Remote electric charge management method for power grid

Abstract

The invention relates to the technical field of power grid dispatching, and discloses a power grid remote electricity charge management method, which comprises the following steps: collecting electric energy use data of a current user and current environment data; the method comprises the following steps: constructing a total power consumption prediction model through collected electric energy use data and current environment data of a current user, analyzing the real-time electric energy use data and the current environment data, and generating a scheduling strategy; according to the scheduling strategy, generating a corresponding power grid scheduling instruction, and performing optimization and real-time demand response management on the power distribution network; and generating a user power consumption bill based on the charging rule. The power grid can realize efficient and flexible scheduling by adjusting the generating capacity, the power transmission line and the user demand response in real time in combination with strategy optimization and artificial intelligence model updating, guarantees the stability and economy of power supply, and promotes the consumption of renewable energy sources and the participation of users at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid dispatching, and in particular to a remote power grid electricity fee management method. Background Art

[0002] At present, smart grid technology is a key component of the modernization of the power system. It realizes the intelligence, efficiency and reliability of the power system by integrating advanced information and communication technology and intelligent control technology. The goal of smart grid is to optimize the allocation of power resources, improve the efficiency and reliability of power grid operation, promote the access of new energy and electric vehicles, and enhance user participation and interactivity. With the growth of energy demand and the improvement of environmental protection awareness, smart grid has become an inevitable trend in the development of future power systems.

[0003] Faced with increasingly complex and dynamic electricity demand, improving the flexibility, rapid response and self-healing capabilities of the power grid is an important challenge facing the current power system; although artificial intelligence and big data have broad application prospects in power systems, how to efficiently and accurately use these technologies for load forecasting, fault diagnosis, etc. still requires in-depth research. Summary of the invention

[0004] The purpose of this invention is to achieve efficient and flexible scheduling of the power grid by adjusting power generation, transmission lines and user demand response in real time, combined with strategy optimization and artificial intelligence model updating, to ensure the stability and economy of power supply, while promoting the consumption of renewable energy and user participation.

[0005] In order to achieve the above object, the present invention provides a method for remote electricity fee management of a power grid, comprising:

[0006] Collect the current user's power usage data and current environmental data;

[0007] Build a total electricity consumption prediction model and generate a scheduling strategy based on current user electricity usage data and environmental data;

[0008] Generate corresponding grid dispatching instructions according to the dispatching strategy, and modify the working parameters of the distribution network according to the grid dispatching instructions;

[0009] Generate user electricity bills based on billing rules.

[0010] In some embodiments of the present invention, constructing a total electricity consumption prediction model includes:

[0011] Obtain historical power data, including historical power data from the power supply end and historical power acquisition from the power consumption end;

[0012] The historical power data of the power supply end includes: obtaining the historical voltage data U, historical current data I, and historical power factor of the power supply end. Generate the total power consumption E1 of the first stage;

[0013] Compare the total power consumption E in the first phase with the historical power consumption E S , determine the total transmission loss Q;

[0014] Calculate the total transmission loss Q in different time periods W ;

[0015] Combined with the total transmission loss Q in different time periods W , get the total power consumption E2 of the second stage;

[0016] The total transmission loss is classified into different levels to obtain a total electricity consumption prediction model.

[0017] In some embodiments of the present invention, determining the total power transmission loss Q includes:

[0018] Obtain historical user power usage data, including:

[0019] User historical voltage data U,U=[u1,u2…u t …u n ];

[0020] User historical current data I,I=[i1,i2…i t …i n ];

[0021] User historical power factor

[0022]

[0023] Among them, u t Represents the historical voltage data value of the t period, i t Represents the historical current data value of the t period, represents the historical power factor of the tth period, n represents the last period of the historical data, and T represents the length of the period;

[0024] The total amount of electricity required by users is predicted based on historical electricity usage data as follows:

[0025]

[0026] Obtain the historical electric energy obtained at the power consumption end ES and obtain the total transmission loss Q, Q = |E1-ES|.

[0027] In some embodiments of the present invention, the total power transmission loss Q in different time periods is calculated. W ,include:

[0028] Based on historical environmental data, a temperature range is selected and evenly divided into different temperature sub-ranges. The total power transmission loss in the time period corresponding to each temperature sub-range is calculated and the total power transmission loss is calculated and arranged in ascending order to obtain Q. W =[Q1,Q2,…Q i …,Q n ];

[0029] Among them, Q W represents the total power transmission loss in the time period corresponding to different temperature sub-ranges; Q1 represents the total power transmission loss in the first section, Q i represents the total transmission loss in the i-th section, and n represents the number of time periods;

[0030] In some embodiments of the present invention, the total power transmission loss Q in different time periods is combined W , the total power consumption E2 of the second stage is obtained, including:

[0031] By calculating the total power transmission loss of the corresponding time period under different user power usage data multiple times and taking the average value, an estimated value Q' of the impact of different temperatures on the total power transmission loss is generated. W , through the estimated value Q' of the impact of different temperatures on the total transmission loss W Generate the total power consumption of the second stage E2, E2 = E1 + Q' W .

[0032] In some embodiments of the present invention, generating a scheduling strategy includes:

[0033] The current user's power usage data and environmental data are input into the total power consumption prediction model, and the total power consumption of the current user in the second stage is output. By dividing the user types and the power consumption growth rate k of different user types, the total power consumption in the third stage E3 is obtained, E3 = E2 × (1 + k);

[0034] Different scheduling strategies are formulated based on the total electricity consumption E3 in the third stage.

[0035] In some embodiments of the present invention, calculating the electricity consumption growth rate k according to the user type includes:

[0036] Obtain historical power usage data and behavior pattern data to generate multiple influencing factors;

[0037] Multiple user categories are constructed according to different value ranges of influencing factors, and the average electricity consumption growth rate of users in different categories is calculated respectively.

[0038] In some embodiments of the present invention, different scheduling strategies are formulated based on the total power consumption E3 in the third stage, including:

[0039] The total power consumption E3 in the third stage is used to generate the overall power distribution in the current test area;

[0040] Based on the overall power distribution in the current area to be tested, the power consumption areas are incrementally classified to generate power consumption areas representing different power consumption levels, including:

[0041] Primary electricity consumption area, secondary electricity consumption area and tertiary electricity consumption area;

[0042] Based on different electricity consumption levels, different electricity scheduling strategies are generated for different electricity consumption areas.

[0043] In some embodiments of the present invention, different power consumption scheduling strategies are generated for different power consumption areas based on different power consumption levels, including:

[0044] Primary scheduling strategy and secondary scheduling strategy;

[0045] Among them, the first-level dispatching strategy is to correct the power supply parameters of different power consumption areas based on different power consumption levels;

[0046] Reduce the current total power supply for the first-level power consumption area;

[0047] Maintain the current total power supply for secondary power consumption areas;

[0048] Increase the current total power supply for the third-level power consumption areas;

[0049] The secondary dispatch strategy is to formulate different demand response policies according to the different types of users in the power consumption area to adjust the user's power consumption and power consumption period.

[0050] In some embodiments of the present invention, generating a user electricity bill based on a billing rule includes:

[0051] Calculate the remaining usage time of the user's current power consumption based on the user's real-time estimated value E3 and the billing rules;

[0052] Users are divided into different levels according to the remaining usage time;

[0053] Send remaining usage time and demand response policies to users of different levels.

[0054] Compared with the prior art, the remote electricity fee management method of the power grid according to the embodiment of the present invention has the following beneficial effects:

[0055] By analyzing historical voltage data, current data and power factor, the total electricity consumption prediction model constructed can more accurately predict the total electricity consumption in the current time period, thereby providing more accurate data support for power grid dispatching.

[0056] By comparing the historical power consumption at the power consumption end with the predicted total power consumption, the total transmission loss can be accurately calculated, and the change in loss in different time periods can be further analyzed; this helps power grid operators identify loss characteristics and take measures to reduce losses.

[0057] Combined with the total electricity consumption prediction model, the power grid can monitor and manage the power quality in different time periods in real time to ensure the stability and reliability of power supply.

[0058] Through effective management and optimized scheduling of transmission losses, energy waste can be reduced, the implementation of energy-saving and emission reduction policies can be supported, and the goal of sustainable development can be met.

[0059] Accurate energy usage forecasting and real-time monitoring can help grid operators provide more personalized services, such as dynamic pricing and demand response incentives, and improve customer satisfaction.

[0060] The total electricity consumption prediction model can automatically adjust according to the grid operation status and external environmental changes, improving the grid's response and self-recovery capabilities to emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 The present invention provides a flow chart of a remote electricity fee management method for a power grid. DETAILED DESCRIPTION

[0062] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0063] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0064] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0065] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0066] like Figure 1 As shown, a method for remote electricity fee management of a power grid according to a preferred embodiment of the present invention includes:

[0067] Collect the current user's power usage data and current environmental data;

[0068] Build a total electricity consumption prediction model and generate a scheduling strategy based on current user electricity usage data and environmental data;

[0069] Generate corresponding grid dispatching instructions according to the dispatching strategy, and modify the working parameters of the distribution network according to the grid dispatching instructions;

[0070] Generate user electricity bills based on billing rules.

[0071] In this embodiment, billing management is the process by which a service provider calculates fees based on the user's use of services, which usually involves data collection, billing rule application, bill generation, and customer payment, etc.; including:

[0072] Real-time monitoring and recording of usage: Use smart meters, network flow meters and other equipment to monitor and record users' service usage in real time, such as electricity, traffic, call time, etc.; Environmental and status information: Factors that affect billing, such as time, location, service status and other information, also need to be collected.

[0073] Data cleaning and verification: Clean the collected data to remove outliers and erroneous data to ensure data accuracy; Data conversion: Convert the original data into a format recognizable by the billing system in preparation for billing calculations; Apply billing rules: Calculate fees based on service type, usage, time and other factors using preset billing rules.

[0074] Bill generation: Generate detailed bills based on the calculated fees, including service items, usage, unit price, total fees and other information; Bill review: Review the generated bills to ensure the accuracy and rationality of the billing results.

[0075] Bill notification: send bill information to customers via email, SMS or mail; payment management: provide multiple payment channels (such as online payment, bank transfer, etc.), track payment status, and handle unpaid bills.

[0076] Consumption behavior analysis: Analyze user consumption data, identify consumption patterns and trends, and provide a basis for billing strategy optimization. Billing strategy adjustment: Adjust billing rules and optimize service pricing based on market feedback and data analysis results.

[0077] Specifically in the smart grid, the process is as follows:

[0078] Real-time data collection by smart meters: Smart meters record users’ electricity consumption in real time.

[0079] Data upload to the server: The meter data is uploaded to the billing system server via the network.

[0080] Billing engine processing: The billing engine on the server calculates the fees based on the electricity price strategy and user electricity usage data.

[0081] Bill Generation and Notification: Generate monthly bills and send them electronically to users.

[0082] User Payment: Users pay their electricity bills online or via bank transfer.

[0083] Through smart meters and automated billing systems, remote billing management can be achieved to improve efficiency, reduce operating costs, and provide users with more transparent and convenient billing services.

[0084] In some embodiments of the present application, a total electricity consumption prediction model is constructed, including:

[0085] Obtain historical power data, including historical power data from the power supply end and historical power acquisition from the power consumption end;

[0086] The historical power data of the power supply end includes: obtaining the historical voltage data U, historical current data I, and historical power factor of the power supply end. Generate the total power consumption E1 of the first stage;

[0087] Compare the total power consumption E in the first phase with the historical power consumption E S , determine the total transmission loss Q;

[0088] Calculate the total transmission loss Q in different time periods W ;

[0089] Combined with the total transmission loss Q in different time periods W , get the total power consumption E2 of the second stage;

[0090] The total transmission loss is classified into different levels to obtain a total electricity consumption prediction model.

[0091] In some embodiments of the present application, determining the total power transmission loss Q includes:

[0092] Obtain historical user power usage data, including:

[0093] User historical voltage data U,U=[u1,u2…u t …u n ];

[0094] User historical current data I,I=[i1,i2…i t …i n ];

[0095] User historical power factor

[0096]

[0097] Among them, u t Represents the historical voltage data value of the t period, i t Represents the historical current data value of the t period, represents the historical power factor of the tth period, n represents the last period of the historical data, and T represents the length of the period;

[0098] The total amount of electricity required by users is predicted based on historical electricity usage data as follows:

[0099]

[0100] Obtain the historical electric energy obtained at the power consumption end ES and obtain the total transmission loss Q, Q = |E1-ES|.

[0101] In this embodiment, the first stage: predicting the total power consumption E1

[0102] Data preprocessing: Standardize historical data to ensure data quality.

[0103] Substitute historical data into the model to predict the electricity consumption in each period.

[0104] Total electricity consumption E1: Add the predicted electricity in each period to obtain the total electricity consumption E1 in the first stage.

[0105] Phase 2: Determine the total transmission loss Q

[0106] Query the historical electric energy acquisition ES of the power consumption end: obtain the historical electric energy acquisition ES of the power consumption end from the historical power supply information registration table.

[0107] Calculate the total transmission loss Q: Q = ES -E1 calculates the total transmission loss.

[0108] Example Results

[0109] Assuming E1 is 1000kWh and ES is 1050kWh, the total transmission loss Q is 50kWh.

[0110] During the day, the QW from 10 am to 12 am is 10 kWh, the QW from 5 pm to 7 pm is 20 kWh, and the average QW at other times is 5 kWh.

[0111] Combined with the loss model, E2 is predicted to be 1020kWh, which is closer to the actual power usage.

[0112] Through this series of steps, the total electricity consumption prediction model can more accurately predict electricity usage, assist in fine-grained management of the power grid, reduce losses and improve efficiency.

[0113] In some embodiments of the present application, the total transmission loss Q in different time periods is calculated. W ,include:

[0114] Based on historical environmental data, a temperature range is selected and evenly divided into different temperature sub-ranges. The total power transmission loss in the time period corresponding to each temperature sub-range is calculated and the total power transmission loss is calculated and arranged in ascending order to obtain Q. W =[Q1,Q2,…Q i …,Q n ];

[0115] Among them, Q W represents the total power transmission loss in the time period corresponding to different temperature sub-ranges; Q1 represents the total power transmission loss in the first section, Q i represents the total transmission loss in the i-th section, and n represents the number of time periods;

[0116] In this embodiment, a temperature range between -20 and 50 degrees Celsius is selected, each temperature range is 10 degrees Celsius, and time periods are divided based on different temperature ranges to calculate the total power transmission loss Q in different time periods. W , Q W =[Q1,Q2,Q3,Q4,Q5,Q6,Q7];

[0117] Among them, Q1 represents the total transmission loss corresponding to -20 to -10 degrees Celsius, Q2 represents the total transmission loss corresponding to -10 to 0 degrees Celsius, Q3 represents the total transmission loss corresponding to 0 to 10 degrees Celsius, Q4 represents the total transmission loss corresponding to 10 to 20 degrees Celsius, Q5 represents the total transmission loss corresponding to 20 to 30 degrees Celsius, Q6 represents the total transmission loss corresponding to 30 to 40 degrees Celsius, and Q7 represents the total transmission loss corresponding to 40 to 50 degrees Celsius;

[0118] In some embodiments of the present invention, the total power transmission loss Q in different time periods is combined W , the total power consumption E2 of the second stage is obtained, including:

[0119] By calculating the total power transmission loss of the corresponding time period under different user power usage data multiple times and taking the average value, an estimated value Q' of the impact of different temperatures on the total power transmission loss is generated. W , through the estimated value Q' of the impact of different temperatures on the total transmission loss W Generate the total power consumption of the second stage E2, E2 = E1 + Q' W .

[0120] In this embodiment, it is assumed that in a certain historical period, the total electricity consumption E1 obtained by the prediction model is 1000 kWh.

[0121] QW calculation: Assuming that in different temperature ranges, the calculated total transmission losses are Q1=10kWh, Q2=15kWh, Q3=18kWh, Q4=20kWh, Q5=25kWh, Q6=30kWh, and Q7=35kWh respectively.

[0122] Q'W calculation: In each temperature range, 10 historical data calculations are performed to obtain the loss value, which corresponds to Q' in a certain temperature range. W If the total power consumption E2 in the second stage is 20kWh, then the total power consumption E2 in the second stage is calculated as follows:

[0123] E2=1000kWh+20kWh=1020kWh;

[0124] Through the above steps, not only the prediction of electricity usage is considered, but also the impact of temperature on total transmission loss is combined to obtain a more accurate second-stage total electricity consumption forecast E2, providing more detailed and accurate data support for smart grid management.

[0125] In some embodiments of the present invention, generating a scheduling strategy includes:

[0126] The current user's power usage data and environmental data are input into the total power consumption prediction model, and the total power consumption of the current user in the second stage is output. By dividing the user types and the power consumption growth rate k of different user types, the total power consumption in the third stage E3 is obtained, E3 = E2 × (1 + k);

[0127] Different scheduling strategies are formulated based on the total electricity consumption E3 in the third stage.

[0128] In some embodiments of the present invention, calculating the electricity consumption growth rate k according to the user type includes:

[0129] Obtain historical power usage data and behavior pattern data to generate multiple influencing factors;

[0130] Multiple user categories are constructed according to different value ranges of influencing factors, and the average electricity consumption growth rate of users in different categories is calculated respectively.

[0131] In this embodiment, by understanding the electricity usage behavior and demand growth trend of user types, the power grid company can provide more personalized services, such as demand response programs and energy efficiency consulting, to improve user satisfaction.

[0132] Competitiveness in the electricity market: Through refined management and intelligent dispatching, power grid companies can enhance their competitiveness in the electricity market, attract more users and expand their market share.

[0133] Grid stability: Analysis of electricity consumption growth rates based on user types helps grid companies prevent and mitigate load fluctuations, reduce grid failures, and improve the stability and reliability of power supply.

[0134] In some embodiments of the present invention, different scheduling strategies are formulated based on the total power consumption E3 in the third stage, including:

[0135] The total power consumption E3 in the third stage is used to generate the overall power distribution in the current test area;

[0136] Based on the overall power distribution in the current area to be tested, the power consumption areas are incrementally classified to generate power consumption areas representing different power consumption levels, including:

[0137] Primary electricity consumption area, secondary electricity consumption area and tertiary electricity consumption area;

[0138] Based on different electricity consumption levels, different electricity scheduling strategies are generated for different electricity consumption areas.

[0139] In some embodiments of the present application,

[0140] In some embodiments of the present invention, different power consumption scheduling strategies are generated for different power consumption areas based on different power consumption levels, including:

[0141] Primary scheduling strategy and secondary scheduling strategy;

[0142] Among them, the first-level dispatching strategy is to correct the power supply parameters of different power consumption areas based on different power consumption levels;

[0143] Reduce the current total power supply for the first-level power consumption area;

[0144] Maintain the current total power supply for secondary power consumption areas;

[0145] Increase the current total power supply for the third-level power consumption areas;

[0146] The secondary dispatch strategy is to formulate different demand response policies according to the different types of users in the power consumption area to adjust the user's power consumption and power consumption period.

[0147] In this embodiment, the power scheduling strategy includes:

[0148] For areas with peak electricity demand, increase power generation or dispatch backup power sources;

[0149] For areas with stable or low electricity consumption, the grid load is monitored in real time, the load of the transmission lines is adjusted dynamically, and users are guided to adjust their electricity consumption behavior through price signals or incentives to encourage users to use electricity, thereby smoothing the grid load curve.

[0150] In this embodiment, the city power grid has a peak electricity consumption period from 17:00 to 21:00 on weekdays, a low electricity consumption period from 21:00 to 8:00 the next day, and the rest of the time is a stable electricity consumption period.

[0151] Peak electricity demand period: From 17:00 to 21:00, the grid dispatch center increases the output of thermal power plants and calls on gas turbines as fast-response power sources to meet peak electricity demand.

[0152] Stable electricity consumption period: During the stable electricity consumption period, the load of the transmission lines is dynamically adjusted through intelligent algorithms to ensure stable operation of the power grid. At the same time, the power generation of renewable energy is monitored and the amount of renewable energy connected to the grid is adjusted in a timely manner.

[0153] Low electricity consumption period: During the low electricity consumption period, time-of-use electricity price strategies are adopted, such as lowering electricity charges to guide users to transfer part of their electricity consumption (such as electric vehicle charging) to this period, while increasing the proportion of electricity grid-connected by renewable energy such as wind and solar energy.

[0154] By implementing the above strategies, the power grid can effectively respond to electricity demand in different power consumption cycles, achieve optimal allocation of power resources, ensure the stability and economy of power supply, and at the same time promote the use of renewable energy and promote the green transformation of the energy structure.

[0155] In some embodiments of the present application, generating corresponding power grid dispatching instructions according to the dispatching strategy includes:

[0156] Based on the analyzed strategy, the power grid dispatching instruction in this embodiment is generated, including:

[0157] Adjust power generation, optimize transmission lines, start or shut down energy storage systems, and adjust user demand response plans;

[0158] Among them, adjusting power generation: dynamically adjusting the output power of various types of generator sets based on load forecast and power generation capacity;

[0159] Optimize transmission lines: adjust line loads and optimize power transmission paths based on real-time grid status;

[0160] Demand response: Send demand response signals to users to encourage or incentivize them to adjust their electricity usage behavior and guide industrial users to produce during off-peak hours through price mechanisms.

[0161] In some embodiments of the present application, the power distribution network is optimized and demand response management is implemented, including:

[0162] Collect data during instruction execution, conduct in-depth analysis, and identify optimization points; Strategy optimization: Based on data analysis results, optimize scheduling strategies and instruction generation algorithms to improve prediction accuracy and scheduling efficiency; use artificial intelligence technology to update historical data during model construction and adjust parameters.

[0163] In some embodiments of the present invention, generating a user electricity bill based on a billing rule includes:

[0164] Calculate the remaining usage time of the user's current power consumption based on the user's real-time estimated value E3 and the billing rules;

[0165] Users are divided into different levels according to the remaining usage time;

[0166] Send remaining usage time and demand response policies to users of different levels.

[0167] In this embodiment, the power generation is adjusted: the output power of each type of generator set is dynamically adjusted according to the load forecast and power generation capacity; thermal power and hydropower: as base load power sources, the basic output is adjusted according to the predicted total load demand; wind power and photovoltaic power: according to weather and light conditions, the power generation of renewable energy is predicted, and the output of other types of power sources is adjusted in real time.

[0168] Optimize transmission lines: adjust line loads and optimize power transmission paths according to the real-time status of the power grid; line loads: adjust power distribution between lines through real-time monitoring to avoid overload and improve power transmission efficiency; power transmission paths: optimize power transmission paths and reduce losses based on power grid topology and real-time loads; start or shut down energy storage systems: start or shut down battery energy storage systems to smooth power grid loads according to real-time demand and forecasts; demand response management: send demand response signals to users and guide users to use electricity during off-peak hours through price mechanisms; price mechanisms: implement time-of-use electricity price strategies to encourage users to use electricity during off-peak hours; industrial users: send demand response signals to industrial users to encourage production during off-peak hours.

[0169] Strategy optimization and intelligent iteration

[0170] Data collection and analysis: Instruction execution data: Collect detailed data during the execution of dispatch instructions, including power generation adjustment, line load changes, energy storage system status, user response, etc.; In-depth analysis: Use big data and artificial intelligence technology to conduct in-depth analysis of the collected data and identify optimization points in the dispatch process.

[0171] Strategy optimization: Dispatching strategy optimization: Based on data analysis results, adjust the power generation and transmission line optimization strategies; Instruction generation algorithm optimization: Optimize the instruction generation algorithm to improve the accuracy and efficiency of dispatching instructions; Artificial intelligence model update: Historical data update: Regularly update historical data during the model construction process to reflect the latest power grid operation status and user behavior; Parameter adjustment: According to model performance, adjust algorithm parameters to improve the accuracy of prediction and scheduling.

[0172] Generate user electricity bills based on billing rules, including:

[0173] According to the real-time estimated value E3 of the user's electricity consumption and the billing rules, the usage time of the user's current electricity consumption balance is calculated, and the users are divided into different levels according to the length of the balance usage time. Different reminders and electricity scheduling strategies are given to users of different levels.

[0174] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. A method for remote electricity fee management of a power grid, characterized in that: include: Collect the current user's power usage data and current environmental data; Build a total electricity consumption prediction model and generate a scheduling strategy based on current user electricity usage data and environmental data; Generate corresponding grid dispatching instructions according to the dispatching strategy, and modify the working parameters of the distribution network according to the grid dispatching instructions; Generate user electricity bills based on billing rules.

2. The remote electricity fee management method for a power grid according to claim 1, characterized in that: Construct a total electricity consumption prediction model, including: Obtain historical power data, including historical power data from the power supply end and historical power acquisition from the power consumption end; The historical power data of the power supply end includes: obtaining the historical voltage data U, historical current data I, and historical power factor of the power supply end. Generate the total power consumption E1 of the first stage; Compare the total power consumption E in the first phase with the historical power consumption E S , determine the total transmission loss Q; Calculate the total transmission loss Q in different time periods W ; Combined with the total transmission loss Q in different time periods W , get the total power consumption E2 of the second stage; The total transmission loss is classified into different levels to obtain a total electricity consumption prediction model.

3. The remote electricity fee management method for a power grid according to claim 2, characterized in that: Determine the total transmission loss Q, including: Obtain historical user power usage data, including: User historical voltage data U,U=[u1,u2…u t …u n ]; User historical current data I,I=[i1,i2…i t …i n ]; User historical power factor Among them, u t Represents the historical voltage data value of the t period, i t Represents the historical current data value of the t period, represents the historical power factor of the tth period, n represents the last period of the historical data, and T represents the length of the period; The total amount of electricity required by users is predicted based on historical electricity usage data as follows: Obtain the historical electric energy obtained at the power consumption end ES and obtain the total transmission loss Q, Q = |E1-ES|.

4. The remote electricity fee management method for a power grid according to claim 2, characterized in that: Calculate the total transmission loss Q in different time periods W ,include: Based on historical environmental data, a temperature range is selected and evenly divided into different temperature sub-ranges. The total power transmission loss in the time period corresponding to each temperature sub-range is calculated and the total power transmission loss is calculated and arranged in ascending order to obtain Q. W =[Q1,Q2,…Q i …,Q n ]; Among them, Q W represents the total power transmission loss in the time period corresponding to different temperature sub-ranges; Q1 represents the total power transmission loss in the first section, Q i It represents the total transmission loss of the i-th section, and n represents the number of time periods.

5. The remote electricity fee management method for a power grid according to claim 4, characterized in that: Combined with the total transmission loss Q in different time periods W , the total power consumption E2 of the second stage is obtained, including: By calculating the total power transmission loss of the corresponding time period under different user power usage data multiple times and taking the average value, an estimated value Q' of the impact of different temperatures on the total power transmission loss is generated. W , through the estimated value Q' of the impact of different temperatures on the total transmission loss W Generate the total power consumption of the second stage E2, E2 = E1 + Q' W .

6. The remote electricity fee management method for a power grid according to claim 5, characterized in that: Generate a scheduling strategy, including: The current user's power usage data and environmental data are input into the total power consumption prediction model, and the total power consumption of the current user in the second stage is output. By dividing the user types and the power consumption growth rate k of different user types, the total power consumption in the third stage E3 is obtained, E3 = E2 × (1 + k); Different scheduling strategies are formulated based on the total electricity consumption E3 in the third stage.

7. The remote electricity fee management method for a power grid according to claim 6, characterized in that: According to the user type, calculate the electricity consumption growth rate k, including: Obtain historical power usage data and behavior pattern data to generate multiple influencing factors; Multiple user categories are constructed according to different value ranges of influencing factors, and the average electricity consumption growth rate of users in different categories is calculated respectively.

8. The remote electricity fee management method for a power grid according to claim 7, characterized in that: Different dispatching strategies are formulated based on the total power consumption E3 in the third stage, including: The total power consumption E3 in the third stage is used to generate the overall power distribution in the current test area; Based on the overall power distribution in the current area to be tested, the power consumption areas are incrementally classified to generate power consumption areas representing different power consumption levels, including: Primary electricity consumption area, secondary electricity consumption area and tertiary electricity consumption area; Based on different electricity consumption levels, different electricity scheduling strategies are generated for different electricity consumption areas.

9. The remote electricity fee management method for a power grid as claimed in claim 8, characterized in that: Based on different power consumption levels, different power dispatching strategies are generated for different power consumption areas, including: Primary scheduling strategy and secondary scheduling strategy; Among them, the first-level dispatching strategy is to correct the power supply parameters of different power consumption areas based on different power consumption levels; Reduce the current total power supply for the first-level power consumption area; Maintain the current total power supply for secondary power consumption areas; Increase the current total power supply for the third-level power consumption areas; The secondary dispatch strategy is to formulate different demand response policies according to the different types of users in the power consumption area to adjust the user's power consumption and power consumption period.

10. The remote electricity fee management method for a power grid according to claim 9, characterized in that: Generate user electricity bills based on billing rules, including: Calculate the remaining usage time of the user's current power consumption based on the user's real-time estimated value E3 and the billing rules; Users are divided into different levels according to the remaining usage time; Send remaining usage time and demand response policies to users of different levels.

Images