Electric vehicle multi-scale regulation and control method and system based on flexible load

Abstract

The invention discloses an electric vehicle multi-scale regulation and control method and system based on a flexible load, and relates to the technical field of electric vehicle charging control, and the method comprises the steps: building a load response model according to a charging habit, a charging time period and a charging demand; constructing a multi-layer control layer, and collecting load data, power grid state information and user charging behaviors of the charging pile in real time according to the multi-layer control layer; constructing load dynamic adjustment under different time scales by combining a plurality of control layers and a load response model; a charging plan is adjusted in real time according to the market electricity price, a charging and discharging strategy and user requirements, a flexible load strategy is applied to load dynamic adjustment under different time scales, and the charging load in the time-of-use electricity price period is reduced. According to the invention, the impact of electric vehicle charging on a power grid is effectively reduced, the utilization efficiency of electric energy is improved, and the charging process is intelligent and flexible; omnibearing and multi-scale optimization of the charging process of the electric vehicle is achieved, the charging load is effectively managed, and the pressure on a power grid in the peak period is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging control, and more specifically to a multi-scale control method and system for electric vehicles based on flexible loads. Background Art

[0002] In recent years, electric vehicles have become increasingly popular in the field of modern transportation due to their green and pollution-free advantages. The global electric vehicle market has shown exponential growth, with sales exceeding 10 million units in 2022 and a penetration rate of 14%.

[0003] However, with the rapid growth of electric vehicle ownership, their power consumption and power load have also increased, which has a profound impact on the power generation side. The potential impact of disorderly charging of electric vehicles on the power generation side includes increasing the power demand of the whole society and exacerbating the peak-to-valley difference of the power grid load. In terms of power consumption, one of the main driving forces for the rapid growth of power demand is the growth of the number of electric vehicles. In terms of power load, disorderly charging of electric vehicles will also increase the peak load of the whole network and aggravate the peak-to-valley difference of the load. Affected by residential power consumption and tertiary industry power consumption, the peak-to-valley difference of the national power grid is constantly expanding. Although the impact of electric vehicle charging on the power grid is not significant at present, if electric vehicles are charged disorderly during peak power consumption in the future, it may further aggravate the imbalance of power supply and demand. Therefore, it is necessary to dispatch electric vehicles to charge in an orderly manner to alleviate the peak-to-valley difference of the power generation side load, which is beneficial to the long-term development of electric vehicles. How to effectively manage the charging load and reduce the pressure on the power grid during peak periods has become an urgent problem to be solved. Existing technologies mostly focus on the regulation of a single time scale, and lack a comprehensive and multi-scale optimization solution for the electric vehicle charging process. Therefore, how to propose a multi-scale control method and system for electric vehicles based on flexible loads, to optimize the charging process of electric vehicles in an all-round and multi-scale manner, to effectively manage the charging load, and to reduce the pressure on the power grid during peak hours is an urgent problem that technicians in this field need to solve. Summary of the invention

[0004] In view of this, the present invention provides a multi-scale control method and system for electric vehicles based on flexible loads, which optimizes the charging process of electric vehicles in an all-round and multi-scale manner and effectively manages the charging load, aiming to optimize the charging process of electric vehicles, improve energy utilization efficiency, and reduce the impact on the power grid.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A multi-scale control method for electric vehicles based on flexible loads, comprising:

[0007] Establish a load response model based on charging habits, charging periods and charging needs;

[0008] Build a multi-layer control layer and collect the load data of charging piles, grid status information and user charging behavior in real time based on the multi-layer control layer;

[0009] Combine multiple control layers and load response models to build dynamic load adjustments at different time scales;

[0010] Adjust the charging plan in real time according to market electricity prices, charging and discharging strategies and user needs, apply flexible load strategies to dynamic load adjustment at different time scales, and reduce the charging load during time-of-use electricity price periods.

[0011] Optionally, establishing a load response model according to charging habits, charging time periods and charging requirements includes:

[0012] Determine the user's charging habits and charging time based on the collected historical charging data;

[0013] According to the time-of-use electricity price information of the power grid, predict and determine the charging demand of users in each period;

[0014] According to the user's charging habits, charging period and charging demand, the intention factor of electric vehicle charging is calculated, and the load response model of the electric vehicle is determined.

[0015] Optionally, determining the user's charging habits based on the collected historical charging data includes:

[0016] Obtain the user's charging data, calculate the unit daily charging amount based on the charging data, take the monthly span as the primary time interval, and divide the unit daily charging amount into multiple primary time intervals;

[0017] Calculate the daily average charge in each primary time interval, marking high-charge days and low-charge days;

[0018] It is determined whether the dates of high charging days and low charging days conform to the preset clustering rules to obtain the user's charging habits.

[0019] Optionally, after determining whether the dates of the high charging day and the low charging day meet the preset clustering rule, the method further includes:

[0020] If the dates of both high-charging days and low-charging days meet the preset clustering rules, the difference between the first average charging amount of the high-charging day and the second average charging amount of the low-charging day is calculated. If the difference is greater than the preset charging ratio of the daily average charging amount, it will be marked as a new charging habit;

[0021] Based on the user's charging data, the fluctuation of charging amount is analyzed to determine whether the user's charging habits and payment level have an impact on the charging level, accurately identify new charging habits, and re-determine whether the dates of high-charging days and low-charging days conform to the preset clustering rules to obtain the user's new charging habits.

[0022] Optionally, constructing a multi-layer control layer includes: constructing a micro layer, a macro layer and a super macro layer, and coordinating and regulating at different time scales. The micro layer optimizes the charging of individual electric vehicles, the macro layer focuses on the overall load management of charging piles, and the super macro layer considers the load balance of the power grid.

[0023] Optionally, the real-time adjustment of the charging plan according to the market electricity price, charging and discharging strategy and user demand, the application of flexible load strategy to the dynamic adjustment of load under different time scales, and the reduction of charging load during time-of-use electricity price periods include: considering the battery condition of the electric vehicle and constructing a charging optimization strategy for the electric vehicle; considering the overall load condition of the charging piles in the region and using the Monte Carlo method to establish a spatiotemporal distribution model of the overall load condition of the charging piles in the region; considering the demand response characteristics of the electric vehicle and establishing a load dynamic adjustment model based on the time-of-use electricity price with the optimization goal of minimizing the charging cost of the electric vehicle and the charging optimization strategy.

[0024] Optionally, the charging optimization strategy includes building a charging optimization model based on the battery SoC model, battery parameters and charging operations of the electric vehicle to predict the battery life.

[0025] Optionally, establishing a load dynamic adjustment model based on time-of-use electricity prices with minimizing the charging cost of electric vehicles and charging optimization strategies as optimization objectives includes establishing a multi-objective solution model with minimizing the charging cost of electric vehicles and minimizing battery life loss as optimization objectives.

[0026] Optionally, the consideration of demand response characteristics of electric vehicles includes:

[0027] Based on the environmental data corresponding to the target area in the target time period in the historical data, the user's driving habit data and the electric vehicle operating parameters, a trained electric vehicle operating parameter prediction model is obtained to obtain the operating parameters of the electric vehicle;

[0028] Combined with the output power parameters, torque demand parameters, in-vehicle environment parameters, and power feedback level parameters of the vehicle battery, the power consumption parameters of the electric vehicle during operation are determined;

[0029] Combined with operating parameters and power consumption parameters, the demand response of electric vehicles can be accurately evaluated and calculated.

[0030] Optionally, a multi-scale control system for electric vehicles based on flexible loads includes:

[0031] Load response model building module: used to build a load response model based on charging habits, charging time periods and charging needs;

[0032] Multi-layer control layer module: used to build a multi-layer control layer and collect the load data of the charging pile, the grid status information and the user charging behavior in real time according to the multi-layer control layer;

[0033] Load dynamic adjustment module: used to combine multiple control layers and load response models to build load dynamic adjustment at different time scales;

[0034] Control module: used to adjust the charging plan in real time according to the market electricity price, charging and discharging strategy and user demand, apply flexible load strategy to the dynamic adjustment of load under different time scales, and reduce the charging load during the time-of-use electricity price period.

[0035] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a multi-scale control method and system for electric vehicles based on flexible loads, which has the following beneficial effects:

[0036] The present invention proposes a multi-scale control method for electric vehicles based on flexible loads, including: establishing a load response model according to charging habits, charging time periods and charging needs; constructing a multi-layer control layer, and collecting load data of charging piles, power grid status information and user charging behavior in real time according to the multi-layer control layer; combining the multi-layer control layer and the load response model to construct dynamic load adjustment at different time scales; adjusting the charging plan in real time according to the market electricity price, charging and discharging strategy and user demand, applying a flexible load strategy to the dynamic load adjustment at different time scales, and reducing the charging load during the time-sharing electricity price period. By combining the multi-layer control layer and the load response model to construct dynamic load adjustment at different time scales; adjusting the charging plan in real time according to the market electricity price, charging and discharging strategy and user demand, applying a flexible load strategy to the dynamic load adjustment at different time scales, and reducing the charging load during the time-sharing electricity price period, the impact of electric vehicle charging on the power grid can be effectively reduced, the efficiency of electric energy utilization can be improved, the intelligentization and flexibility of the charging process can be realized, and an economical and affordable charging solution can be provided to users at the same time. The present invention realizes all-round and multi-scale optimization of the electric vehicle charging process, effectively manages the charging load, and reduces the pressure on the power grid during peak periods. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0038] Figure 1 A schematic flow chart of a multi-scale control method for an electric vehicle based on flexible load provided by the present invention.

[0039] Figure 2 A structural framework diagram of a flexible load-based electric vehicle multi-scale control system provided by the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] The embodiment of the present invention discloses a multi-scale control method for electric vehicles based on flexible loads, such as Figure 1 As shown, including:

[0042] Establish a load response model based on charging habits, charging periods and charging needs;

[0043] Build a multi-layer control layer and collect the load data of charging piles, grid status information and user charging behavior in real time based on the multi-layer control layer;

[0044] Combine multiple control layers and load response models to build dynamic load adjustments at different time scales;

[0045] Adjust the charging plan in real time according to market electricity prices, charging and discharging strategies and user needs, apply flexible load strategies to dynamic load adjustment at different time scales, and reduce the charging load during time-of-use electricity price periods.

[0046] Furthermore, establishing a load response model according to charging habits, charging time periods and charging requirements includes:

[0047] Determine the user's charging habits and charging time based on the collected historical charging data;

[0048] According to the time-of-use electricity price information of the power grid, predict and determine the charging demand of users in each period;

[0049] According to the user's charging habits, charging period and charging demand, the intention factor of electric vehicle charging is calculated, and the load response model of the electric vehicle is determined.

[0050] Furthermore, determining the user's charging habits based on the collected historical charging data includes:

[0051] Obtain the user's charging data, calculate the unit daily charging amount based on the charging data, take the monthly span as the primary time interval, and divide the unit daily charging amount into multiple primary time intervals;

[0052] Calculate the daily average charge in each primary time interval, marking high-charge days and low-charge days;

[0053] It is determined whether the dates of high charging days and low charging days conform to the preset clustering rules to obtain the user's charging habits.

[0054] Furthermore, after determining whether the dates of the high charging day and the low charging day meet the preset clustering rule, it also includes:

[0055] If the dates of both high-charging days and low-charging days meet the preset clustering rules, the difference between the first average charging amount of the high-charging day and the second average charging amount of the low-charging day is calculated. If the difference is greater than the preset charging ratio of the daily average charging amount, it will be marked as a new charging habit;

[0056] Based on the user's charging data, the fluctuation of charging amount is analyzed to determine whether the user's charging habits and payment level have an impact on the charging level, accurately identify new charging habits, and re-determine whether the dates of high-charging days and low-charging days conform to the preset clustering rules to obtain the user's new charging habits.

[0057] In a specific implementation, if the difference is greater than a preset charging ratio of the average daily charging amount, marking it as a new charging habit specifically includes:

[0058] Obtain the high charging date interval of each month, extract the overlapping dates from the high charging date intervals of multiple months, and obtain the intermediate time interval from the overlapping dates; obtain charging data and browsing data, the charging data includes the first-level commodity electricity consumption information and charging time, and the browsing data includes the intermediate commodity electricity consumption information and browsing time; identify the charging data with charging time in the intermediate time interval, match the corresponding first-level commodity electricity consumption information with the intermediate commodity electricity consumption information in the browsing data, and obtain multiple valid browsing times; calculate the average time difference between each valid browsing time and the charging time; calculate the average number of valid browsing times corresponding to each charging data; obtain the intermediate commodity electricity consumption information whose browsing time is less than or equal to the average time difference from the current time in the unmatched browsing data, identify the first browsing number of the electricity consumption information of the same type of commodity, if the first browsing number is greater than the average number of valid browsing times, then obtain the average price of commodity electricity; if the average price of commodity electricity is greater than the average daily charging amount of multiple months of the preset charging ratio, then mark the new charging habit.

[0059] Further, the calculating the daily average charge amount in each primary time interval and marking the high-charge day and the low-charge day comprises: calculating the daily average charge amount in each primary time interval, marking the date with a charge amount greater than the daily average as a high-charge day, and marking the date with a charge amount less than the daily average as a low-charge day;

[0060] The method also includes fitting a charging curve according to the daily charging amount in the primary time interval, identifying a secondary time interval whose absolute value of the slope on the charging curve exceeds a preset slope, and eliminating a high charging day or a low charging day corresponding to the secondary time interval.

[0061] In a specific implementation, predicting and determining the charging demand of users in each time period according to the time-sharing electricity price information of the power grid includes:

[0062] Time-of-use electricity price refers to the electricity price system that implements different electricity fee standards in each period according to the system load level. The time-of-use electricity price can be expressed as: P t =P0·(1+P r,t ),t=1,2,...,N p , where t represents the time period, N p is the total number of time periods divided, P t It represents the rate standard at time t, in units of ￥ / kW·h, P0 represents the basic electricity price, P r,t It indicates the floating ratio of the relative rate standard of each period to the basic electricity price. The time-of-use electricity price response is reflected by the restriction of load and electricity distribution in each period. Its constraint condition is to meet the restriction that the user's electricity fee is relatively small. The daily average electricity fee expenditure L in the past month is used as the electricity fee expenditure amount for judgment;

[0063] The load distribution process is as follows: (a) according to the characteristics of charging habits, solve the standard power consumption corresponding to each time period of the electric vehicle; (b) solve the total load of each time period; (c) solve the total electricity expenditure; (d) determine whether the total electricity expenditure exceeds the electricity expenditure quota L. If it exceeds, the use time of the electric vehicle is moderately shifted to the adjacent low electricity price period within one hour, and the shift duration is the time difference. If there is no adjacent low electricity price period, it ends. After adjusting the operating time period of the electric vehicle, repeat (b) and (c) until the total electricity expenditure is within the electricity expenditure quota L.

[0064] In a specific implementation, the calculation of the electric vehicle charging intention factor and determination of the electric vehicle load response model according to the user's charging habits, charging period and charging demand includes:

[0065] 1) The charging status of electric vehicles is often related to user satisfaction, and user satisfaction is also affected by their electric vehicle usage and charging habits. The electric vehicle intention factor K is used c To characterize the impact of the real-time state of the electric vehicle on the user's charging behavior, the larger the value, the lower the user's satisfaction. The charging state of the electric vehicle is related to the user's charging habits. c,iTo characterize the real-time status of the electric vehicle, users can respond to time-of-use electricity prices based on historical charging behavior and achieve reasonable control of smart electric vehicles based on electric vehicle satisfaction. The calculation formula is as follows:

[0066]

[0067] Where M n,i,t is the operating electricity cost of the electric vehicle during period t, M s,i,t is the electricity cost of electric vehicles during the period with the lowest electricity price, E u It is a collection of electric cars.

[0068] 2) Constructing the operation status model;

[0069]

[0070] In the formula, S u,t is the working state of the electric vehicle in period t, 0 represents the power-off state, 1 represents the power-on state, T i,t Represents the component of the fuzzy electricity consumption period matrix that is closest to period t.

[0071] 3) According to the satisfaction of electric vehicles, determine the dynamic control priority and control algorithm of electric vehicles to realize intelligent control of electric vehicles;

[0072] In order to achieve reasonable electric vehicle control, it is necessary to determine the control priority of electric vehicles and introduce the dynamic priority K of electric vehicle control. K can change in real time with the state of the electric vehicle. The larger the K value corresponding to an electric vehicle, the higher the priority control. For an electric vehicle, the electric vehicle satisfaction K c,i The larger the value is, the lower the user satisfaction is, and the higher the dynamic control priority is. Therefore, the satisfaction index K of electric vehicles can be used. c,i To characterize the dynamic control priority K of electric vehicles, the specific calculation process is as follows:

[0073] The solution formula of the sampling function Kapp(t) representing K is as follows:

[0074]

[0075] The solution formula of the electric vehicle priority function K(t) is as follows:

[0076] K (t)＝ N(K app (t));

[0077] Where N() is the sorting function of x, K app (t) is the sampling value of K in period t, K c (t) is the electric vehicle satisfaction in period t.

[0078] Furthermore, the construction of a multi-layer control layer includes: constructing a micro layer, a macro layer and a super macro layer to coordinate and regulate at different time scales. The micro layer optimizes the charging of individual electric vehicles, the macro layer focuses on the overall load management of charging piles, and the super macro layer considers the load balance of the power grid.

[0079] Furthermore, the real-time adjustment of the charging plan according to the market electricity price, charging and discharging strategy and user demand, the application of flexible load strategy to the dynamic adjustment of load under different time scales, and the reduction of charging load during time-of-use electricity price periods include: considering the battery condition of the electric vehicle and constructing a charging optimization strategy for the electric vehicle; considering the overall load condition of the charging piles in the region and using the Monte Carlo method to establish a spatiotemporal distribution model of the overall load condition of the charging piles in the region; considering the demand response characteristics of the electric vehicle and establishing a load dynamic adjustment model based on the time-of-use electricity price with minimizing the charging cost of the electric vehicle and the charging optimization strategy as the optimization goal.

[0080] Specifically, the Monte Carlo method based on randomness and probability is used to simulate the spatiotemporal distribution of charging demand in the planning area. A large number of electric vehicle travel records are obtained by random sampling according to the travel characteristics of electric vehicle owners in the planning area, and the spatiotemporal distribution of charging demand in the area is obtained through statistics. The activities of residents in the same area are periodic, and the cycle is one day. Therefore, the charging demand in the area for 24 hours is simulated with one hour as the unit time, and the spatiotemporal distribution model of the overall load of charging piles in the area is established according to the spatiotemporal distribution of charging demand in the area.

[0081] In a specific implementation, the real-time adjustment of the charging plan according to the market electricity price, charging and discharging strategy and user demand, the application of a flexible load strategy to the dynamic adjustment of the load at different time scales, and the reduction of the charging load during the time-of-use electricity price period also include:

[0082] Considering the properties of the traffic network, a traffic network model is established, and the congested road conditions are considered in the traffic network model. Specifically, a directed traffic network graph is established based on graph theory methods; the Dijkstra algorithm based on greedy and breadth-first search is widely used in shortest path search. This algorithm is used to plan the travel path with the shortest driving time for electric vehicles. The Dijkstra algorithm is used to search for the path with the smallest section weight between all nodes in the road network, and the driving time and distance of the planned path between each node are obtained; considering the satisfaction of electric vehicle owners and the randomness of charging, time constraints and scheduling scale constraints are added to the established scheduling optimization model; the particle swarm algorithm with penalty terms is used to solve the constrained scheduling optimization model.

[0083] In a specific implementation, the time constraint and the scheduling scale constraint are added to the established scheduling optimization model, including:

[0084] Assuming the owner has reserved The time period is designed to accept reasonable charging scheduling, and the constraints are constructed as follows:

[0085]

[0086] In the formula, x k ,t k They represent the ordered charging time and the disordered charging time of the kth electric vehicle respectively. The inequality constraint indicates that the charging time of the electric vehicle after being scheduled should not differ from the original charging time by more than the time expected by the owner.

[0087] In order to avoid the orderly charging method dispatching too many electric vehicles and causing new load peaks, the constraints are constructed as follows: Among them, |K i | represents the total number of electric vehicles with charging demand at the i-th node, θ is a proportion factor, and the formula stipulates that the number of electric vehicles scheduled at the node cannot exceed the prescribed proportion of the total number of electric vehicles at the node, ρ k The dispatch flag is a bool variable indicating whether the kth electric car is dispatched. The details are as follows: If there is a deviation between the ordered charging time and the disordered charging time, it means that the electric vehicle is dispatched. k =1, if there is no time deviation, it means that the electric vehicle is not dispatched, then ρ k =0.

[0088] In a specific implementation, the use of a particle swarm algorithm with a penalty term to solve a constrained scheduling optimization model includes:

[0089] In S4, the particle swarm algorithm specifically includes the following processes:

[0090] S1: First, set the relevant parameters of the algorithm, randomly initialize the position and velocity of each particle in the population, and initialize the individual historical optimum and global historical optimum of the particle;

[0091] S2: Update the position and velocity of each dimension of the particle according to the individual historical optimum and the global historical optimum.

[0092] S3: Calculate the fitness value of each particle with the inequality constraint condition with penalty term as the optimization target. If the fitness value of the particle is better than the individual historical optimal p Besk (t) fitness value, then update the historical optimal p of the next generation individual Besk The position and fitness value of (t+1);

[0093] S4: If the current optimal fitness value of the population is better than the global historical optimal Leader k(t)’s fitness value, then update the next generation global historical optimal Leader k The position and fitness value of (t+1);

[0094] S5: When the number of population evolutions reaches the set upper limit, the algorithm iteration is completed and the current global historical optimal position is output, that is, the orderly charging scheduling optimization plan for electric vehicles with the lowest total charging cost on the optimization node. If the number of population evolutions does not reach the upper limit, it returns to execute S2.

[0095] Furthermore, the charging optimization strategy includes building a charging optimization model based on the battery SoC model, battery parameters and charging operations of the electric vehicle to predict the battery life.

[0096] Furthermore, establishing a load dynamic adjustment model based on time-of-use electricity prices with minimizing the charging cost of electric vehicles and charging optimization strategies as optimization objectives includes establishing a multi-objective solution model with minimizing the charging cost of electric vehicles and minimizing battery life loss as optimization objectives.

[0097] In a specific implementation, the multi-objective solution model established by minimizing the charging cost of the electric vehicle and minimizing the battery life loss as the optimization objectives includes:

[0098] (1) Determine the optimization objectives: Minimize charging costs to minimize the electricity costs at charging stations or at home; minimize battery life loss. The battery's usage cycle, depth of charge (DOD), and charging speed (C-rate) will affect the battery's health status and service life.

[0099] (2) Determine the decision variables: Charging time: determines when to charge, taking advantage of the difference in electricity prices during different periods of time; Charging power: controls the power during charging, affecting the charging speed and battery life; Charging frequency: determines when to charge to reduce losses caused by deep discharge.

[0100] (3) Model building: Use objective functions to represent the above two optimization objectives, and use weighted methods or Pareto optimization to form a multi-objective optimization model.

[0101] Objective Function

[0102] Charging cost:

[0103]

[0104] Among them, P electric (t) represents the electricity price at time t, E charge (t) is the amount of electricity charged at time t.

[0105] Battery life loss:

[0106]

[0107] Here, f is a function that calculates the battery's health loss based on the depth of discharge and charge rate.

[0108] Constraints:

[0109] Battery charging capacity limit (maximum charging power).

[0110] Timing constraints for charge and discharge states.

[0111] Power demand limit ensures that the power can meet the vehicle's usage requirements.

[0112] (4) Optimization solution

[0113] The simulated annealing algorithm is used to solve this multi-objective optimization problem. According to the Pareto optimization theory, an equilibrium point is sought to achieve the best compromise between charging cost and battery life loss.

[0114] (5) Model evaluation

[0115] After obtaining the multi-objective optimization results, the charging costs and battery life losses of different schemes are compared to evaluate their efficiency and economy.

[0116] Furthermore, the consideration of the demand response characteristics of electric vehicles includes:

[0117] Based on the environmental data corresponding to the target area in the target time period in the historical data, the user's driving habit data and the electric vehicle operating parameters, a trained electric vehicle operating parameter prediction model is obtained to obtain the operating parameters of the electric vehicle;

[0118] Combined with the output power parameters, torque demand parameters, in-vehicle environment parameters, and power feedback level parameters of the on-board battery, the power consumption parameters of the electric vehicle during operation are determined through a decision tree model;

[0119] By combining operating parameters and power consumption parameters, a random forest model is constructed to accurately evaluate and calculate the demand response of electric vehicles.

[0120] In a specific implementation, a multi-scale control system for electric vehicles based on flexible loads, such as Figure 2 As shown, including:

[0121] Load response model building module: used to build a load response model based on charging habits, charging time periods and charging needs;

[0122] Multi-layer control layer module: used to build a multi-layer control layer and collect the load data of the charging pile, the grid status information and the user charging behavior in real time according to the multi-layer control layer;

[0123] Load dynamic adjustment module: used to combine multiple control layers and load response models to build load dynamic adjustment at different time scales;

[0124] Control module: used to adjust the charging plan in real time according to the market electricity price, charging and discharging strategy and user demand, apply flexible load strategy to the dynamic adjustment of load under different time scales, and reduce the charging load during the time-of-use electricity price period.

[0125] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0126] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-scale control method for electric vehicles based on flexible loads, characterized in that: include: Establish a load response model based on charging habits, charging periods and charging needs; Build a multi-layer control layer and collect the load data of charging piles, grid status information and user charging behavior in real time based on the multi-layer control layer; Combine multiple control layers and load response models to build dynamic load adjustments at different time scales; Adjust the charging plan in real time according to market electricity prices, charging and discharging strategies and user needs, apply flexible load strategies to dynamic load adjustment at different time scales, and reduce the charging load during time-of-use electricity price periods.

2. The multi-scale control method of electric vehicles based on flexible load according to claim 1 is characterized in that: The load response model established according to charging habits, charging period and charging demand includes: Determine the user's charging habits and charging time based on the collected historical charging data; According to the time-of-use electricity price information of the power grid, predict and determine the charging demand of users in each period; According to the user's charging habits, charging period and charging demand, the intention factor of electric vehicle charging is calculated, and the load response model of the electric vehicle is determined.

3. The electric vehicle multi-scale control method based on flexible load according to claim 2 is characterized in that: Determining the user's charging habits based on the collected historical charging data includes: Obtain the user's charging data, calculate the unit daily charging amount based on the charging data, take the monthly span as the primary time interval, and divide the unit daily charging amount into multiple primary time intervals; Calculate the daily average charge in each primary time interval, marking high-charge days and low-charge days; It is determined whether the dates of high charging days and low charging days conform to the preset clustering rules to obtain the user's charging habits.

4. The electric vehicle multi-scale control method based on flexible load according to claim 3 is characterized in that: After determining whether the dates of high charging days and low charging days meet the preset clustering rules, it also includes: If the dates of both high-charging days and low-charging days meet the preset clustering rules, the difference between the first average charging amount of the high-charging day and the second average charging amount of the low-charging day is calculated. If the difference is greater than the preset charging ratio of the daily average charging amount, it will be marked as a new charging habit; Based on the user's charging data, the fluctuation of charging amount is analyzed to determine whether the user's charging habits and payment level have an impact on the charging level, accurately identify new charging habits, and re-determine whether the dates of high-charging days and low-charging days conform to the preset clustering rules to obtain the user's new charging habits.

5. The multi-scale control method of electric vehicles based on flexible load according to claim 1 is characterized in that: The construction of the multi-layer control layer includes: constructing a micro layer, a macro layer and a super macro layer to coordinate and regulate at different time scales. The micro layer optimizes the charging of individual electric vehicles, the macro layer focuses on the overall load management of charging piles, and the super macro layer considers the load balance of the power grid.

6. The electric vehicle multi-scale control method based on flexible load according to claim 1 is characterized in that: The method of adjusting the charging plan in real time according to the market electricity price, charging and discharging strategy and user demand, applying a flexible load strategy to the dynamic adjustment of the load under different time scales, and reducing the charging load during the time period of time-sharing electricity price includes: considering the battery condition of the electric vehicle and constructing a charging optimization strategy for the electric vehicle; considering the overall load condition of the charging piles in the region and using the Monte Carlo method to establish a spatiotemporal distribution model of the overall load condition of the charging piles in the region; considering the demand response characteristics of the electric vehicle and establishing a load dynamic adjustment model based on the time-sharing electricity price with minimizing the charging cost of the electric vehicle and the charging optimization strategy as the optimization goal.

7. The electric vehicle multi-scale control method based on flexible load according to claim 6 is characterized in that: The charging optimization strategy includes building a charging optimization model based on the battery SoC model, battery parameters and charging operation of the electric vehicle to predict the battery life.

8. The electric vehicle multi-scale control method based on flexible load according to claim 7 is characterized in that: The method of establishing a load dynamic adjustment model based on time-of-use electricity prices with minimizing the charging cost of electric vehicles and charging optimization strategies as optimization goals includes establishing a multi-objective solution model with minimizing the charging cost of electric vehicles and minimizing battery life loss as optimization goals.

9. The electric vehicle multi-scale control method based on flexible load according to claim 6 is characterized in that: The demand response characteristics of electric vehicles include: Based on the environmental data corresponding to the target area in the target time period in the historical data, the user's driving habit data and the electric vehicle operating parameters, a trained electric vehicle operating parameter prediction model is obtained to obtain the operating parameters of the electric vehicle; Combined with the output power parameters, torque demand parameters, in-vehicle environment parameters, and power feedback level parameters of the vehicle battery, the power consumption parameters of the electric vehicle during operation are determined; Combined with operating parameters and power consumption parameters, the demand response of electric vehicles can be accurately evaluated and calculated.

10. A multi-scale control system for electric vehicles based on flexible loads, characterized in that: include: Load response model building module: used to build a load response model based on charging habits, charging time periods and charging needs; Multi-layer control layer module: used to build a multi-layer control layer and collect the load data of the charging pile, the grid status information and the user charging behavior in real time according to the multi-layer control layer; Load dynamic adjustment module: used to combine multiple control layers and load response models to build load dynamic adjustment at different time scales; Control module: used to adjust the charging plan in real time according to the market electricity price, charging and discharging strategy and user demand, apply flexible load strategy to the dynamic adjustment of load under different time scales, and reduce the charging load during the time-of-use electricity price period.

Images