data, marketing event data, marketing calendar data, price index data, and economic event data;

[0011] According to the commercial operation status indicators and comfort requirement indicators, the subjective willingness influence coefficient of the user to be evaluated in the electricity demand response is obtained, including:

[0012] Input event popularity data, marketing event data, and marketing calendar data into a pre-trained traffic flow prediction model, and obtain predicted traffic flow data corresponding to the area through the traffic flow prediction model;

[0013] Input the predicted traffic data, price index data and economic event index data into the pre-built sales forecasting model, and obtain the predicted sales corresponding to the user to be evaluated through the sales forecasting model;

[0014] Based on the predicted sales, the expected sales pre-set for the area, and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated in responding to electricity demand is obtained.

[0015] In one embodiment, the subjective willingness influence coefficient of the user to be evaluated on the electricity demand response is obtained based on the predicted sales, the expected sales preset for the area, and the comfort requirement index, including:

[0016] Based on the forecasted sales and expected sales, obtain the sales forecast difference evaluation coefficient;

[0017] Obtain the corresponding comfort evaluation coefficient according to the comfort requirement index;

[0018] Based on the sales expected difference evaluation coefficient and the comfort evaluation coefficient, the subjective willingness influence coefficient of the user to be evaluated in responding to electricity demand is obtained.

[0019] In one embodiment, the crowd flow prediction model is trained by the following steps:

[0020] Obtain sample business status operation indicators and sample traffic data of the sample user's area;

[0021] Extract the features of the sample business status operation indicators and sample traffic data to obtain the original feature vector, time feature vector and cross feature vector;

[0022] The original feature vector, the time feature vector and the cross feature vector are input into the pedestrian flow prediction model to be trained to train the pedestrian flow prediction model to be trained.

[0023] In an exemplary embodiment, the equipment operation index includes maintenance cost and start-stop time, the maintenance cost includes current maintenance cost, maximum maintenance cost and maintenance cost increase rate, and the start-stop time includes current switching duration and rated minimum switching duration of the equipment;

[0024] According to the equipment operation indicators, the objective willingness influence coefficient of the user to be evaluated in terms of electricity demand response is obtained, including:

[0025] According to the current maintenance cost, the maximum maintenance cost and the maintenance cost increase rate, the objective response coefficient is obtained;

[0026] Based on the current switching duration, the rated minimum switching duration and the objective response coefficient, an objective willingness influence coefficient is obtained.

[0027] In one embodiment, based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, determining the probability of the user to be evaluated participating in the electricity demand response includes:

[0028] According to the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the user willingness influence factor of the user to be evaluated in the electricity demand response is obtained;

[0029] Based on the user willingness influencing factors, the probability of the user to be evaluated participating in electricity demand response is determined.

[0030] In a second aspect, the present application further provides a device for acquiring a power demand response probability, comprising:

[0031] An index acquisition module is used to obtain multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, business operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located;

[0032] An influence coefficient construction module is used to obtain the subjective willingness influence coefficient of the user to be evaluated in the power demand response according to the commercial operation status index and the comfort requirement index, and to obtain the objective willingness influence coefficient of the user to be evaluated in the power demand response according to the equipment operation index;

[0033] The probability determination module is used to determine the probability of the user to be evaluated participating in the electricity demand response based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient.

[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] Obtain multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, commercial operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located;

[0036] According to the commercial operation status index and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated in the power demand response is obtained, and according to the equipment operation index, the objective willingness influence coefficient of the user to be evaluated in the power demand response is obtained;

[0037] Based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0039] Obtain multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, commercial operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located;

[0040] According to the commercial operation status index and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated in the power demand response is obtained, and according to the equipment operation index, the objective willingness influence coefficient of the user to be evaluated in the power demand response is obtained;

[0041] Based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined.

[0042] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0043] Obtain multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, commercial operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located;

[0044] According to the commercial operation status index and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated in the power demand response is obtained, and according to the equipment operation index, the objective willingness influence coefficient of the user to be evaluated in the power demand response is obtained;

[0045] Based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined.

[0046] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for obtaining the probability of electricity demand response obtain the electricity price evaluation index, comfort requirement index and equipment operation index of the area where the user to be evaluated is located, and the commercial operation status index corresponding to the user to be evaluated. According to the commercial operation status index and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated in the electricity demand response is obtained, and according to the equipment operation index, the objective willingness influence coefficient of the user to be evaluated in the electricity demand response is obtained. Finally, based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined. By obtaining the multi-factor evaluation index of the area where the user to be evaluated is located, and according to the corresponding index, the subjective willingness influence coefficient and the objective willingness influence coefficient of the user to be evaluated on the user demand response are obtained, and the subjective willingness influence coefficient, the objective willingness influence coefficient and the electricity price evaluation index are further used to calculate the probability of the user participating in the electricity demand response. The above method not only avoids the blind increase of power generation facilities to meet the electricity load demand and leads to a decrease in resource utilization, but also the probability determined by the multi-factor index has higher environmental adaptability and accuracy. The user's willingness to participate in the electricity demand response is measured by probability, and the electricity demand with a higher probability can be executed, which ensures the resource balance on both the supply and demand sides and improves the robustness of the system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 This is a diagram of an application environment of a method for obtaining a power demand response probability in one embodiment;

[0049] Figure 2 is a flow chart of a method for obtaining a power demand response probability in one embodiment;

[0050] Figure 3 is a flow chart of a method for obtaining a power demand response probability in another embodiment;

[0051] Figure 4 A schematic diagram of a flow chart of a method for obtaining predicted sales in one embodiment;

[0052] Figure 5A schematic diagram of the relationship between the expected sales difference and the expected sales difference influence coefficient in one embodiment;

[0053] Figure 6 A schematic diagram of another embodiment of a normal distribution simulating the randomness of a user's objective willingness;

[0054] Figure 7 It is a structural block diagram of a device for acquiring user demand response probability in one embodiment;

[0055] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The method for obtaining the power demand response probability provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the power grid system communicates with the server 102 through the network, and the power grid system includes power generation equipment and power consumption equipment, wherein the power consumption equipment includes commercial users and non-commercial users, and the power generation equipment transmits electricity to the power consumption equipment through the transmission line. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or it can be placed on the cloud or other network servers. Obtain the multi-factor evaluation index of the area where the user to be evaluated is located, wherein the multi-factor evaluation index includes the electricity price evaluation index, the commercial operation status index corresponding to the user to be evaluated, the comfort requirement index of the area where the user is located, and the equipment operation index of the area, and then obtain the subjective willingness influence coefficient of the user to be evaluated on the power demand response according to the commercial operation status index and the comfort requirement index, and obtain the objective willingness influence coefficient of the user to be evaluated on the power demand response according to the equipment operation index, and finally determine the probability of the user to be evaluated participating in the power demand response based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient. The server 102 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0058] In an exemplary embodiment, Figure 2 As shown, a method for obtaining the probability of electricity demand response is provided, and the method is applied to Figure 1 The server 102 in the example is used as an example to illustrate the method, which includes the following steps S201 to S203. Among them:

[0059] Step S201, obtaining multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, business operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located.

[0060] Among them, the electricity price evaluation index can be understood as electricity price data, including basic electricity price, current electricity price, compensation electricity price and maximum electricity price; the commercial operation status index can be understood as an indicator used to quantify the operation status of various activities of merchants; the comfort requirement index can be understood as an indicator used to quantify the comfort information of users in the area; and the equipment operation index can be understood as an indicator for quantifying the operation status of equipment in the area.

[0061] Optionally, the server 102 obtains multi-factor evaluation indicators of the user to be evaluated from the power grid system, wherein the multi-factor evaluation indicators include electricity price evaluation indicators, business operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located. By obtaining multi-factor evaluation indicators, the data acquisition sources are increased, which lays a solid data foundation for the subsequent construction of the subjective willingness influence coefficient and objective willingness influence coefficient corresponding to the electricity demand of the user to be evaluated, and also improves the accuracy of the obtained probability of the user to be evaluated participating in the electricity demand response.

[0062] Step S202, obtaining the subjective willingness influence coefficient of the user to be evaluated in the power demand response according to the business operation status index and the comfort requirement index, and obtaining the objective willingness influence coefficient of the user to be evaluated in the power demand response according to the equipment operation index.

[0063] Among them, the subjective willingness influence coefficient can be understood as the parameter information used to measure the user's subjective ideas on the response to electricity demand. Similarly, the objective willingness influence coefficient can be understood as the objective parameter information used to measure the user's response to electricity demand affected by the equipment operating conditions in the area.

[0064] Exemplarily, the server 102 determines the predicted sales corresponding to the user to be evaluated based on the business operation status indicator, and then determines the subjective willingness influence coefficient of the user to be evaluated on the corresponding electricity demand based on the predicted sales, the expected sales pre-set for the area, and the comfort evaluation index; and the server 102 also determines the equipment operation status of the area according to the equipment operation indicator, and obtains the objective willingness influence coefficient of the user to be evaluated on the corresponding electricity demand based on the equipment operation status. By combining the business operation status indicator with the user's predicted sales, and using the comfort index to pay attention to the user's electricity demand and satisfaction, the subjective willingness influence coefficient constructed from the above data can more accurately evaluate the electricity demand of the user to be evaluated; the objective willingness influence coefficient calculated based on the equipment operation status can more comprehensively reflect the actual electricity demand of the user to be evaluated. This evaluation can reduce the deviation caused by the user's subjective judgment, thereby providing more objective data support.

[0065] The subjective willingness influence coefficient and the objective willingness influence coefficient determined in the above manner complement each other in assessing the actual electricity demand of the user to be assessed, make up for each other's shortcomings, and thus improve the accuracy of the probability determined subsequently.

[0066] Step S203, based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, determine the probability of the user to be evaluated participating in the electricity demand response.

[0067] Optionally, the server 102 determines the user willingness influence factor for reflecting the willingness to participate in the electricity demand response based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, and then determines the probability of the power demand response of the user parameter to be evaluated based on the user willingness influence factor. By integrating subjective and objective factors, the calculation of the user willingness influence factor can more comprehensively reflect the user's willingness to respond to the power demand, and the probability of the user's participation in the power demand response determined by using this user willingness influence factor is more accurate, which is conducive to helping relevant technical personnel to plan activities according to probability, avoiding the high activity cost caused by the low enthusiasm of users to participate in the activity planning based on simple affirmative propositions (i.e. willingness to participate) and negative propositions (i.e. refusal to participate), and improving the utilization rate of resources.

[0068] In the above-mentioned method for obtaining the probability of electricity demand response, the electricity price evaluation index, comfort requirement index and equipment operation index of the area where the user to be evaluated is located, and the commercial operation status index corresponding to the user to be evaluated are obtained; based on the commercial operation status index and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated in the electricity demand response is obtained; and based on the equipment operation index, the objective willingness influence coefficient of the user to be evaluated in the electricity demand response is obtained; finally, based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined. By obtaining the multi-factor evaluation index of the area where the user to be evaluated is located, and according to the corresponding index, the subjective willingness influence coefficient and the objective willingness influence coefficient of the user to be evaluated on the user demand response are obtained, and the subjective willingness influence coefficient, the objective willingness influence coefficient and the electricity price evaluation index are further used to calculate the probability of the user participating in the electricity demand response. The above method not only avoids the blind increase of power generation facilities to meet the electricity load demand and leads to a decrease in resource utilization, but also the probability determined by the multi-factor index has higher environmental adaptability and accuracy. The user's willingness to participate in the electricity demand response is measured by probability, and the electricity demand with a higher probability can be executed, which ensures the resource balance on both the supply and demand sides and improves the robustness of the system operation.

[0069] In one embodiment, the business operation status indicators include event popularity data, marketing event data, marketing calendar data, price index data, and economic event data;

[0070] According to the business operation status indicators and comfort requirement indicators, the subjective willingness influence coefficient of the user to be evaluated in responding to electricity demand is obtained, including: inputting event heat data, marketing event data and marketing calendar data into a pre-trained pedestrian flow prediction model, and obtaining the predicted pedestrian flow data corresponding to the area through the pedestrian flow prediction model; inputting the predicted pedestrian flow data, price index data and economic event index data into a pre-built sales forecasting model, and obtaining the predicted sales corresponding to the user to be evaluated through the sales forecasting model; according to the predicted sales, the expected sales pre-set for the area and the comfort requirement indicators, the subjective willingness influence coefficient of the user to be evaluated in responding to electricity demand is obtained.

[0071] Among them, the pedestrian flow prediction model can be understood as a pedestrian flow random forest prediction model based on business operation status indicators, and the sales prediction model can be understood as a commercial user sales prediction model based on multi-source linear regression established based on the predicted value of pedestrian flow and corresponding economic indicators.

[0072] Exemplarily, server 102 inputs event popularity data, marketing event data, and marketing calendar data into a pre-trained pedestrian flow prediction model, obtains predicted pedestrian flow data corresponding to the area through the pedestrian flow prediction model, and then inputs the predicted pedestrian flow data, price index data, and economic event index data into a pre-built sales forecasting model, obtains the predicted sales corresponding to the user to be evaluated through the sales forecasting model, and finally obtains the subjective willingness influence coefficient of the user to be evaluated in the electricity demand response based on the predicted sales, the expected sales pre-set for the area, and the comfort requirement index.

[0073] Collect data such as temperature, promotional activities, holidays, and traffic volume of large commercial buildings, query the consumer price index and economic activity index of users around commercial buildings, and perform data cleaning, data preprocessing, and feature extraction:

[0074]

[0075] Where: The feature vector representing the i-th sample contains all the features used for model training. For the input temperature, holidays, promotional activities and the corresponding original data of traffic flow, The extracted time feature sequences are as follows, such as quarterly features, holiday features, weekday features, time interval features of the number of days from the last promotion, and periodic time features related to consumption levels.

[0076] For the extracted cross-feature sequences, for example, temperature is combined with holidays to form the "high temperature during holidays" feature, and promotional activities are combined with the day of the week to form the "weekend promotion" feature.

[0077] Crowd flow prediction model based on random forest:

[0078]

[0079] Where: The predicted result of the representative flow of people, is a random forest model.

[0080] Based on the flow of people, the predicted flow of people is used as one of the independent variables, combined with the consumer price index , the level of economic activity in the surrounding commercial areas Further forecast sales:

[0081]

[0082] Where: is the sales volume on day t, obtained from the sales records of commercial users, is the flow of people on day t, which can be obtained by get, is the consumer price index, which can be obtained from official statistical agencies or economic databases. is the level of economic activity, which can be obtained through economic activity reports of business districts or other relevant data sources, is the error term, and the error is minimized by solving the optimization problem.

[0083] In terms of parameter estimation, the model parameters , , , The solution is obtained by least square method by solving the following optimization problem, and the validity of the model is ensured by residual analysis and model diagnosis.

[0084]

[0085] When the difference between actual sales and sales expectations is small, merchants are insensitive to compensation for demand response; on the contrary, merchants with a larger difference in sales expectations are more willing to make up for their losses through electricity price compensation.

[0086] The above model is used to predict the sales of merchants through the relationship between thermal comfort and pedestrian flow, and corresponding model evaluation indicators are formulated to optimize the model and corresponding parameters.

[0087] Through the above method, the following technical effects are achieved:

[0088] 1. Collect multi-dimensional data such as temperature, promotional activities, holidays and traffic, as well as the surrounding consumer price index and economic activity index to form a comprehensive database. This provides a rich information basis for subsequent analysis.

[0089] 2. By combining predicted foot traffic with the Consumer Price Index and economic activity levels, sales can be more accurately predicted. This multivariate model takes into account market dynamics and improves the accuracy of forecasts.

[0090] In one of the embodiments, the subjective willingness influence coefficient of the user to be evaluated in responding to electricity demand is obtained based on the predicted sales, the expected sales pre-set for the area, and the comfort requirement index, including: obtaining the sales expectation difference evaluation coefficient based on the predicted sales and the expected sales; obtaining the corresponding comfort evaluation coefficient based on the comfort requirement index; and obtaining the subjective willingness influence coefficient of the user to be evaluated in responding to electricity demand based on the sales expectation difference evaluation coefficient and the comfort evaluation coefficient.

[0091] Optionally, based on the sales forecast, calculate the sales forecast difference according to the formula The impact coefficient of the difference between sales expectations and :

[0092] After obtaining the forecast value of commercial user sales, the expected sales difference of commercial users can be calculated as follows:

[0093]

[0094] in: is the forecast value of sales for commercial users, Expected sales for business users.

[0095] According to the relationship between the sales expectation difference and the sales expectation difference impact coefficient, the sales expectation difference evaluation coefficient is obtained. .

[0096]

[0097] Collect user thermal comfort scores through questionnaires (i.e. the aforementioned comfort evaluation index), and the gradient descent method is used to solve the optimal parameters and :

[0098] A questionnaire survey was conducted among users in the area to collect thermal comfort scores of different groups at different temperatures. , and the corresponding rating values ​​at different temperatures As different temperatures Measured value of .

[0099]

[0100] Use gradient descent method to solve the optimal problem:

[0101]

[0102] Given initial parameters and , iteratively solve the optimal value:

[0103]

[0104] Where: is the learning rate, and the parameter update speed can be controlled artificially.

[0105] Initial Parameters and The determination of can be done by using a uniformly distributed random initialization method on [0,1] and limiting the range to [0,0.5].

[0106] Calculate the thermal comfort correction factor based on the IPMV value of the thermal comfort evaluation index , the comprehensive correction coefficient is calculated according to the formula :

[0107] The predicted mean vote value (PMV) recommended by the international standard ISO 7730 is used to evaluate thermal comfort. The PMV value is calculated based on the human body thermal balance equation, taking into account the influence of multiple factors such as metabolic rate, clothing thermal resistance, air temperature, humidity, wind speed, etc. The calculation formula is as follows:

[0108]

[0109] think It is a comfort level generally acceptable to users across the country, and The comfort level is the best when the user can accept the demand response to the greatest extent. The corresponding maximum temperature , minimum temperature The corresponding calculation formula for the thermal comfort evaluation coefficient is as follows:

[0110]

[0111] Where: and k is the adjustment coefficient, is the local thermal comfort benchmark value, This is the optimal local temperature, obtained by consulting climate data and research reports.

[0112] The sales expectation difference impact coefficient and thermal comfort evaluation coefficient jointly determine the subjective willingness comprehensive correction coefficient (i.e. the subjective willingness impact coefficient mentioned above). Given by:

[0113]

[0114] By comparing the user sales forecast value and the expected sales value and calculating the expected sales difference, a quantitative basis is provided for evaluating the merchant's sensitivity in demand response, and a more accurate sales expectation difference evaluation coefficient is obtained; collecting data from diverse user groups can improve the representativeness and credibility of the comfort score, thereby optimizing the comprehensive evaluation results, and based on this evaluation result, a comfort evaluation coefficient that is more in line with the user's actual situation is obtained. Finally, based on the sales expectation difference evaluation coefficient and the comfort evaluation coefficient, the subjective willingness influence coefficient of the user to be evaluated in the electricity demand response is constructed. The obtained subjective willingness influence coefficient is more accurate and more in line with the user's current environment, laying a data foundation for the subsequent calculation of probability.

[0115] In an exemplary embodiment, the pedestrian flow prediction model is trained through the following steps: obtaining sample business condition operation indicators and sample pedestrian flow data of the area where the sample users are located; extracting features of the sample business condition operation indicators and sample pedestrian flow data to obtain original feature vectors, time feature vectors and cross feature vectors; inputting the original feature vectors, time feature vectors and cross feature vectors into the pedestrian flow prediction model to be trained to train the pedestrian flow prediction model to be trained.

[0116] For example, collect data such as temperature, promotional activities, holidays, and traffic volume of large commercial buildings, query the consumer price index and economic activity index of users around the commercial buildings, and perform data cleaning, data preprocessing, and feature extraction:

[0117] The collected temperature, holidays, promotional activities and corresponding traffic data are cleaned, corrected, standardized and smoothly converted, and time features and appropriate cross features are extracted to generate corresponding feature phasors:

[0118]

[0119] Where: The feature vector representing the i-th sample contains all the features used for model training. For the input temperature, holidays, promotional activities and the corresponding original data of traffic flow, The extracted time feature sequences are as follows, such as quarterly features, holiday features, weekday features, time interval features of the number of days from the last promotion, and periodic time features related to consumption levels.

[0120] For the extracted cross-feature sequences, for example, temperature is combined with holidays to form the "high temperature during holidays" feature, and promotional activities are combined with the day of the week to form the "weekend promotion" feature.

[0121] Establish a random forest prediction model for commercial building traffic based on thermal comfort, holidays and promotions:

[0122] Establish a random forest-based crowd flow prediction model:

[0123]

[0124] Where: The predicted result of the representative flow of people, is a random forest model.

[0125] 1. Ensure data quality through data cleaning, standardization and smooth conversion, extract time features and cross-features (such as "high temperatures during holidays" and "weekend promotions"), and enhance the model's adaptability to complex market behaviors.

[0126] 2. Use the random forest algorithm to build a crowd flow prediction model that can process high-dimensional data and capture complex nonlinear relationships; use the extracted feature vector as input to train the model to predict crowd flow. This ensemble learning method improves the stability and accuracy of prediction by building multiple decision trees; the random forest model can provide feature importance scores to help identify which features have the greatest impact on crowd flow prediction, thereby optimizing feature selection.

[0127] In one embodiment, the equipment operation index includes maintenance cost and start-stop time, the maintenance cost includes current maintenance cost, maximum maintenance cost and maintenance cost increase rate, and the start-stop time includes current switch duration and rated minimum switch duration of the equipment;

[0128] According to the equipment operation indicators, the objective willingness influence coefficient of the user to be evaluated in responding to electricity demand is obtained, including: obtaining the objective response coefficient based on the current maintenance cost, the maximum maintenance cost and the maintenance cost increase rate; obtaining the objective willingness influence coefficient based on the current switching duration, the rated minimum switching duration and the objective response coefficient.

[0129] Optionally, each terminal device collects the current operating status and start and stop time , And upload it to the computing platform, and collect the maximum maintenance cost of each terminal device and equipment maintenance cost increase rate Used to calculate the user objective response coefficient and objective willingness factor , :

[0130]

[0131] Where: Maintenance cost for a terminal device, is the maximum maintenance cost of the terminal equipment in the commercial building, The increase rate of maintenance cost for this equipment.

[0132] The coefficient is the influence of the terminal equipment usage status on the user's willingness to respond, which can be understood as the user's sensitivity to the loss of equipment start-up and shutdown. The larger the coefficient value is, the greater the influence of equipment start-up and shutdown on the user's willingness to respond, and vice versa.

[0133] definition and is the user's objective willingness factor (i.e. the aforementioned objective willingness influence coefficient), then:

[0134]

[0135]

[0136] Where: is the current switching duration of the air conditioning terminal equipment, The shortest switching duration permitted for air conditioning terminal equipment, is the objective response coefficient.

[0137] Taking into account the differences among air-conditioning users in commercial buildings, the normal distribution function can be used to represent the objective randomness of the terminal users' willingness within the same central air-conditioning system.

[0138]

[0139]

[0140] The objective response coefficient is calculated by the current maintenance cost, maximum maintenance cost and corresponding maintenance cost increase rate of the equipment included in the equipment operation index, and the objective willingness influence coefficient is calculated by using the objective response coefficient, the current switching duration and rated minimum switching duration of the equipment included in the equipment operation index to quantify user demand so that it can be used to measure the actual needs of users. This lays a data foundation for the subsequent calculation of the probability of users participating in the electricity demand response and improves the accuracy of the obtained probability.

[0141] In one of the embodiments, based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined, including: according to the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, obtaining the user willingness influence factor of the user to be evaluated in the electricity demand response; based on the user willingness influence factor, determining the probability of the user to be evaluated participating in the electricity demand response.

[0142] For example, relevant electricity consumption data is collected and uploaded to the computing platform to calculate the basic electricity price. , Compensation for electricity price and maximum electricity price , based on the current real-time electricity price Calculate the user willingness influencing factor based on the objective operation status :

[0143] Define the user willingness influencing factor that reflects the user's response willingness as follows:

[0144] (1) For the jth terminal of the i-th central air conditioner, when the compensation electricity price The subsequent electricity price is still higher than the basic electricity price hour:

[0145]

[0146] (2) For the jth terminal of the i-th central air conditioner, when the compensation electricity price The subsequent electricity price is lower than the basic electricity price hour:

[0147]

[0148] Where: N(·) is the normal distribution function, is the comprehensive correction coefficient of the user's subjective will, is the current electricity price, As the basic electricity price, To compensate for the electricity price, is the maximum electricity price, and It is the user's objective willingness factor.

[0149] Calculate the platform based on the user willingness impact factor Real-time calculation of the probability P of a user participating in demand response:

[0150] when When is positive, the user's response willingness is positive; when When it is negative, the user's response willingness is negative, and the value reflects the strength of the willingness. It can be used as a probability assessment of commercial users' willingness to participate in demand response. When <0, it is regarded that the user refuses to participate in demand response at this time.

[0151]

[0152] In the formula, Probabilistic assessment of demand response participation for commercial users.

[0153] By calculating the user willingness influencing factors in real time, the system can quantify the user's response willingness and further calculate the probability of the user to be evaluated participating in the electricity demand response based on the user's willingness influencing factors. It can help relevant departments formulate reasonable demand response plans based on the user's response willingness and implement targeted incentives to improve user participation and satisfaction, and avoid formulating plans that are out of touch with reality and bring about unnecessary waste of resource costs.

[0154] In an exemplary embodiment, Figure 3 As shown, a specific implementation of a method for obtaining a power demand response probability is provided (the following data are all specific examples of a method for obtaining a power demand response probability, and are not limited to being implemented in this case only). Among them:

[0155] a) Collect data such as temperature, promotional activities, holidays, and traffic volume of large commercial buildings, query the consumer price index and economic activity index of users around commercial buildings, and perform data cleaning, data preprocessing, and feature extraction:

[0156] The collected temperature, holidays, promotional activities and corresponding traffic data are cleaned, corrected, standardized and smoothly converted, and time features and appropriate cross features are extracted to generate corresponding feature phasors:

[0157] (1)

[0158] Where: The feature vector representing the i-th sample contains all the features used for model training. For the input temperature, holidays, promotional activities and the corresponding original data of traffic flow, The extracted time feature sequences are as follows, such as quarterly features, holiday features, weekday features, time interval features of the number of days from the last promotion, and periodic time features related to consumption levels.

[0159] For the extracted cross-feature sequences, for example, temperature is combined with holidays to form the "high temperature during holidays" feature, and promotional activities are combined with the day of the week to form the "weekend promotion" feature.

[0160] b) If Figure 4 As shown in the figure, a random forest prediction model for commercial building traffic based on thermal comfort, holidays and promotional activities is established; a commercial user sales prediction model based on multivariate linear regression is established based on the predicted value of traffic and corresponding economic indicators, and Python is used to train and solve the model, evaluate and correct the prediction results, and upload them to the computing platform:

[0161] Establish a random forest-based crowd flow prediction model:

[0162] (2)

[0163] Where: The predicted result of the representative flow of people, is a random forest model.

[0164] Based on the flow of people, the predicted flow of people is used as one of the independent variables, combined with the consumer price index , the level of economic activity in the surrounding commercial areas Further forecast sales:

[0165] (3)

[0166] Where: is the sales volume on day t, obtained from the sales records of commercial users, is the passenger flow on the tth day, which can be obtained by formula (2): is the consumer price index, which can be obtained from official statistical agencies or economic databases. is the level of economic activity, which can be obtained through economic activity reports of business districts or other relevant data sources, is the error term, and the error is minimized by solving the optimization problem.

[0167] In terms of parameter estimation, the model parameters , , , The solution is obtained by least square method by solving the following optimization problem, and the validity of the model is ensured by residual analysis and model diagnosis.

[0168] (4)

[0169] When the difference between actual sales and sales expectations is small, merchants are insensitive to compensation for demand response; on the contrary, merchants with a larger difference in sales expectations are more willing to make up for their losses through electricity price compensation.

[0170] The above model is used to predict the sales of merchants through the relationship between thermal comfort and pedestrian flow, and corresponding model evaluation indicators are formulated to optimize the model and corresponding parameters.

[0171] c) Based on the sales forecast, calculate the expected sales difference according to the formula The impact coefficient of the difference between sales expectations and :

[0172] After obtaining the forecast value of commercial user sales, the expected sales difference of commercial users can be calculated as follows:

[0173] (5)

[0174] in: is the forecast value of sales for commercial users, Expected sales for business users.

[0175] like Figure 5 As shown in Figure 2, based on the relationship between the sales expectation difference and the sales expectation difference impact coefficient, the sales expectation difference evaluation coefficient is obtained. .

[0176] (6)

[0177] d) Collect user thermal comfort scores through questionnaire survey , and use the gradient descent method to solve the optimal parameters and :

[0178] A questionnaire survey was conducted among users in the area to collect thermal comfort scores of different groups at different temperatures. , and the corresponding rating values ​​at different temperatures As different temperatures Measured value of .

[0179] (7)

[0180] Use gradient descent method to solve the optimal problem:

[0181] (8)

[0182] Given initial parameters and , iteratively solve the optimal value:

[0183] (9)

[0184] Where: is the learning rate, and the parameter update speed can be controlled artificially.

[0185] Initial Parameters and The determination of can be done by using a uniformly distributed random initialization method on [0,1] and limiting the range to [0,0.5].

[0186] e) Calculate the thermal comfort correction factor based on the IPMV value of the thermal comfort evaluation index , the comprehensive correction coefficient is calculated according to the formula :

[0187] The predicted mean vote value (PMV) recommended by the international standard ISO 7730 is used to evaluate thermal comfort. The PMV value is calculated based on the human body heat balance equation, which fully considers the influence of multiple factors such as metabolic rate, clothing thermal resistance, air temperature, humidity, wind speed, etc. The calculation formula is as follows:

[0188] (10)

[0189] think It is a comfort level generally acceptable to users across the country, and The comfort level is the best when the user can accept the demand response to the greatest extent. The corresponding maximum temperature , minimum temperature The corresponding calculation formula for the thermal comfort evaluation coefficient is as follows:

[0190] (11)

[0191] Where: and k is the adjustment coefficient, is the local thermal comfort benchmark value, This is the optimal local temperature, obtained by consulting climate data and research reports.

[0192] The sales expectation difference impact coefficient and thermal comfort evaluation coefficient jointly determine the subjective willingness comprehensive correction coefficient (i.e. the aforementioned subjective willingness impact coefficient). Given by formula (12):

[0193] (12)

[0194] f) Each terminal device collects the current operating status and start and stop time , And upload it to the computing platform, and collect the maximum maintenance cost of each terminal device and equipment maintenance cost increase rate Used to calculate the user objective response coefficient and objective willingness factor , :

[0195] (13)

[0196] Where: Maintenance cost for a terminal device, is the maximum maintenance cost of the terminal equipment in the commercial building, The increase rate of maintenance cost for this equipment.

[0197] The coefficient is the influence of the terminal equipment usage status on the user's willingness to respond, which can be understood as the user's sensitivity to the loss of equipment start-up and shutdown. The larger the coefficient value is, the greater the influence of equipment start-up and shutdown on the user's willingness to respond, and vice versa.

[0198] definition and is the user's objective willingness factor, then:

[0199] (14)

[0200] (15)

[0201] Where: is the switching duration of the air conditioning terminal equipment, The shortest switching duration permitted for air conditioning terminal equipment, is the objective response coefficient.

[0202] like Figure 6 As shown in the figure, considering the differences among air-conditioning users in commercial buildings, the normal distribution function can be used to represent the objective randomness of the terminal users within the same central air-conditioning system.

[0203] (16)

[0204] (17)

[0205] g) Collect relevant electricity consumption data and upload it to the computing platform to calculate the basic electricity price , Compensation for electricity price and maximum electricity price , based on the current real-time electricity price Calculate the user willingness influencing factor based on the objective operation status :

[0206] Define the user willingness influencing factor that reflects the user's response willingness as follows:

[0207] (1) For the jth terminal of the i-th central air conditioner, when the compensation electricity price The subsequent electricity price is still higher than the basic electricity price hour:

[0208] (18)

[0209] (2) For the jth terminal of the i-th central air conditioner, when the compensation electricity price The subsequent electricity price is lower than the basic electricity price hour:

[0210] (19)

[0211] Where: N(·) is the normal distribution function, is the comprehensive correction coefficient of the user's subjective will, is the current electricity price, As the basic electricity price, To compensate for the electricity price, is the maximum electricity price, and It is the user's objective willingness factor.

[0212] h) Calculate the platform's influence factor based on user willingness Real-time calculation of the probability P of a user participating in demand response:

[0213] when When is positive, the user's response willingness is positive; when When it is negative, the user's response willingness is negative, and the value reflects the strength of the willingness. It can be used as a probability assessment of commercial users' willingness to participate in demand response. When <0, it is regarded that the user refuses to participate in demand response at this time.

[0214] (20)

[0215] In the formula, Probabilistic assessment of demand response participation for commercial users.

[0216] Compared with the prior art, this application has the following advantages:

[0217] 1. This application focuses on analyzing the subjective and objective factors that may affect the willingness of commercial users to participate in demand response, and establishes a random forest model and a multivariate linear regression model to predict the flow of people in commercial buildings and the sales of commercial users. The prediction results directly affect the subsequent user willingness evaluation and the probability of users participating in demand response.

[0218] 2. Based on the existing evaluation of commercial user demand response potential that takes into account user willingness, this application has developed a detailed demand response willingness evaluation system method. When developing the evaluation method, the state randomness of the terminal equipment and the impact of objective willingness on the user's willingness to participate in demand response are taken into account. The comprehensive evaluation method establishes a probabilistic evaluation model for user participation in demand response, making the evaluation results more accurate and reliable. It provides reliable data support for the power department to formulate corresponding commercial user demand response scheduling plans and demand response decision plans.

[0219] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0220] Based on the same inventive concept, the embodiment of the present application also provides a device for obtaining the probability of response of power demand for implementing the method for obtaining the probability of response of power demand involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more devices for obtaining the probability of response of power demand provided below can refer to the limitations of the method for obtaining the probability of response of power demand above, and will not be repeated here.

[0221] In an exemplary embodiment, Figure 7 As shown, a device for obtaining the probability of a power demand response is provided, comprising: an indicator obtaining module 701, an influence coefficient building module 702 and a probability determining module 703, wherein:

[0222] The index acquisition module 701 is used to obtain the multi-factor evaluation index of the area where the user to be evaluated is located; the multi-factor evaluation index includes the electricity price evaluation index, the commercial operation status index corresponding to the user to be evaluated, the comfort requirement index of the area where the user is located, and the equipment operation index of the area where the user is located;

[0223] The influence coefficient construction module 702 is used to obtain the subjective willingness influence coefficient of the user to be evaluated on the power demand response according to the business operation status index and the comfort requirement index, and to obtain the objective willingness influence coefficient of the user to be evaluated on the power demand response according to the equipment operation index;

[0224] The probability determination module 703 is used to determine the probability of the user to be evaluated participating in the electricity demand response based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient.

[0225] In one embodiment, the business operation status indicators include event popularity data, marketing event data, marketing calendar data, price index data and economic event data, and the influence coefficient construction module 702 also includes: a traffic flow prediction submodule, a sales prediction submodule and a subjective willingness influence coefficient construction submodule, wherein:

[0226] The pedestrian flow prediction submodule is used to input event popularity data, marketing event data and marketing calendar data into a pre-trained pedestrian flow prediction model, and obtain the predicted pedestrian flow data corresponding to the area through the pedestrian flow prediction model;

[0227] The sales forecasting submodule is used to input the predicted traffic data, price index data and economic event index data into a pre-built sales forecasting model, and obtain the predicted sales corresponding to the user to be evaluated through the sales forecasting model;

[0228] The subjective willingness influence coefficient construction submodule is used to obtain the subjective willingness influence coefficient of the user to be evaluated in the electricity demand response based on the predicted sales, the expected sales pre-set for the area, and the comfort requirement index.

[0229] In one of the embodiments, the subjective willingness influence coefficient construction submodule is also used to obtain the sales expectation difference evaluation coefficient based on the predicted sales and the expected sales; obtain the corresponding comfort evaluation coefficient according to the comfort requirement index; and obtain the subjective willingness influence coefficient of the user to be evaluated in the electricity demand response based on the sales expectation difference evaluation coefficient and the comfort evaluation coefficient.

[0230] In an exemplary embodiment, the device for acquiring the probability of response to electricity demand also includes a crowd flow prediction model training module, which is used to obtain sample business condition operation indicators and sample crowd flow data in the area where the sample users are located; extract features of the sample business condition operation indicators and sample crowd flow data to obtain original feature vectors, time feature vectors and cross feature vectors; and input the original feature vectors, time feature vectors and cross feature vectors into the crowd flow prediction model to be trained to train the crowd flow prediction model to be trained.

[0231] In one embodiment, the equipment operation indicators include maintenance cost and start-stop time, the maintenance cost includes the current maintenance cost, the maximum maintenance cost and the maintenance cost increase rate, and the start-stop time includes the current switching duration and the rated minimum switching duration of the equipment; the influence coefficient construction module 702 is also used to obtain the objective response coefficient based on the current maintenance cost, the maximum maintenance cost and the maintenance cost increase rate; based on the current switching duration, the rated minimum switching duration and the objective response coefficient, obtain the objective willingness influence coefficient.

[0232] In one of the embodiments, the probability determination module 703 is also used to obtain the user willingness influence factor of the user to be evaluated in the electricity demand response based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient; based on the user willingness influence factor, determine the probability of the user to be evaluated participating in the electricity demand response.

[0233] Each module in the above-mentioned device for obtaining the probability of response to electricity demand can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0234] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store electricity price evaluation indicators, commercial operation status indicators, comfort requirement indicators, equipment operation indicators, subjective willingness influence coefficients, objective willingness influence coefficients and probability data. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for obtaining a probability of electricity demand response is implemented.

[0235] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0236] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method for obtaining the electricity demand response probability of the above embodiment is implemented.

[0237] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for obtaining the electricity demand response probability of the above embodiment is implemented.

[0238] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method for obtaining the electricity demand response probability of the above embodiment.

[0239] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0240] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0241] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0242] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for obtaining a power demand response probability, characterized in that: The method comprises: Obtaining multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, business operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located; According to the commercial operation status index and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated on the power demand response is obtained, and according to the equipment operation index, the objective willingness influence coefficient of the user to be evaluated on the power demand response is obtained; Based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response is determined.

2. The method according to claim 1, characterized in that The business operation status indicators include event popularity data, marketing event data, marketing calendar data, price index data and economic event data; The obtaining, according to the commercial operation status index and the comfort requirement index, a subjective willingness influence coefficient of the user to be evaluated on the electricity demand response includes: Input the event popularity data, marketing event data and marketing calendar data into a pre-trained pedestrian flow prediction model, and obtain predicted pedestrian flow data corresponding to the area through the pedestrian flow prediction model; Inputting the predicted traffic data, price index data and economic event index data into a pre-built sales forecasting model, and obtaining the predicted sales corresponding to the user to be evaluated through the sales forecasting model; The subjective willingness influence coefficient of the user to be evaluated on the electricity demand response is obtained based on the predicted sales, the expected sales pre-set for the area, and the comfort requirement index.

3. The method according to claim 2, characterized in that The obtaining, according to the predicted sales, the expected sales preset for the region, and the comfort requirement index, the subjective willingness influence coefficient of the user to be evaluated on the electricity demand response includes: Based on the predicted sales volume and the expected sales volume, obtaining an evaluation coefficient of the expected sales volume difference; Obtaining a corresponding comfort evaluation coefficient according to the comfort requirement index; Based on the sales expected difference evaluation coefficient and the comfort evaluation coefficient, the subjective willingness influence coefficient of the user to be evaluated in responding to electricity demand is obtained.

4. The method according to claim 2, characterized in that: The crowd flow prediction model is trained by the following steps: Obtain sample business status operation indicators and sample traffic data of the sample user's area; Extracting features of the sample business condition operation indicators and sample passenger flow data to obtain original feature vectors, time feature vectors and cross feature vectors; The original feature vector, the time feature vector and the cross feature vector are input into the pedestrian flow prediction model to be trained to train the pedestrian flow prediction model to be trained.

5. The method according to claim 1, characterized in that The equipment operation index includes maintenance cost and start-stop time, the maintenance cost includes current maintenance cost, maximum maintenance cost and maintenance cost increase rate, and the start-stop time includes current switch duration and rated minimum switch duration of the equipment; The step of obtaining the objective willingness influence coefficient of the user to be evaluated on the electricity demand response according to the equipment operation index includes: Obtaining an objective response coefficient according to the current maintenance cost, the maximum maintenance cost, and the maintenance cost increase rate; The objective willingness influence coefficient is obtained based on the current switching duration, the rated minimum switching duration, and the objective response coefficient.

6. The method according to claim 1, characterized in that The determining, based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, the probability of the user to be evaluated participating in the electricity demand response includes: According to the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient, a user willingness influence factor of the user to be evaluated on the electricity demand response is obtained; Based on the user willingness influencing factor, the probability of the user to be evaluated participating in the electricity demand response is determined.

7. A device for obtaining a probability of response to electricity demand, characterized in that: The device comprises: An index acquisition module is used to obtain multi-factor evaluation indicators of the area where the user to be evaluated is located; the multi-factor evaluation indicators include electricity price evaluation indicators, business operation status indicators corresponding to the user to be evaluated, comfort requirement indicators of the area where the user is located, and equipment operation indicators of the area where the user is located; An influence coefficient construction module, used to obtain the subjective willingness influence coefficient of the user to be evaluated on the power demand response according to the commercial operation status index and the comfort requirement index, and to obtain the objective willingness influence coefficient of the user to be evaluated on the power demand response according to the equipment operation index; The probability determination module is used to determine the probability of the user to be evaluated participating in the electricity demand response based on the electricity price evaluation index, the subjective willingness influence coefficient and the objective willingness influence coefficient.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images