User energy storage auxiliary settlement method and system

Abstract

The invention discloses a user energy storage auxiliary settlement method and system, and relates to the field of electricity markets and energy management, and the method comprises the steps: obtaining and preprocessing user side data; based on the user electricity consumption data, the user electricity consumption habit index data and the energy storage equipment use duration data, the user load fluctuation degree, the user electricity consumption fluctuation degree and the workday and weekend use duration ratio are obtained through calculation; acquiring power consumption time data of each time period, and outputting and correcting a power consumption predicted value of each time period based on the power consumption time data, the user load fluctuation degree, the user power consumption fluctuation degree and the workday to weekend use duration ratio in combination with a linear regression model and a Bayesian theorem; and on the basis of the corrected electricity consumption predicted value of each time period and the electricity price of each time period, calculating the energy storage settlement cost of the user. According to the invention, the final electric charge of the user can be predicted more accurately.

Description

Technical Field

[0001] The present invention relates to the field of power market and energy management, and in particular to a user energy storage auxiliary settlement method and system. Background Art

[0002] With the continuous development of renewable energy and the gradual opening of the electricity market, user-side energy storage systems have played an important role in regulating power grid loads and improving energy efficiency, and a user energy storage auxiliary settlement method and system have emerged. A user energy storage auxiliary settlement method and system in the prior art can collect multiple data on the user side, extract multiple feature data from the user's electricity usage habit indicator data to build a model for prediction, obtain the corresponding charging or discharging amount of the user in different time periods according to the predicted values, and obtain the costs and benefits obtained in different time periods according to the corresponding charging or discharging amount and electricity price of the user in different time periods, and comprehensively obtain the actual settlement cost of the energy storage equipment.

[0003] Although the existing user energy storage assisted settlement methods and systems have achieved user energy storage assisted settlement to a certain extent, there are problems with inaccurate data and complex settlement in the process of electricity consumption and electricity fee settlement. It is difficult to extract multiple feature data from the user's electricity usage habit indicator data to build a model. There is a lack of information based on the constructed model to obtain the discharge amount during peak hours and the charging amount during normal and off-peak hours. It is difficult to comprehensively settle the costs and benefits obtained in different time periods to obtain the actual settlement cost of the energy storage equipment.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes a user energy storage auxiliary settlement method and system to overcome the above-mentioned technical problems existing in the existing related art.

[0006] To this end, the specific technical solution adopted by the present invention is as follows:

[0007] According to one aspect of the present invention, a user energy storage auxiliary settlement method is provided, the method comprising:

[0008] S1. Acquire and pre-process user-side data, where the user-side data includes user power consumption data, user power consumption habit indicator data, and energy storage device usage time data;

[0009] S2. Based on the user's electricity consumption data, the user's electricity consumption habit index data and the energy storage equipment usage time data, calculate the user's load fluctuation degree, the user's electricity consumption fluctuation degree and the usage time ratio between weekdays and weekends;

[0010] S3, obtaining the electricity consumption time data of each time period, and based on the electricity consumption time data, the user load fluctuation degree, the user electricity consumption fluctuation degree and the usage time ratio between weekdays and weekends, and combining the linear regression model and Bayesian theorem, outputting and correcting the electricity consumption forecast value of each time period;

[0011] S4. Based on the corrected electricity consumption forecast value for each time period and the electricity price for each time period, the user's energy storage settlement fee is calculated.

[0012] Furthermore, based on the user's electricity consumption data, the user's electricity consumption habit index data and the energy storage equipment usage time data, the user's load fluctuation degree, the user's electricity consumption fluctuation degree and the ratio of usage time on weekdays to weekends are calculated, including:

[0013] Extracting the user power load data within a period from the user power usage habit index data, and the user power load data within the period includes the highest peak value, the lowest valley value and the average value;

[0014] The user load fluctuation degree is calculated based on the highest peak value, lowest valley value and average value of the user power load data within the period;

[0015] According to the user's electricity consumption data, the fluctuation degree of the user's electricity consumption is calculated;

[0016] Based on the power consumption time data of the energy storage equipment and combined with the number of weekdays and weekends, the ratio of weekday to weekend usage time is calculated.

[0017] Furthermore, according to the highest peak value, lowest valley value and average value of the user power load data within the cycle, the user load fluctuation degree is calculated to include:

[0018] The user load fluctuation degree is calculated using the user's highest peak load value within the cycle, the user's lowest valley load value within the cycle, the user's average load value within the cycle, and the user's daily load value within the cycle.

[0019] Furthermore, based on the user's power consumption data, the user's power consumption fluctuation degree is calculated including:

[0020] The degree of fluctuation of the user's electricity consumption is calculated by using the user's daily electricity consumption within the cycle and the average electricity consumption within the user's cycle.

[0021] Furthermore, based on the power consumption time data of the energy storage equipment and combined with the number of working days and weekends, the ratio of working days to weekend usage time is calculated, including:

[0022] Obtain the daily electricity consumption duration data of users within the period, and extract features from the user electricity consumption data and electricity consumption duration data to obtain the daily average electricity consumption and the standard deviation of electricity consumption;

[0023] Based on the average daily electricity consumption and the standard deviation of electricity consumption, and combined with the machine learning algorithm, a classification model is trained and used to output the attributes of each day;

[0024] Record the number of times each day is a working day to get the total number of working days in the cycle, and calculate the total number of weekend days in the cycle based on the difference between the total number of days in the cycle and the total number of working days in the cycle;

[0025] The ratio of working day to weekend usage time is calculated using the total number of working days in the cycle, the usage time of the energy storage equipment on each working day, the total number of weekends in the cycle, and the usage time of the energy storage equipment on each weekend.

[0026] Furthermore, the power consumption time data of each time period is obtained, and based on the power consumption time data, the user load fluctuation degree, the user power consumption fluctuation degree and the usage time ratio between weekdays and weekends, and combined with the linear regression model and Bayesian theorem, the power consumption forecast value of each time period is output and corrected, including:

[0027] Collect electricity consumption time data for each time period, including peak time, normal time and off-peak time;

[0028] The user load fluctuation degree, user power consumption fluctuation degree, weekday and weekend usage time ratio and power consumption time data are used as input, and power consumption is used as output to train the linear regression model and obtain the prediction model;

[0029] The prediction model is used to output the predicted value of electricity consumption in each time period, and the predicted value of the prediction model is corrected based on the Bayesian algorithm.

[0030] Furthermore, the forecast model is used to output the power consumption forecast values ​​for each period, including:

[0031] Among the predicted electricity consumption output by the prediction model, the maximum value, median value and minimum value are used as the peak period electricity consumption forecast value, the normal period electricity consumption forecast value and the off-peak period electricity consumption forecast value respectively.

[0032] Furthermore, the prediction value of the prediction model is corrected based on the Bayesian algorithm, including:

[0033] Obtain the prior probability of the prediction model, and calculate the likelihood function of the prediction model based on the observed data corresponding to the prediction model;

[0034] Using Bayes' theorem and combining the prior probability and likelihood function of the prediction model, the posterior distribution of the prediction model parameters is calculated, and the posterior distribution is used to correct the predicted value of the prediction model.

[0035] Furthermore, based on the revised power consumption forecast value and the electricity price of each period, the user's energy storage settlement fee is calculated to include:

[0036] Get electricity prices during peak, normal and off-peak hours;

[0037] The corrected peak-period electricity consumption forecast value is used as the discharge amount of the energy storage device during the peak period, the corrected normal-period electricity consumption forecast value is used as the charge amount of the energy storage device during the normal period, and the corrected valley-period electricity consumption forecast value is used as the charge amount of the energy storage device during the valley period;

[0038] The calculation formula for user energy storage settlement fees is:

[0039]

[0040] Among them, M is the user's energy storage settlement fee;

[0041] P peak is the discharge amount during peak hours, M peak is the electricity price during peak hours;

[0042] P avg is the charge amount in normal period, η is the charge and discharge efficiency of energy storage equipment, M avg The electricity price during normal times;

[0043] P valley is the charging capacity during the low-peak period, M valley The electricity price during off-peak hours.

[0044] According to another aspect of the present invention, a user energy storage auxiliary settlement system is provided, which includes a data acquisition module, a characteristic data calculation module, a user power consumption prediction module and an energy storage electricity fee settlement module:

[0045] The data acquisition module is used to acquire and pre-process user-side data, and the user-side data includes user power consumption data, user power consumption habit indicator data and energy storage device usage time data;

[0046] The characteristic data calculation module is used to calculate the user load fluctuation degree, the user power consumption fluctuation degree and the usage time ratio between weekdays and weekends based on the user power consumption data, the user power consumption habit index data and the energy storage device usage time data;

[0047] The user electricity consumption prediction module is used to obtain the electricity consumption time data including each time period, and output and correct the electricity consumption prediction value of each time period based on the electricity consumption time data, the user load fluctuation degree, the user electricity consumption fluctuation degree and the usage time ratio between weekdays and weekends, and combined with the linear regression model and Bayesian theorem;

[0048] The energy storage electricity fee settlement module is used to calculate the user's energy storage settlement fee based on the corrected electricity consumption forecast value in each time period and the electricity price in each time period.

[0049] The beneficial effects of the present invention are:

[0050] (1) The present invention analyzes the historical electricity consumption data of users, obtains the user load fluctuation degree, the user electricity consumption fluctuation degree and the user weekday-weekend usage time ratio as feature data through statistical analysis methods, constructs a model based on the extracted features to predict the electricity consumption to obtain a predicted value, and corrects the predicted value through the Bayesian method, which can more accurately reflect the user's electricity consumption habits and patterns, improve the accuracy of electricity consumption prediction, and use the predicted electricity consumption in different time periods as the charging or discharging amount of the energy storage device in different time periods, thereby realizing peak shaving and valley filling of the power grid.

[0051] (2) The present invention calculates the discharge amount of the energy storage device during the peak period, the charging amount during the normal period and the off-peak period, and the electricity price during the corresponding period, and obtains the cost of charging during the off-peak period and the normal period and the benefit of discharging during the peak period, thereby obtaining the actual settlement cost of the energy storage device. This realizes the consideration of the electricity price in different time periods, improves the accuracy of the economic benefit calculation of the energy storage device in each time period, and can more accurately predict the user's final electricity bill. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 is a flow chart of a user energy storage auxiliary settlement method according to an embodiment of the present invention;

[0054] Figure 2 It is a module schematic diagram of a user energy storage auxiliary settlement system according to an embodiment of the present invention.

[0055] In the figure:

[0056] 1. Data acquisition module; 2. Feature data calculation module; 3. User electricity consumption prediction module; 4. Energy storage electricity fee settlement module. DETAILED DESCRIPTION

[0057] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0058] According to an embodiment of the present invention, a user energy storage auxiliary settlement method and system are provided.

[0059] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 According to one embodiment of the present invention, a user energy storage auxiliary settlement method is provided, the method comprising:

[0060] S1. Acquire and pre-process user-side data, where the user-side data includes user power consumption data, user power consumption habit indicator data, and energy storage device usage time data;

[0061] S2. Based on the user's electricity consumption data, the user's electricity consumption habit index data and the energy storage equipment usage time data, calculate the user's load fluctuation degree, the user's electricity consumption fluctuation degree and the usage time ratio between weekdays and weekends;

[0062] S3, obtaining the electricity consumption time data of each time period, and based on the electricity consumption time data, the user load fluctuation degree, the user electricity consumption fluctuation degree and the usage time ratio between weekdays and weekends, and combining the linear regression model and Bayesian theorem, outputting and correcting the electricity consumption forecast value of each time period;

[0063] S4. Based on the corrected electricity consumption forecast value for each time period and the electricity price for each time period, the user's energy storage settlement fee is calculated.

[0064] like Figure 2 As shown, according to another embodiment of the present invention, a user energy storage auxiliary settlement system is provided, which includes: a data acquisition module 1, a characteristic data calculation module 2, a user power consumption prediction module 3 and an energy storage electricity fee settlement module 4:

[0065] The data acquisition module 1 is used to acquire and pre-process user-side data, and the user-side data includes user power consumption data, user power consumption habit index data and energy storage device usage time data;

[0066] Characteristic data calculation module 2, used to calculate the user load fluctuation degree, the user power consumption fluctuation degree and the usage time ratio between weekdays and weekends based on the user power consumption data, the user power consumption habit index data and the energy storage device usage time data;

[0067] The user power consumption prediction module 3 is used to obtain the power consumption time data of each time period, and output and correct the power consumption prediction value of each time period based on the power consumption time data, the user load fluctuation degree, the user power consumption fluctuation degree and the usage time ratio between weekdays and weekends, and in combination with the linear regression model and Bayesian theorem;

[0068] The energy storage electricity fee settlement module 4 is used to calculate the user's energy storage settlement fee based on the corrected power consumption forecast value of each time period and the electricity price of each time period.

[0069] In order to facilitate understanding of the above technical solutions of the present invention, the above technical solutions of the present invention are further explained below from the perspectives of architecture and principle.

[0070] Install smart meters with remote communication functions at power consumption sites, and configure wireless communication modules for smart meters so that the meters can transmit the collected data to the cloud platform in real time. Set the data collection time interval in the smart meters, collect data every 1 hour, and automatically record the power consumption in each time period, including the total power consumption and the power consumption divided by peak hours, normal hours, and off-peak hours. Use smart meters to collect users' power consumption habit indicator data. Smart meters installed on the grid side collect grid load data. The collected user-side data and grid-side data are transmitted to the cloud platform in real time through the communication network for processing and analysis. Use the data processing services provided by the cloud computing platform to batch process the data, apply filters to remove high-frequency noise, and calculate the mean and standard deviation of the data through statistical analysis methods. Use the Z-score method to identify and remove outliers, determine a unified data format, and use data conversion tools on the cloud platform, including AWS Glue cloud data integration service or Azure Data Any of the data integration systems on the Factory cloud converts data in different formats into a unified format; extracts features from the user's electricity usage habit indicator data to build a linear regression model, including the usage time ratio between weekdays and weekends, the degree of electricity consumption fluctuation and the degree of load fluctuation; uses the extracted features as input, and takes the electricity consumption during peak hours, normal hours and valley hours as output to train the model; uses the trained model to obtain the peak electricity consumption, normal electricity consumption and valley electricity consumption forecast values ​​respectively; uses the peak electricity consumption forecast value as the discharge amount of the energy storage device during the peak hours, the normal electricity consumption forecast value as the charge amount of the energy storage device during the normal hours, and the valley electricity consumption forecast value as the charge amount of the energy storage device during the valley hours; multiplies the electricity price during the peak hours by the corresponding discharge amount to obtain the discharge benefit during the peak hours, and combines the electricity price, charge and discharge efficiency and corresponding charge amount during the normal hours to obtain the charging cost during the normal hours.

[0071] The electricity price, charging and discharging efficiency and corresponding charging amount during the off-peak period are combined to obtain the charging cost during the off-peak period. The charging costs during normal and off-peak periods are added together to obtain the total charging cost. The discharge benefits during the peak period are listed separately. The actual settlement cost of the energy storage equipment is obtained through the comprehensive calculation of the total charging cost and the discharge benefits.

[0072] In one embodiment, S1 comprises the following steps:

[0073] Smart meters are installed on the user side and the grid side respectively. The smart meters collect the user's electricity consumption data and the grid's power supply data every hour at preset time intervals, including electricity consumption data during peak, normal and off-peak periods, user's electricity consumption habit indicator data and grid load data.

[0074] Specifically, smart meters with remote communication functions are installed at electricity consumption sites, and wireless communication modules are configured for the smart meters, so that the meters can transmit the collected data to the cloud platform in real time. The data collection time interval is set in the smart meters, and data is collected every 1 hour. The smart meters automatically record the electricity consumption in each time period, including the total electricity consumption and the electricity consumption divided by peak hours, normal hours, and off-peak hours. The smart meters are used to collect users' electricity consumption habit indicator data. The smart meters installed on the grid side collect grid load data. The collected user-side data and grid-side data are transmitted to the cloud platform in real time through the communication network for processing and analysis.

[0075] In one embodiment, S2 includes the following steps:

[0076] The collected data is processed using cloud computing algorithms, filters are used to remove high-frequency noise in the data, and outliers are identified and removed through statistical analysis methods. Data in different formats are converted into a unified format, and data from different devices and systems are integrated.

[0077] Specifically, use the data processing service provided by the cloud computing platform to process the data in batches, apply filters to remove high-frequency noise, and use statistical analysis to calculate statistics such as the mean and standard deviation of the data. Use the Z-score method to identify and remove outliers, determine a unified data format, and use data conversion tools on the cloud platform, including AWS Glue or Azure Data Factory, to convert data in different formats into a unified format.

[0078] In one embodiment, S3 includes the following steps:

[0079] The collected data on users’ electricity usage habits within a month in history, including daily electricity consumption and load, are cleaned to remove outliers and missing values. User electricity usage habit indicators are extracted from the cleaned data, including user load fluctuation degree, user electricity consumption fluctuation degree and user weekday-weekend usage time ratio.

[0080] Record the user power load data within a month, including the highest peak value, the lowest valley value and the average value, and obtain the user load fluctuation degree calculation formula:

[0081]

[0082] Among them, C degree is the user load fluctuation degree, C highest is the highest load peak of the user in a month, C lowst is the lowest load value of the user in a month, C avg is the average load of the user in a month, C i is the load value of the user on the i-th day, and 30 is the total number of days in a month.

[0083] Record the user's electricity consumption data within a month and obtain the calculation formula for the user's electricity consumption fluctuation degree:

[0084]

[0085] Among them, E degree is the fluctuation degree of user electricity consumption, E i is the electricity consumption of the user on the i-th day, E avg It is the average electricity consumption of users in a month, and 30 is the total number of days in a month.

[0086] The energy storage equipment monitoring system and smart meter are used to record the daily usage time data of the energy storage equipment within one month. After cleaning the collected data and removing outliers, features are extracted from the power consumption data and the power consumption time data, including the daily average power consumption and the standard deviation of power consumption. A classification model is trained using a machine learning algorithm, and the extracted features are used as input, and each day is a working day or a weekend as output. The collected data is classified according to working days and weekends, and the average usage time of the two types of data on working days and weekends is calculated respectively. The average usage time of working days is compared with the average usage time of weekends, and the ratio obtained is recorded as the working day-weekend usage time ratio. It should be noted that in the present invention, weekends refer to non-working days.

[0087] The formula for calculating the weekday-weekend usage time ratio is:

[0088]

[0089] Among them, T rate is the ratio of working day to weekend usage time, n is the total number of working days in a month, T workday,i is the usage time of the energy storage equipment on the ith working day, 30-n is the total number of weekend days in a month, T holiday,j is the usage time of the energy storage device on the jth weekend.

[0090] The actual electricity consumption data of each stage is collected, including the electricity consumption time in the peak stage, the normal stage and the valley stage. The linear regression model is constructed by extracting the features from the user's electricity consumption habit indicator data and the actual electricity consumption data. The features include the usage time ratio of weekdays to weekends, the degree of electricity consumption fluctuation, the degree of load fluctuation and any one of the electricity consumption time during the peak period, the normal period and the valley period obtained through statistical analysis. The extracted features are used as input, and the electricity consumption during the peak period, the normal period and the valley period is used as output to train the model. After the model training is completed, the Bayesian method is used to correct the predicted value, and the prior distribution of the model parameters is obtained according to the historical data. Based on the new observations, the model is trained. The likelihood function of the model is calculated based on the measured data. The posterior distribution of the model parameters is calculated using the Bayesian theorem combined with the prior probability and the likelihood function. The predicted values ​​are corrected using the posterior distribution to obtain the corrected predicted values ​​for each time period. The corrected peak power consumption prediction value is used as the discharge amount of the energy storage device during the peak period, the corrected normal power consumption prediction value is used as the charging amount of the energy storage device during the normal period, and the corrected valley power consumption prediction value is used as the charging amount of the energy storage device during the valley period. The trained model is used to predict the peak power consumption, normal power consumption and valley power consumption according to the characteristic data, and the peak power consumption prediction value, normal power consumption prediction value and valley power consumption prediction value are obtained.

[0091] The formula for calculating the predicted power consumption is:

[0092] y=α0+x_C degree ×α1+x_E degree ×α2+x_T rate ×α3+x_H i ×α4

[0093] Among them, y is the predicted power consumption, x_C degree 、x_E degree 、x_T rate and x_H i is the input feature of the model, C degree is the user load fluctuation degree, E degree is the fluctuation degree of user electricity consumption, T rate is the ratio of working day to weekend usage time, x_H i is the user's electricity usage time. When i is 1, it means the user's electricity usage time is during peak hours. When i is 2, it means the user's electricity usage time is during normal hours. When i is 3, it means the user's electricity usage time is during off-peak hours. α0, α1, α2, α3 and α4 are all parameters of the model.

[0094] Extract feature vector x = [x_C degree , x_E degree , x_T rate , x_H i ]T , bring it into the model formula, and find the maximum, median and minimum values ​​in the predicted electricity consumption of the day as the peak electricity consumption prediction value, normal electricity consumption prediction value and valley electricity consumption prediction value of the day.

[0095] P peak =max(y)

[0096] P valley =min(y)

[0097] P avg =middle(y)

[0098] Among them, max(y) is the maximum value of the predicted power consumption for that day, min(y) is the minimum value of the predicted power consumption for that day, middle(y) is the average value of the predicted power consumption for that day, P peak is the predicted peak power consumption value for the day, P avg is the predicted value of the daily electricity consumption, P valley It is the predicted value of the low-peak electricity consumption for that day.

[0099] Specifically, collect the electricity consumption data of users within a month, including daily load, electricity consumption and electricity consumption time. After processing the missing values ​​and outliers in the data, record the power load data of users within a month, including the highest peak value, the lowest valley value and the mean value, and obtain the user load fluctuation value; record the electricity consumption data of users within a month, including the mean value, and obtain the user electricity consumption fluctuation value; classify the data by weekdays and weekends, for example, weekdays are Monday to Friday, and weekends are Saturday and Sunday, calculate the average electricity consumption time on weekdays and weekends respectively, and compare the average usage time on weekdays with the average usage time on weekends to obtain the weekday-weekend usage time ratio; from the user's electricity usage habit indicator data and electricity usage time data Extract features from the data to construct a linear regression model, take the usage time ratio of weekdays to weekends, the degree of power consumption fluctuation, the degree of load fluctuation, and the power consumption time during peak hours, normal hours, and valley hours, use the extracted features as input, and take the power consumption during peak hours, normal hours, and valley hours as output, train the model, and correct the predicted value by the Bayesian method, and use the corrected peak power consumption prediction value as the discharge amount of the energy storage device during the peak period, the corrected normal power consumption prediction value as the charging amount of the energy storage device during the normal period, and the corrected valley power consumption prediction value as the charging amount of the energy storage device during the valley period, and use the trained model to obtain the peak power consumption, normal power consumption, and valley power consumption prediction values ​​respectively;

[0100] Among them, the new observation data includes input features and output variables. The input features are the feature data collected after the model is trained, including the usage time ratio between weekdays and weekends, the degree of power consumption fluctuation, the degree of load fluctuation, and any one of the power consumption time during peak hours, normal hours and off-peak hours. The output variables are the actual power consumption during peak hours, normal hours and off-peak hours.

[0101] In one embodiment, S4 includes the following steps:

[0102] By obtaining the peak, normal and off-peak periods of electricity consumption from the electricity price policy of the power system, and obtaining the electricity prices of the peak, normal and off-peak periods from the power grid company's agency power purchase price list, the peak electricity consumption forecast value is used as the discharge amount of the energy storage device during the peak period, the normal electricity consumption forecast value is used as the charging amount of the energy storage device during the normal period, and the off-peak electricity consumption forecast value is used as the charging amount of the energy storage device during the off-peak period. The cost of charging during the off-peak period and the normal period and the benefit of discharging during the peak period can be obtained respectively, and the actual settlement cost of the energy storage device can be obtained.

[0103] The actual settlement fee calculation formula is:

[0104]

[0105] Among them, M is the actual settlement cost of energy storage equipment (user energy storage settlement cost), P peak is the discharge amount during peak hours, M peak is the electricity price during peak hours, P avg is the charge amount in normal period, η is the charge and discharge efficiency of energy storage equipment, M avg is the electricity price during normal times, P valley is the charging capacity during the low-peak period, M valley The electricity price during off-peak hours.

[0106] Specifically, understand the electricity price policy of the power system in the area, obtain the standards for dividing peak hours, normal hours and off-peak hours, obtain the time range of peak hours, normal hours and off-peak hours based on the electricity price policy, and obtain electricity price information for peak hours, normal hours and off-peak hours from the local power grid company's agency electricity purchase price list.

[0107] Among them, for discharge during peak hours: multiply the electricity price during peak hours by the corresponding discharge amount to obtain the discharge revenue during peak hours.

[0108] For charging during normal periods, the electricity price, charging and discharging efficiency and corresponding charging amount during normal periods are combined to obtain the charging cost during normal periods.

[0109] For charging during off-peak hours, the electricity price, charging and discharging efficiency, and corresponding charging amount during the off-peak hours are combined to obtain the charging cost during the off-peak hours.

[0110] Add up the charging costs during normal and off-peak hours to get the total charging cost, list the discharge benefits during peak hours separately, and calculate the total charging cost and discharge benefits to get the actual settlement cost of the energy storage equipment.

[0111] In summary, the present invention solves the technical problems that it is difficult to extract multiple feature data from the user's electricity usage habit indicator data to construct a model, there is a lack of obtaining the charging and discharging amounts in different time periods according to the constructed model, and it is difficult to comprehensively settle the costs and benefits obtained in different time periods to obtain the actual settlement costs of the energy storage equipment.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A user energy storage auxiliary settlement method, characterized in that: The method includes: S1. Acquire and pre-process user-side data, and the user-side data includes user power consumption data, user power consumption habit indicator data, and energy storage device usage time data; S2. Based on the user's electricity consumption data, the user's electricity consumption habit index data and the energy storage equipment usage time data, calculate the user's load fluctuation degree, the user's electricity consumption fluctuation degree and the usage time ratio between weekdays and weekends; S3, obtaining the electricity consumption time data of each time period, and based on the electricity consumption time data, the user load fluctuation degree, the user electricity consumption fluctuation degree and the usage time ratio between weekdays and weekends, and combining the linear regression model and Bayesian theorem, outputting and correcting the electricity consumption forecast value of each time period; S4. Based on the corrected electricity consumption forecast value for each time period and the electricity price for each time period, the user's energy storage settlement fee is calculated.

2. A user energy storage auxiliary settlement method according to claim 1, characterized in that: The calculation of the user load fluctuation degree, the user power consumption fluctuation degree and the ratio of the usage time on weekdays to weekends based on the user power consumption data, the user power consumption habit index data and the energy storage device usage time data includes: Extracting the user power load data within a period from the user power usage habit index data, and the user power load data within the period includes the highest peak value, the lowest valley value and the average value; The user load fluctuation degree is calculated based on the highest peak value, lowest valley value and average value of the user power load data within the period; According to the user's electricity consumption data, the fluctuation degree of the user's electricity consumption is calculated; Based on the power consumption time data of the energy storage equipment and combined with the number of weekdays and weekends, the ratio of weekday to weekend usage time is calculated.

3. A user energy storage auxiliary settlement method according to claim 2, characterized in that: The user load fluctuation degree is calculated based on the highest peak value, the lowest valley value and the average value of the user power load data in the cycle, including: The user load fluctuation degree is calculated using the user's highest peak value in the cycle, the user's lowest valley value in the cycle, the user's average load value in the cycle, and the user's daily load value in the cycle.

4. A user energy storage auxiliary settlement method according to claim 2, characterized in that: The calculation of the fluctuation degree of the user's power consumption according to the user's power consumption data includes: The degree of fluctuation of the user's electricity consumption is calculated by using the user's daily electricity consumption within the cycle and the average electricity consumption within the user's cycle.

5. A user energy storage auxiliary settlement method according to claim 2, characterized in that: The calculation of the usage time ratio of weekdays to weekends based on the power usage time data of the energy storage device and the number of weekdays and weekends includes: Obtain the daily electricity consumption duration data of users within the period, and extract features from the user electricity consumption data and electricity consumption duration data to obtain the daily average electricity consumption and the standard deviation of electricity consumption; Based on the average daily electricity consumption and the standard deviation of electricity consumption, and combined with the machine learning algorithm, a classification model is trained and used to output the attributes of each day; Record the number of times each day is a working day to get the total number of working days in the cycle, and calculate the total number of weekend days in the cycle based on the difference between the total number of days in the cycle and the total number of working days in the cycle; The ratio of working day to weekend usage time is calculated using the total number of working days in the cycle, the usage time of the energy storage equipment on each working day, the total number of weekends in the cycle, and the usage time of the energy storage equipment on each weekend.

6. A user energy storage auxiliary settlement method according to claim 1, characterized in that: The acquisition includes power consumption time data for each time period, and based on the power consumption time data, user load fluctuation degree, user power consumption fluctuation degree and the ratio of usage time on weekdays to weekends, and combined with the linear regression model and Bayesian theorem, output and correct the power consumption forecast value for each time period, including: Collect electricity consumption time data for each time period, including peak time, normal time and off-peak time; The user load fluctuation degree, user power consumption fluctuation degree, weekday and weekend usage time ratio and power consumption time data are used as input, and power consumption is used as output to train the linear regression model and obtain the prediction model; The prediction model is used to output the predicted value of electricity consumption in each time period, and the predicted value of the prediction model is corrected based on the Bayesian algorithm.

7. A user energy storage auxiliary settlement method according to claim 6, characterized in that: The method of outputting the power consumption forecast value for each time period using the forecast model includes: Among the predicted electricity consumption output by the prediction model, the maximum value, median value and minimum value are used as the peak period electricity consumption forecast value, the normal period electricity consumption forecast value and the off-peak period electricity consumption forecast value respectively.

8. A user energy storage auxiliary settlement method according to claim 6, characterized in that: The correction of the predicted value of the prediction model based on the Bayesian algorithm includes: Obtain the prior probability of the prediction model, and calculate the likelihood function of the prediction model based on the observed data corresponding to the prediction model; Using Bayes' theorem and combining the prior probability and likelihood function of the prediction model, the posterior distribution of the prediction model parameters is calculated, and the posterior distribution is used to correct the predicted value of the prediction model.

9. A user energy storage auxiliary settlement method according to claim 8, characterized in that: The user energy storage settlement fee calculated based on the corrected power consumption forecast value of each time period and the electricity price of each time period includes: Get electricity prices during peak, normal and off-peak hours; The corrected peak-period electricity consumption forecast value is used as the discharge amount of the energy storage device during the peak period, the corrected normal-period electricity consumption forecast value is used as the charge amount of the energy storage device during the normal period, and the corrected valley-period electricity consumption forecast value is used as the charge amount of the energy storage device during the valley period; The calculation formula for user energy storage settlement fees is: Among them, M is the user's energy storage settlement fee; P peak is the discharge amount during peak hours, M peak is the electricity price during peak hours; P avg is the charge amount in normal period, η is the charge and discharge efficiency of energy storage equipment, M avg The electricity price during normal times; P valley is the charging capacity during the low-peak period, M valley The electricity price during off-peak hours.

10. A user energy storage auxiliary settlement system, used to implement the user energy storage auxiliary settlement method according to any one of claims 1 to 9, characterized in that: The system includes a data acquisition module, a characteristic data calculation module, a user electricity consumption prediction module and an energy storage electricity fee settlement module: The data acquisition module is used to acquire and pre-process user-side data, and the user-side data includes user power consumption data, user power consumption habit indicator data and energy storage device usage time data; The characteristic data calculation module is used to calculate the user load fluctuation degree, the user power consumption fluctuation degree and the usage time ratio between weekdays and weekends based on the user power consumption data, the user power consumption habit index data and the energy storage device usage time data; The user power consumption prediction module is used to obtain power consumption time data including each time period, and output and correct the power consumption prediction value of each time period based on the power consumption time data, user load fluctuation degree, user power consumption fluctuation degree and the usage time ratio between weekdays and weekends, and in combination with the linear regression model and Bayesian theorem; The energy storage electricity fee settlement module is used to calculate the user's energy storage settlement fee based on the corrected power consumption forecast value of each time period and the electricity price of each time period.

Images