Charging pile energy consumption scheduling method based on load prediction model

Abstract

The invention provides a charging pile energy consumption scheduling method based on a load prediction model, and the method comprises the steps: carrying out the data collection and preprocessing, obtaining multi-source data, such as charging, equipment, environment and electricity price, from a charging station management system, and cleaning abnormal values; and then using grey correlation analysis to determine weights of factors influencing energy consumption, constructing a grey prediction model, and combining preprocessing and weight distribution data to predict future charging pile load demands. And the control center receives a load prediction result and vehicle reservation information, preliminarily plans a charging distribution scheme according to the real-time state of the charging pile, and optimizes scheduling by taking the minimization of the total charging cost and consideration of the user satisfaction and the stability of the power system as targets through a simulated annealing algorithm. During operation, an actual state and an external environment are continuously monitored, a charging plan is rapidly adjusted when deviation occurs, finally, vehicle charging bills of all departments are generated according to an execution scheme, and system performance indexes are regularly evaluated to realize continuous optimization. The method can effectively reduce energy consumption cost and guarantee efficient and stable operation of the charging station.

Description

Technical Field

[0001] The present invention relates to the field of charging pile energy consumption scheduling, and in particular to a charging pile energy consumption scheduling method based on a load forecasting model. Background Art

[0002] With the increasing popularity of electric vehicles, the demand for charging stations is growing. Efficiently and rationally scheduling charging stations to reduce energy costs and improve service quality has become a key issue. Traditional charging station scheduling methods often lack comprehensive consideration and precise control of multiple factors.

[0003] In terms of energy consumption scheduling, load forecasting technology has not been fully utilized, making it impossible to predict charging demand at different times in advance, resulting in irrational allocation of power resources. On the one hand, during peak periods, a large number of vehicles charging simultaneously may exceed the power distribution capacity of charging stations, not only increasing peak electricity costs but also potentially impacting grid stability. On the other hand, during off-peak periods, charging station utilization is low, and low-priced electricity is not fully utilized.

[0004] Traditional methods for vehicle charging management fail to effectively integrate vehicle reservation information, department affiliation, and urgency, making it difficult to meet diverse user needs. This results in long wait times and a poor user experience. Furthermore, traditional scheduling methods lack the ability to respond in real time and dynamically adjust to changing charging station operating conditions and external environmental disturbances. This makes it difficult to promptly address charging station failures, new vehicle additions, power supply fluctuations, or unexpected weather changes, making charging plans difficult to execute.

[0005] Furthermore, in cost accounting and system evaluation, traditional methods are unable to accurately generate charging bills for each department's vehicles based on complex charging scenarios and multiple factors. They also struggle to comprehensively and scientifically evaluate system performance, thus failing to provide a robust basis for optimizing scheduling strategies. Therefore, a method for scheduling charging pile energy consumption based on a load forecasting model is urgently needed to address these issues and enable intelligent and efficient management of charging piles. Summary of the Invention

[0006] The main purpose of the present invention is to provide a charging pile energy consumption scheduling method based on a load forecasting model to solve the problem that with the popularization of electric vehicles, the demand for charging piles is increasing, and how to efficiently and reasonably schedule charging piles, reduce energy consumption costs and improve service quality has become a key issue.

[0007] To solve the above technical problems, the technical solution adopted by the present invention is: a charging pile energy consumption scheduling method based on a load forecasting model, the method comprising: S1. Obtain charging data from the charging station management system through the data interface module, pre-process the data, and store it in the database; S2. Extract data on factors affecting charging pile energy consumption from the database, determine the weights of each factor through grey correlation analysis, construct a grey prediction model, and use the pre-processed and weighted data to predict future charging pile load demand; S3: The control center receives the load forecast results and vehicle reservation information, and preliminarily plans the charging distribution plan for vehicles to each charging pile based on the real-time status of the charging piles; S4. Define a comprehensive evaluation function that minimizes the total charging cost while taking into account user satisfaction and power system stability. Apply the simulated annealing algorithm to optimize the initial scheduling plan. Find a better solution through multiple iterations and output the final scheduling plan. S5. Continuously monitor the actual operating status of the charging station and changes in the external environment, and transmit the monitoring data in real time. When the control center detects deviations between the actual operation and the scheduled scheduling plan, it will quickly re-evaluate and adjust the charging plan; S6. Automatically generate charging bills for vehicles in each department based on the final charging scheduling plan and actual charging volume; S7. Equipped with a system evaluation and feedback unit to regularly collect system operation data and evaluate system performance indicators.

[0008] In a preferred embodiment, the data acquired by the data interface module includes historical charging data, charging pile equipment parameters, environmental data, and electricity price information.

[0009] In the preferred solution, historical charging data is cleaned according to preset rules to remove data points where the charging amount is negative or far exceeds the capacity of the charging pile, which is obviously wrong. At the same time, fluctuating data is smoothed using techniques such as moving average. The processed data is stored in the database according to the charging time.

[0010] In the preferred solution, charging data, charging pile equipment parameters, environmental data, and electricity price information are selected from the database to create a factor set; Taking the historical charging energy consumption as the reference sequence and the sets of influencing factors as the comparison sequence, the grey correlation analysis algorithm is used to calculate the correlation degree, and the weight of each factor in load forecasting and scheduling is determined accordingly; The grey prediction model GM (1, N) is constructed using the preprocessed and weighted factor set data, where N is the number of influencing factors. By accumulating historical data to generate a new sequence, establishing a first-order differential equation and solving the parameters, the charging load demand of each charging pile at different time periods in the future, including the charging amount and power demand, is predicted.

[0011] In the preferred solution, the prediction result of the charging pile load demand obtained by the grey prediction model in step S3 is sent to the control center: The control center receives and stores the load forecast results as a two-dimensional array ,in Indicates the time interval, Indicates the charging pile number, stored in the time interval Internal charging pile The estimated amount of electricity that can be provided; Vehicle reservation information is stored as a structure array , including vehicle number , expected charge capacity , expected charging time interval , Vehicle Emergency Level ; Array for real-time status of charging pile Indicates that 0 is idle, 1 is occupied, and -1 is faulty, enabling effective organization of multi-source data; For each vehicle reservation information , by traversing all charging piles, according to the conditions: ,exist Make And the remaining power of the charging pile in the corresponding time interval satisfy , determine whether there is a preliminary feasible charging allocation plan for the vehicle and ensure that the allocation plan is within the capacity of the charging pile and the safety of power supply; By setting the electricity price period weight function , Vehicle urgency weight , appointment sequence weight , using the comprehensive priority score formula Calculate a composite priority score for each vehicle, a formula that takes into account multiple factors to determine the order in which vehicles should be charged; Sort the vehicles in descending order according to their comprehensive priority scores, starting with the vehicle with the highest priority, and select the vehicle with the remaining power within its feasible charging piles and time intervals. Relatively more combinations are allocated and updated , until all vehicles are allocated or cannot be allocated anymore, an initial charging scheduling plan including the vehicle-to-charging pile allocation relationship and the initial charging time series is generated.

[0012] In the preferred solution, the charging pile scheduling method of the simulated annealing algorithm in step S4 is: It includes a total charging cost calculation module, a power system stability assessment module, a comprehensive evaluation function construction module, and a comprehensive evaluation function construction module; Charging cost calculation module Vehicles to be charged, based on the vehicle Charge capacity And its charging pile Electricity prices , through the formula Calculate the total charging cost; Power system stability assessment module for vehicle arrival time and start charging time Calculate vehicle waiting time , and then calculate the average waiting time of vehicles , and use the user satisfaction function quantify, where is the adjustment factor; The comprehensive evaluation function building module is used to divide the time into Based on the period, Total charging power prediction value of all charging piles in and safe power cap , through the formula Calculating power system stability functions , is the time period weight coefficient; The comprehensive evaluation function construction module integrates the results of the above modules and uses the formula Constructing a comprehensive evaluation function , is the balance coefficient; The comprehensive evaluation function construction module comprehensively covers the key factors of cost, user satisfaction and power system stability, providing clear optimization target guidance for the simulated annealing algorithm.

[0013] In a preferred embodiment, the steps of executing the simulated annealing algorithm for optimizing charging pile scheduling according to claim 6 are as follows: Set the initial temperature of the simulated annealing algorithm , cooling rate and termination temperature , and determine the initial scheduling plan And calculate its fitness value , laying the foundation for the iterative process; In each iteration: by randomly perturbing the current solution Generate a neighborhood solution that meets the basic conditions; use the objective function to define the comprehensive evaluation function of the unit Compute neighborhood solutions The fitness value of ; Calculate the acceptance probability according to the Metropolis criterion ; is the current temperature; Combined with random numbers Determine whether to accept the neighborhood solution, update the solution, and promote the iterative process; According to the cooling rate Update temperature and by comparing the current temperature with the termination temperature Decide whether to terminate the iteration. If it is lower than , output the current solution as the optimized charging scheduling plan.

[0014] In a preferred embodiment, the method for continuously monitoring the charging station in step S5 is: It includes charging pile real-time power monitoring module, vehicle charging progress monitoring module, power supply fluctuation monitoring module and external environment change monitoring module; The real-time power monitoring module of the charging pile sets a power sensor in the charging pile to monitor the power of the charging pile at fixed time intervals. Collect power data and obtain charging piles Real-time power , and according to the formula Calculate the power change rate and combine it with the preset power fluctuation coefficient ,when When determining abnormal power fluctuation; The vehicle charging progress monitoring module is used to monitor the progress of each charging vehicle. , record the time when charging starts and battery capacity , by continuously obtaining the current charged capacity And according to the formula Calculate charging saturation and set charging progress threshold ,when It is determined that the vehicle is about to be fully charged; The new vehicle monitoring module records the arrival time of a new vehicle when it arrives. , vehicle type , Remaining battery power information and use functions trained on historical data Estimated charging time; The power supply fluctuation monitoring module installs power monitoring equipment at the grid connection end to obtain real-time voltage and current , according to the formula Calculate the real-time power and use the formula Combined with the preset power supply stability factor Determine if the power supply fluctuates, where Supply power for the expected electricity; External environment change monitoring module, monitoring temperature with the help of meteorological sensors ,humidity , wind speed Environmental parameters: When the rate of change of environmental parameters exceeds the preset range, it is determined that the external environment changes affect the system operation.

[0015] In the preferred solution, step S6 of generating charging bills for vehicles in each department of the charging pile is as follows: After charging is completed, for each vehicle , collect the departments to which they belong , Actual charge capacity , Start charging time and end charging time , and the electricity prices corresponding to each electricity price period , ensuring a comprehensive and accurate data basis for cost calculation; For vehicles Calculate the charging cost based on the charging period and the corresponding electricity price ; The charging process spans The calculation formula for different electricity price periods is: ; in, It's a vehicle During electricity price period To calculate the charge capacity First, you need to determine the vehicle At the start and end time of each electricity price period, The starting time of each electricity price period is , and the end time is ,but: ; Using the formula , summarize the expenses of vehicles in the same department and generate a detailed charging bill for each department. The bill covers the charging information and total cost of each vehicle in the department.

[0016] In the preferred solution, the steps for evaluating the performance indicators of the charging pile system in step S7 are: Define the performance indicators of charging cost reduction rate, load forecast accuracy, average vehicle waiting time, and charging pile utilization rate; By formula Calculate the charging cost reduction rate. This formula compares the average daily charging costs before and after the current scheduling scheme is adopted, visually reflecting the effectiveness of the current scheduling scheme in reducing charging costs. According to the formula Calculate load forecast accuracy index ,in is the total number of time intervals during the evaluation period. The formula is based on the mean absolute percentage error, which measures the closeness of the predicted charging load to the actual charging load. The closer the value is to 100%, the more accurate the prediction; It has a module for calculating the average waiting time of vehicles, using the formula Calculate the average waiting time of vehicles, where For vehicles The waiting time, is the total number of vehicles charged during the evaluation period; This formula is used to measure the user's waiting experience during the charging process; Using the formula Calculate the charging pile utilization rate, where is the total number of charging piles, is the total time of the evaluation period, For charging piles The time in the charging state; this formula reflects the efficiency of the use of charging pile resources; Conduct a comprehensive evaluation of the system based on the calculated results of various performance indicators; if some indicators do not meet expectations, find out the reasons by analyzing the data, and adjust relevant parameters or improve the algorithm based on the evaluation results.

[0017] This invention provides a method for scheduling charging pile energy consumption based on a load forecasting model. This method, combined with load forecasting and information on peak and off-peak electricity prices, allows for precise timing of charging. By prioritizing large charging tasks during off-peak periods, the method effectively leverages the difference between peak and off-peak electricity prices, significantly reducing charging costs at charging stations. Furthermore, rational scheduling reduces the additional costs and equipment losses that may result from overloading, improving the economic efficiency of charging station operations.

[0018] From a resource allocation perspective, this method integrates charging station distribution capacity, charging pile usage, and vehicle profile information, allowing for advance planning based on load forecasts. This avoids overuse of charging piles during certain periods while leaving them idle in others, improving overall charging pile utilization and enabling a more balanced and efficient allocation of power resources. This ensures that vehicle charging needs are met while remaining within distribution capacity limits, thus ensuring stable grid operation.

[0019] To improve user experience, we consider factors such as vehicle reservation information and urgency to rationally arrange charging times and charging stations for vehicles. This reduces average waiting times for vehicles, especially by prioritizing charging for emergency vehicles, meeting the diverse needs of different users and significantly improving user satisfaction.

[0020] This approach offers robust adaptability to complex and ever-changing real-world situations. By monitoring charging station operations and external environmental changes in real time, it can rapidly reassess and adjust charging plans if actual conditions deviate from the planned plan. Whether it's charging station failures, new vehicles entering the fleet, power supply fluctuations, or weather changes, this approach can flexibly address these challenges, ensuring smooth progress of charging plans and maintaining stable charging station operations.

[0021] In terms of fee settlement and system management, vehicle charging bills are automatically generated for the corresponding departments based on charging plans and vehicle types, facilitating financial accounting and management. Furthermore, system performance is regularly evaluated, and multi-dimensional data is collected to conduct in-depth analysis of existing system issues. Based on the evaluation results, load forecasting models and charging strategies are optimized, forming a closed-loop optimization mechanism. This continuously improves the system's overall service quality and operational efficiency, and promotes the continued development of intelligent and scientific charging pile energy consumption scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below with reference to the accompanying drawings and examples: Figure 1 This is a main structural diagram of the cleaning process of the present invention; DETAILED DESCRIPTION Example 1 like Figure 1 As shown, a charging pile energy consumption scheduling method based on a load forecasting model includes: S1. Obtain charging data from the charging station management system through the data interface module, pre-process the data, and store it in the database; S2. Extract data on factors affecting charging pile energy consumption from the database, determine the weights of each factor through grey correlation analysis, construct a grey prediction model, and use the pre-processed and weighted data to predict future charging pile load demand; S3: The control center receives the load forecast results and vehicle reservation information, and preliminarily plans the charging distribution plan for vehicles to each charging pile based on the real-time status of the charging piles; S4. Define a comprehensive evaluation function that minimizes the total charging cost while taking into account user satisfaction and power system stability. Apply the simulated annealing algorithm to optimize the initial scheduling plan. Find a better solution through multiple iterations and output the final scheduling plan. S5. Continuously monitor the actual operating status of the charging station and changes in the external environment, and transmit the monitoring data in real time. When the control center detects deviations between the actual operation and the scheduled scheduling plan, it will quickly re-evaluate and adjust the charging plan; S6. Automatically generate charging bills for vehicles in each department based on the final charging scheduling plan and actual charging volume; S7. Equipped with a system evaluation and feedback unit to regularly collect system operation data and evaluate system performance indicators.

[0023] In a preferred embodiment, the data acquired by the data interface module includes historical charging data, charging pile equipment parameters, environmental data, and electricity price information.

[0024] In the preferred solution, historical charging data is cleaned according to preset rules to remove data points where the charging amount is negative or far exceeds the capacity of the charging pile, which is obviously wrong. At the same time, fluctuating data is smoothed using techniques such as moving average. The processed data is stored in the database according to the charging time.

[0025] In the preferred solution, charging data, charging pile equipment parameters, environmental data, and electricity price information are selected from the database to create a factor set; Taking the historical charging energy consumption as the reference sequence and the sets of influencing factors as the comparison sequence, the grey correlation analysis algorithm is used to calculate the correlation degree, and the weight of each factor in load forecasting and scheduling is determined accordingly; The grey prediction model GM (1, N) is constructed using the preprocessed and weighted factor set data, where N is the number of influencing factors. By accumulating historical data to generate a new sequence, establishing a first-order differential equation and solving the parameters, the charging load demand of each charging pile at different time periods in the future, including the charging amount and power demand, is predicted.

[0026] The time factor is , divide the 24 hours of a day into 2-hour periods, a total of 12 periods, and use Indicates; ambient temperature factor is , in degrees Celsius; the electricity price period factor is , divided into peaks Pinggu , trough ; Charging pile usage frequency factor is , count the number of times each charging station was used in the past week. Then the factor set .

[0027] Grey correlation analysis calculation correlation degree: Assume that the historical charging energy consumption sequence is ,in is the number of historical data points. , whose data sequence is ,calculate and Grey correlation coefficient :

[0028] in is the resolution coefficient, set to $0.5$. 、 、 Similarly, calculate the correlation coefficient 、 、 Then calculate the correlation , 、 、 Similarly, the correlation formula is used to measure the closeness of each factor to charging energy consumption.

[0029] Example 2 Further illustrate with reference to Example 1, Figure 1 In the structure shown, the prediction result of the grey prediction model on the charging pile load demand in step S3 is sent to the control center: The control center receives and stores the load forecast results as a two-dimensional array ,in Indicates the time interval, Indicates the charging pile number, stored in the time interval Internal charging pile The estimated amount of electricity that can be provided; Vehicle reservation information is stored as a structure array , including vehicle number , expected charge capacity , expected charging time interval , Vehicle Emergency Level ; Array for real-time status of charging pile Indicates that 0 is idle, 1 is occupied, and -1 is faulty, enabling effective organization of multi-source data; For each vehicle reservation information , by traversing all charging piles, according to the conditions: ,exist Make And the remaining power of the charging pile in the corresponding time interval satisfy , determine whether there is a preliminary feasible charging allocation plan for the vehicle and ensure that the allocation plan is within the capacity of the charging pile and the safety of power supply; By setting the electricity price period weight function , Vehicle urgency weight , appointment order weight , using the comprehensive priority score formula Calculate a composite priority score for each vehicle, a formula that takes into account multiple factors to determine the order in which vehicles should be charged; Example 3 Further illustrate with reference to Example 1, Figure 1 The structure shown in FIG4 shows, the charging pile scheduling method of the simulated annealing algorithm in step S4 is: It includes a total charging cost calculation module, a power system stability assessment module, a comprehensive evaluation function construction module, and a comprehensive evaluation function construction module; Charging cost calculation module Vehicles to be charged, according to the vehicle Charge capacity And its charging pile Electricity prices , through the formula Calculate the total charging cost; Power system stability assessment module for vehicle arrival time and start charging time Calculate vehicle waiting time , and then calculate the average waiting time of vehicles , and use the user satisfaction function quantify, where is the adjustment factor; The comprehensive evaluation function building module is used to divide the time into Based on the period, Total charging power prediction value of all charging piles in and safe power cap , through the formula Calculating power system stability functions , is the time period weight coefficient; The comprehensive evaluation function construction module integrates the results of the above modules and uses the formula Constructing a comprehensive evaluation function , is the balance coefficient; The comprehensive evaluation function construction module comprehensively covers the key factors of cost, user satisfaction and power system stability, providing clear optimization target guidance for the simulated annealing algorithm.

[0030] In a preferred embodiment, the steps of executing the simulated annealing algorithm for optimizing charging pile scheduling according to claim 6 are as follows: Set the initial temperature of the simulated annealing algorithm , cooling rate and termination temperature , and determine the initial scheduling plan And calculate its fitness value , laying the foundation for the iterative process; In each iteration: by randomly perturbing the current solution Generate a neighborhood solution that meets the basic conditions; use the objective function to define the comprehensive evaluation function of the unit Compute neighborhood solutions The fitness value of ; Calculate the acceptance probability according to the Metropolis criterion ; is the current temperature; Combined with random numbers Determine whether to accept the neighborhood solution, update the solution, and promote the iterative process; According to the cooling rate Update temperature and by comparing the current temperature with the termination temperature Decide whether to terminate the iteration. If it is lower than , output the current solution as the optimized charging scheduling plan.

[0031] In a preferred embodiment, the method for continuously monitoring the charging station in step S5 is: It includes charging pile real-time power monitoring module, vehicle charging progress monitoring module, power supply fluctuation monitoring module and external environment change monitoring module; The real-time power monitoring module of the charging pile sets a power sensor in the charging pile to monitor the power of the charging pile at fixed time intervals. Collect power data and obtain charging piles Real-time power , and according to the formula Calculate the power change rate and combine it with the preset power fluctuation coefficient ,when When determining abnormal power fluctuation; The vehicle charging progress monitoring module is used to monitor the progress of each charging vehicle. , record the time when charging starts and battery capacity , by continuously obtaining the current charged capacity And according to the formula Calculate charging saturation and set charging progress threshold ,when It is determined that the vehicle is about to be fully charged; The new vehicle monitoring module records the arrival time of a new vehicle when it arrives. , vehicle type , Remaining battery power information and use functions trained on historical data Estimated charging time; The power supply fluctuation monitoring module installs power monitoring equipment at the grid connection end to obtain real-time voltage and current , according to the formula Calculate the real-time power and use the formula Combined with the preset power supply stability factor Determine if the power supply fluctuates, where Supply power for the expected electricity; External environment change monitoring module, monitoring temperature with the help of meteorological sensors ,humidity , wind speed Environmental parameters: When the rate of change of environmental parameters exceeds the preset range, it is determined that the external environment changes affect the system operation.

[0032] Example 4 Further illustrate with reference to Example 1, Figure 1 In the structure shown, step S6 generates the charging bills for each department of the charging pile vehicle as follows: After charging is completed, for each vehicle , collect the departments to which they belong , Actual charge capacity , Start charging time and end charging time , and the electricity prices corresponding to each electricity price period , ensuring a comprehensive and accurate data basis for cost calculation; For vehicles Calculate the charging cost based on the charging period and the corresponding electricity price ; The charging process spans Different electricity price periods, the calculation formula is: ; in, It's a vehicle During electricity price period To calculate the charge capacity First, you need to determine the vehicle At the start and end time of each electricity price period, The starting time of each electricity price period is , and the end time is ,but: ; Using the formula , summarize the expenses of vehicles in the same department and generate a detailed charging bill for each department. The bill covers the charging information and total cost of each vehicle in the department.

[0033] Example 5 Further illustrate with reference to Example 1, Figure 1 In the structure shown, the steps for evaluating the performance indicators of the charging pile system in step S7 are: Define the performance indicators of charging cost reduction rate, load forecast accuracy, average vehicle waiting time, and charging pile utilization rate; By formula Calculate the charging cost reduction rate. This formula compares the average daily charging costs before and after the current scheduling scheme is adopted, visually reflecting the effectiveness of the current scheduling scheme in reducing charging costs. According to the formula Calculate load forecast accuracy index ,in is the total number of time intervals during the evaluation period. The formula is based on the mean absolute percentage error, which measures the closeness of the predicted charging load to the actual charging load. The closer the value is to 100%, the more accurate the prediction; It has a module for calculating the average waiting time of vehicles, using the formula Calculate the average waiting time of vehicles, where For vehicles The waiting time, is the total number of vehicles charged during the evaluation period; This formula is used to measure the user's waiting experience during the charging process; Using the formula Calculate the charging pile utilization rate, where is the total number of charging piles, is the total time of the evaluation period, For charging piles The time in the charging state; this formula reflects the efficiency of the use of charging pile resources; Conduct a comprehensive evaluation of the system based on the calculated results of various performance indicators; if some indicators do not meet expectations, find out the reasons by analyzing the data, and adjust relevant parameters or improve the algorithm based on the evaluation results.

[0034] Based on the calculated results of the aforementioned performance indicators, a comprehensive system evaluation is conducted. If certain indicators fail to meet expectations, such as a low charging cost reduction rate or substandard load forecasting accuracy, data analysis is conducted to identify possible causes, such as inappropriate scheduling algorithm parameters or data quality issues. Based on the evaluation results, feedback is provided to adjust relevant parameters or improve the algorithm, such as adjusting parameters in the load forecasting model or optimizing the charging scheduling algorithm strategy, to continuously improve system performance.

[0035] The above embodiments are merely preferred technical solutions of the present invention and should not be construed as limiting the present invention. The scope of protection of the present invention shall be the technical solutions set forth in the claims, including equivalent alternatives to the technical features of the technical solutions set forth in the claims. In other words, equivalent alternatives and improvements within this scope are also within the scope of protection of the present invention.

Claims

1. A method for scheduling energy consumption of charging piles based on a load forecasting model, characterized by: The method includes: S1. Obtain charging data from the charging station management system through the data interface module, pre-process the data, and store it in the database; S2. Extract data on factors affecting charging pile energy consumption from the database, determine the weights of each factor through grey correlation analysis, construct a grey prediction model, and use the pre-processed and weighted data to predict future charging pile load demand; S3: The control center receives the load forecast results and vehicle reservation information, and preliminarily plans the charging distribution plan for vehicles to each charging pile based on the real-time status of the charging piles; S4. Define a comprehensive evaluation function that minimizes the total charging cost while taking into account user satisfaction and power system stability. Apply the simulated annealing algorithm to optimize the initial scheduling plan. Find a better solution through multiple iterations and output the final scheduling plan. S5. Continuously monitor the actual operating status of the charging station and changes in the external environment, and transmit the monitoring data in real time. When the control center detects deviations between the actual operation and the scheduled scheduling plan, it will quickly re-evaluate and adjust the charging plan; S6. Automatically generate charging bills for vehicles in each department based on the final charging scheduling plan and actual charging volume; S7. Equipped with a system evaluation and feedback unit to regularly collect system operation data and evaluate system performance indicators.

2. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 1, wherein: The data obtained by the data interface module includes historical charging data, charging pile equipment parameters, environmental data, and electricity price information.

3. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 1, wherein: The historical charging data is cleaned according to preset rules to remove data points with negative charging amounts or obviously incorrect data points that far exceed the charging pile capacity. At the same time, fluctuating data are smoothed using technologies such as moving average. The processed data is stored in the database according to the charging time.

4. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 3, wherein: Select charging data, charging pile equipment parameters, environmental data, and electricity price information from the database to build a factor set; Taking the historical charging energy consumption as the reference sequence and the sets of influencing factors as the comparison sequence, the grey correlation analysis algorithm is used to calculate the correlation degree, and the weight of each factor in load forecasting and scheduling is determined accordingly; The grey prediction model GM (1, N) is constructed using the preprocessed and weighted factor set data, where N is the number of influencing factors. By accumulating historical data to generate a new sequence, establishing a first-order differential equation and solving the parameters, the charging load demand of each charging pile at different time periods in the future, including the charging amount and power demand, is predicted.

5. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 4 is characterized by: In step S3, the prediction result of the grey prediction model for the charging pile load demand is sent to the control center: The control center receives and stores the load forecast results as a two-dimensional array ,in Indicates the time interval, Indicates the charging pile number, stored in the time interval Internal charging pile The estimated amount of electricity that can be provided; Vehicle reservation information is stored as a structure array , including vehicle number , expected charge capacity , expected charging time interval , Vehicle Emergency Level ; Array for real-time status of charging pile Indicates that 0 is idle, 1 is occupied, and -1 is faulty, enabling effective organization of multi-source data; For each vehicle reservation information , by traversing all charging piles, according to the conditions: ,exist Make And the remaining power of the charging pile in the corresponding time interval satisfy , determine whether there is a preliminary feasible charging allocation plan for the vehicle and ensure that the allocation plan is within the capacity of the charging pile and the safety of power supply; By setting the electricity price period weight function , Vehicle urgency weight , appointment sequence weight , using the comprehensive priority score formula Calculate a composite priority score for each vehicle, a formula that takes into account multiple factors to determine the order in which vehicles should be charged; Sort the vehicles in descending order according to their comprehensive priority scores, starting with the vehicle with the highest priority, and select the vehicle with the remaining power within its feasible charging piles and time intervals. Relatively more combinations are allocated and updated , until all vehicles are allocated or cannot be allocated anymore, an initial charging scheduling plan including the vehicle-to-charging pile allocation relationship and the initial charging time series is generated.

6. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 1, wherein: The charging pile scheduling method of the simulated annealing algorithm in step S4 is: It includes a total charging cost calculation module, a power system stability assessment module, a comprehensive evaluation function construction module, and a comprehensive evaluation function construction module; Charging cost calculation module Vehicles to be charged, according to the vehicle Charge capacity And its charging pile Electricity prices , through the formula Calculate the total charging cost; Power system stability assessment module for vehicle arrival time and start charging time Calculate vehicle waiting time , and then calculate the average waiting time of vehicles , and use the user satisfaction function quantify, where is the adjustment factor; The comprehensive evaluation function building module is used to divide the time into Based on the period, Total charging power prediction value of all charging piles in and safe power cap , through the formula Calculating power system stability functions , is the time period weight coefficient; The comprehensive evaluation function construction module integrates the results of the above modules and uses the formula Constructing a comprehensive evaluation function , is the balance coefficient; The comprehensive evaluation function construction module comprehensively covers the key factors of cost, user satisfaction and power system stability, providing clear optimization target guidance for the simulated annealing algorithm.

7. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 6, wherein: The steps for executing the simulated annealing algorithm for optimizing charging pile scheduling according to claim 6 are as follows: Set the initial temperature of the simulated annealing algorithm , cooling rate and termination temperature , and determine the initial scheduling plan And calculate its fitness value , laying the foundation for the iterative process; In each iteration: by randomly perturbing the current solution Generate neighborhood solutions that meet basic conditions; Using the objective function to define the comprehensive evaluation function of the unit Compute neighborhood solutions The fitness value of ; Calculate the acceptance probability based on the Metropolis criterion ; is the current temperature; Combined with random numbers Determine whether to accept the neighborhood solution, update the solution, and promote the iterative process; According to the cooling rate Update temperature and by comparing the current temperature with the termination temperature Decide whether to terminate the iteration. If it is lower than , output the current solution as the optimized charging scheduling plan.

8. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 1, wherein: The method for continuously monitoring the charging station in step S5 is: It includes charging pile real-time power monitoring module, vehicle charging progress monitoring module, power supply fluctuation monitoring module and external environment change monitoring module; The real-time power monitoring module of the charging pile sets a power sensor in the charging pile to monitor the power of the charging pile at fixed time intervals. Collect power data and obtain charging piles Real-time power , and according to the formula Calculate the power change rate and combine it with the preset power fluctuation coefficient ,when When determining abnormal power fluctuation; The vehicle charging progress monitoring module is used to monitor the progress of each charging vehicle. , record the time when charging starts and battery capacity , by continuously obtaining the current charged capacity And according to the formula Calculate charging saturation and set charging progress threshold ,when It is determined that the vehicle is about to be fully charged; The new vehicle monitoring module records the arrival time of a new vehicle when it arrives. , vehicle type , Remaining battery power information and use functions trained on historical data Estimated charging time; The power supply fluctuation monitoring module installs power monitoring equipment at the grid connection end to obtain real-time voltage and current , according to the formula Calculate the real-time power and use the formula Combined with the preset power supply stability factor Determine if the power supply fluctuates, where Supply power for the expected electricity; External environment change monitoring module, monitoring temperature with the help of meteorological sensors ,humidity , wind speed Environmental parameters: When the rate of change of environmental parameters exceeds the preset range, it is determined that the external environment changes affect the system operation.

9. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 1, wherein: Step S6 generates the charging bills for each department of the charging pile vehicle as follows: After charging is completed, for each vehicle , collect the departments to which they belong , Actual charge capacity , Start charging time and end charging time , and the electricity prices corresponding to each electricity price period , ensuring a comprehensive and accurate data basis for cost calculation; For vehicles Calculate the charging cost based on the charging period and the corresponding electricity price ; The charging process spans The calculation formula for different electricity price periods is: ； in, It's a vehicle During electricity price period To calculate the charge capacity First, you need to determine the vehicle At the start and end time of each electricity price period, The starting time of each electricity price period is , and the end time is ,but: ； Using the formula , summarize the expenses of vehicles in the same department and generate a detailed charging bill for each department. The bill covers the charging information and total cost of each vehicle in the department.

10. The method for scheduling energy consumption of charging piles based on a load forecasting model according to claim 1, wherein: The steps for evaluating the performance indicators of the charging pile system in step S7 are: Define the performance indicators of charging cost reduction rate, load forecast accuracy, average vehicle waiting time, and charging pile utilization rate; By formula Calculate the charging cost reduction rate. This formula compares the average daily charging costs before and after the current scheduling scheme is adopted, visually reflecting the effectiveness of the current scheduling scheme in reducing charging costs. According to the formula Calculate load forecast accuracy index ,in is the total number of time intervals during the evaluation period. The formula is based on the mean absolute percentage error, which measures the closeness of the predicted charging load to the actual charging load. The closer the value is to 100%, the more accurate the prediction; It has a module for calculating the average waiting time of vehicles, using the formula Calculate the average waiting time of vehicles, where For vehicles The waiting time, is the total number of vehicles charged during the evaluation period; This formula is used to measure the user's waiting experience during the charging process; Using the formula Calculate the charging pile utilization rate, where is the total number of charging piles, is the total time of the evaluation period, For charging piles Time in charging state; This formula reflects the efficiency of using charging pile resources; Conduct a comprehensive evaluation of the system based on the calculated results of various performance indicators; if some indicators do not meet expectations, find out the reasons by analyzing the data, and adjust relevant parameters or improve the algorithm based on the evaluation results.

Images