A flexible load-based multi-scale regulation method and system for electric vehicles

Abstract

The application discloses a kind of based on flexible load electric vehicle multiscale regulation and control method and system, it is related to electric vehicle charging control technical field, including: according to charging habit, charging time period and charging demand to establish load response model;Multi-layer control layer is constructed, and according to multi-layer control layer real-time acquisition charging pile load data, power grid state information and user charging behavior;Combining multi-layer control layer and load response model constructs load dynamic adjustment under different time scales;According to market electricity price, charge-discharge strategy and user demand real-time adjustment charging plan, exert flexible load strategy to load dynamic adjustment under different time scales, reduce the charging load of time-of-use electricity price time period.The application effectively reduces the impact of electric vehicle charging on power grid, improves the efficiency of electric energy utilization, realizes the intelligentization and flexibility of charging process;Realize all-around, multi-scale optimization to electric vehicle charging process, effectively manage charging load, reduce the pressure on power grid in peak period.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric vehicle charging control, and more particularly to an electric vehicle multi-scale regulation method and system based on flexible load. BACKGROUND

[0002] In recent years, electric vehicles are becoming more and more popular in the modern transportation field due to their green and pollution-free advantages. The global electric vehicle market is growing exponentially, with sales exceeding 100 million units in 2022 and a penetration rate of 14%.

[0003] However, with the rapid growth of the number of electric vehicles, their electricity consumption and load also increase, which has a profound impact on the power generation side. The potential impact of electric vehicle disorderly charging on the power generation side includes increasing the demand for electricity consumption in the whole society and exacerbating the peak-valley difference of the power grid. In terms of electricity consumption, one of the main driving forces for the rapid growth of electricity demand is the increase in the number of electric vehicles. In terms of electricity load, the disorderly charging of electric vehicles also increases the peak load of the entire network and exacerbates the peak-valley difference. Influenced by residential electricity and third industry electricity, the peak-valley difference of the national power grid is expanding. Although the current impact of electric vehicle charging on the power grid is not significant, if electric vehicles are charged disorderly during the peak of electricity consumption in the future, it may further exacerbate the imbalance between power supply and demand. Therefore, it is necessary to regulate the orderly charging of electric vehicles to alleviate the peak-valley difference of the power generation side, 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 hours has become a problem to be solved. The existing technology mainly focuses on single-time-scale regulation, and lacks a comprehensive and multi-scale optimization scheme for the charging process of electric vehicles. Therefore, how to propose an electric vehicle multi-scale regulation method and system based on flexible load, which optimizes the charging process of electric vehicles in a comprehensive and multi-scale manner, effectively manages the charging load, and reduces the pressure on the power grid during peak hours, is a problem that needs to be solved by those skilled in the art. SUMMARY

[0004] Therefore, the present application provides an electric vehicle multi-scale regulation method and system based on flexible load, which optimizes the charging process of electric vehicles in a comprehensive and multi-scale manner, effectively manages the charging load, and aims 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-mentioned purpose, the present application adopts the following technical solutions:

[0006] An electric vehicle multi-scale regulation method based on flexible load, comprising:

[0007] establishing a load response model according to charging habits, charging time periods and charging demands;

[0008] A multi-layer control layer is constructed, and load data of the charging pile, power grid state information and user charging behavior are collected in real time according to the multi-layer control layer;

[0009] The load dynamic adjustment under different time scales is constructed in combination with the multi-layer control layer and the load response model;

[0010] The charging plan is adjusted in real time according to the market electricity price, the charging and discharging strategy and the user demand, the flexible load strategy is applied to the load dynamic adjustment under different time scales, and the charging load in the time-of-use electricity price period is reduced.

[0011] Optionally, the load response model is established according to the charging habit, the charging period and the charging demand, and includes:

[0012] The charging habit and the charging period of the user are determined according to the collected historical charging data;

[0013] The charging demand of the user corresponding to each period is determined by prediction according to the time-of-use electricity price information of the power grid;

[0014] The intention factor of the electric vehicle charging is calculated according to the charging habit, the charging period and the charging demand of the user, and the load response model of the electric vehicle is determined.

[0015] Optionally, the charging habit of the user is determined according to the collected historical charging data, and includes:

[0016] The charging data of the user is obtained, the daily charging amount is calculated according to the charging data, the daily charging amount is divided into a plurality of primary time intervals with a month span as a primary time interval, and the daily charging amount is divided into a plurality of primary time intervals;

[0017] The daily average charging amount in each primary time interval is calculated, and the high charging day and the low charging day are marked;

[0018] Whether the dates of the high charging day and the low charging day conform to the preset clustering rule is judged, and the charging habit of the user is obtained.

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

[0020] If the dates of the high charging day and the low charging day both conform to the preset clustering rule, the difference value between the first average charging amount of the high charging day and the second average charging amount of the low charging day is calculated, and if the difference value is greater than a preset charging proportion of the daily average charging amount, the new charging habit is marked;

[0021] The fluctuation of the charging amount is analyzed based on the charging data of the user, whether the charging habit and the payment level of the user have an influence on the charging level is judged, the new charging habit is accurately identified, and whether the dates of the high charging day and the low charging day conform to the preset clustering rule is re-judged, and the new charging habit of the user is obtained.

[0022] Optionally, the constructing the multi-scale control layer comprises: constructing a micro layer, a macro layer and a super-macro layer, which are coordinated and regulated at different time scales, the micro layer is for charging optimization of individual electric vehicles, the macro layer is for overall load management of charging piles, and the super-macro layer is for load balancing of the power grid.

[0023] Optionally, the real-time adjustment of the charging plan according to the market electricity price, the charging and discharging strategy and the user demand, the dynamic adjustment of the load at different time scales and the flexible load strategy reduce the charging load in the time-of-use electricity price period, which comprises: considering the battery condition of the electric vehicle, constructing a charging optimization strategy of the electric vehicle; considering the overall load condition of the charging piles in the region, using the Monte Carlo method to establish a space-time distribution model of the overall load condition of the charging piles in the region; considering the demand response characteristics of the electric vehicle, establishing a load dynamic adjustment model according to the time-of-use electricity price, with the optimization objective of minimizing the charging cost of the electric vehicle and the charging optimization strategy.

[0024] Optionally, the charging optimization strategy comprises: constructing a charging optimization model according to the battery SoC model, the battery parameters and the charging operation of the electric vehicle, and predicting the battery life.

[0025] Optionally, the load dynamic adjustment model established according to the time-of-use electricity price, with the optimization objective of minimizing the charging cost of the electric vehicle and the charging optimization strategy comprises: a multi-objective solution model with the optimization objective of minimizing the charging cost of the electric vehicle and minimizing the battery life loss.

[0026] Optionally, the consideration of the demand response characteristics of the electric vehicle comprises:

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

[0028] In combination with the output power parameters, the torque demand parameters, the in-vehicle environment parameters and the power feedback level parameters of the vehicle-mounted battery, the power consumption parameter condition of the electric vehicle in the running process is determined;

[0029] In combination with the operating parameters and the power consumption parameters, the demand response of the electric vehicle is accurately evaluated and calculated.

[0030] Optionally, a multi-scale regulation system for electric vehicles based on flexible load comprises:

[0031] A load response model establishing module is configured to establish a load response model according to charging habits, charging time periods and charging demands;

[0032] Multi-layer control layer module: used for constructing a multi-layer control layer and collecting load data of charging piles, power grid state information and user charging behaviors in real time according to the multi-layer control layer;

[0033] Load dynamic adjustment module: used for constructing load dynamic adjustment under different time scales in combination with the multi-layer control layer and the load response model;

[0034] Regulation and control module: used for adjusting charging plans in real time according to market electricity prices, charging and discharging strategies and user demands, exerting flexible load strategies on load dynamic adjustment under different time scales and reducing charging load in time-of-use electricity price periods.

[0035] According to the technical solution, compared with the prior art, the application provides a multi-scale regulation and control method and system for electric vehicles based on flexible load, which has the following beneficial effects:

[0036] The application provides a multi-scale regulation and control method for electric vehicles based on flexible load, which comprises the following steps: establishing a load response model according to charging habits, charging periods and charging demands; constructing a multi-layer control layer and collecting load data of charging piles, power grid state information and user charging behaviors in real time according to the multi-layer control layer; constructing load dynamic adjustment under different time scales in combination with the multi-layer control layer and the load response model; and adjusting charging plans in real time according to market electricity prices, charging and discharging strategies and user demands, exerting flexible load strategies on load dynamic adjustment under different time scales and reducing charging load in time-of-use electricity price periods. By constructing load dynamic adjustment under different time scales in combination with the multi-layer control layer and the load response model, adjusting charging plans in real time according to market electricity prices, charging and discharging strategies and user demands, exerting flexible load strategies on load dynamic adjustment under different time scales and reducing charging load in time-of-use electricity price periods, the impact of electric vehicle charging on the power grid can be effectively reduced, the utilization efficiency of electric energy can be improved, the intelligentization and flexibility of the charging process can be realized, and an economical and practical charging solution can be provided for users. The application realizes all-round and multi-scale optimization of the charging process of electric vehicles, effectively manages charging load and reduces the pressure on the power grid during peak periods. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are only embodiments of the application, and other accompanying drawings can be obtained by those skilled in the art without any creative effort on the basis of the provided accompanying drawings.

[0038] Figure 1 A multi-scale regulation and control method for electric vehicles based on flexible load provided by the application is shown in the flowchart.

[0039] Figure 2 A flexible load-based multi-scale regulation system structure framework for electric vehicles is provided. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0041] The embodiments of the present application disclose a flexible load-based multi-scale regulation method for electric vehicles, as shown in the figure, comprising: Figure 1

[0042] A load response model is established according to charging habits, charging time periods and charging demands;

[0043] A multi-layer control layer is constructed, and load data of charging piles, power grid state information and user charging behaviors are collected in real time according to the multi-layer control layer;

[0044] Load dynamic adjustment under different time scales is constructed in combination with the multi-layer control layer and the load response model;

[0045] According to market electricity prices, charging and discharging strategies and user demands, the charging plan is adjusted in real time, and flexible load strategies are applied to load dynamic adjustment under different time scales to reduce charging load in time-of-use electricity price periods.

[0046] Further, the load response model is established according to charging habits, charging time periods and charging demands, comprising:

[0047] According to the collected historical charging data, the charging habits and charging time periods of the user are determined;

[0048] According to the time-of-use electricity price information of the power grid, the charging demands of the user corresponding to each time period are predicted and determined;

[0049] According to the charging habits, charging time periods and charging demands of the user, the intention factor of electric vehicle charging is calculated, and the load response model of the electric vehicle is determined.

[0050] Further, the charging habits of the user are determined according to the collected historical charging data, comprising:

[0051] The charging data of the user is obtained, the daily charging amount is calculated according to the charging data, the daily charging amount is divided into a plurality of primary time intervals with month span as the primary time interval, and the daily charging amount is divided into a plurality of primary time intervals.

[0052] ​calculate daily average charging amount in each first time interval, mark high charging days and low charging days;

[0053] determine whether the dates of the high charging days and the low charging days meet preset clustering rules to obtain the charging habit of the user.

[0054] Further, after determining whether the dates of the high charging days and the low charging days meet preset clustering rules, the method further comprises:

[0055] If the dates of the high charging days and the low charging days both meet the preset clustering rules, a difference value between a first average charging amount of the high charging days and a second average charging amount of the low charging days is calculated, and if the difference value is greater than a preset charging proportion of the daily average charging amount, the new charging habit is marked.

[0056] Based on the charging data of the user, the fluctuation of the charging amount is analyzed, it is determined whether the charging habit and the payment level of the user have an influence on the charging level, the new charging habit is accurately identified, and it is determined again whether the dates of the high charging days and the low charging days meet the preset clustering rules to obtain the new charging habit of the user.

[0057] In the specific implementation, if the difference value is greater than the preset charging proportion of the average daily charging amount, the new charging habit is marked, which specifically comprises:

[0058] obtain high charging date intervals of each month, extract overlapping dates in the high charging date intervals of the plurality of months, and obtain a middle time interval from the overlapping dates; obtain charging data and browsing data, the charging data comprising first-level commodity electricity information and charging time, and the browsing data comprising middle-level commodity electricity information and browsing time; identify charging data with charging time in the middle time interval, match the corresponding first-level commodity electricity information with the middle-level commodity electricity information in the browsing data to obtain a plurality of effective browsing times; calculate a time difference average value of each effective browsing time and the charging time; calculate an effective browsing frequency average value corresponding to each charging data; obtain middle-level commodity electricity information in the un-matched browsing data with browsing time less than or equal to the time difference average value from the current time, identify a first browsing frequency of the same type of commodity electricity information, and if the first browsing frequency is greater than the effective browsing frequency average value, obtain an average price of commodity electricity; and if the average price of commodity electricity is greater than a preset charging proportion of the average daily charging amount of the plurality of months, mark a new charging habit.

[0059] Further, the calculation of the daily average charging amount in each first time interval and the marking of the high charging days and the low charging days comprises: calculating the daily average charging amount in each first time interval, marking dates greater than the daily average charging amount as high charging days, and marking dates lower than the daily average charging amount as low charging days.

[0060] Further comprising: fitting a charging curve according to the charging amount of each day in the primary time interval, identifying a secondary time interval with an absolute value of slope on the charging curve exceeding a preset slope, and eliminating the high or low charging day corresponding to the secondary time interval.

[0061] In the specific embodiment, the method further comprises:

[0062] The time-of-use price refers to a price system that performs different electricity price standards for each time period according to the system load level. The time-of-use 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 divided time periods, P t represents the rate standard at time t, with the unit of ￥ / kW·h, P0represents the basic price, and P r,t represents the floating ratio of the relative rate standard to the basic price for each time period. The response of the time-of-use price is embodied by the limitation of load distribution for each time period, and the constraint condition is to meet the limitation of relatively less electricity charges. The daily average electricity charges L for nearly a month are used as the electricity charge amount to determine whether the limitation is met.

[0063] The load distribution process is as follows: (a) solving the standard electricity consumption of the electric vehicle corresponding to each time period according to the charging habit characteristics; (b) solving the total load of each time period; (c) solving the total electricity charges; (d) determining whether the total electricity charges exceed the electricity charge amount L. If it exceeds, the use time of the electric vehicle is moderately shifted to the adjacent low-price time period with a time difference of less than one hour, and the shift length is the time difference. If there is no adjacent low-price time period, the process is ended. After adjusting the running time period of the electric vehicle, steps (b) and (c) are repeated until the total electricity charges are within the electricity charge amount L.

[0064] In the specific embodiment, the method further comprises:

[0065] 1) The charging state of the electric vehicle is often related to the satisfaction of the user, and the satisfaction of the user is affected by the use of the electric vehicle and the charging habit. The electric vehicle intention factor K c is used to represent the influence of the real-time state of the electric vehicle on the charging behavior of the user. The larger the value, the lower the satisfaction of the user. The charging state of the electric vehicle is related to the charging habit of the user. The electric vehicle intention factor K c,iTo characterize the real-time state of the electric vehicle, users can respond to time-of-use electricity prices based on historical charging behavior and achieve intelligent control of electric vehicles based on electric vehicle satisfaction, which is calculated as follows:

[0066]

[0067] In the formula, M n,i,t is the operating electricity cost of the electric vehicle for the t period, M s,i,t is the electricity cost of the electric vehicle corresponding to the lowest electricity price period, E u is the set of electric vehicles.

[0068] 2) Build an operating state model;

[0069]

[0070] In the formula, S u,t is the operating state of the electric vehicle for the t period, 0 indicates a power-off state, and 1 indicates a power-on state, T i,t represents the distance from the t period to the nearest component of the fuzzy power consumption period matrix.

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

[0072] To achieve reasonable control of electric vehicles, the control priority of electric vehicles needs to be determined. The electric vehicle control dynamic priority K is introduced, which can change in real time with the state of the electric vehicle. The greater the K value corresponding to a certain electric vehicle, the more priority control, for the electric vehicle, the greater the electric vehicle satisfaction K c,i , the lower the user satisfaction, and the higher the dynamic control priority. Therefore, the electric vehicle satisfaction index K c,i can be used to represent the electric vehicle dynamic control priority K, and 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] In the formula, N() is the sorting function of x, K app (t) is the sampling value representing K for the t period, and K c (t) is the electric vehicle satisfaction for the t period.

[0078] Further, the construction of the multi-layer control layer includes: constructing micro-layers, macro-layers and super-macro-layers, which are coordinated and regulated at different time scales, the micro-layers are for charging optimization of individual electric vehicles, the macro-layers are for overall load management of charging piles, and the super-macro-layers are for load balancing of power grids.

[0079] Further, the real-time adjustment of the charging plan according to market electricity prices, charging and discharging strategies and user demands, the dynamic adjustment of loads at different time scales and the application of flexible load strategies to reduce charging loads in time-of-use electricity price periods include: considering the battery conditions of electric vehicles, constructing a charging optimization strategy for electric vehicles; considering the overall load conditions of charging piles in the region, using a Monte Carlo method to establish a spatiotemporal distribution model of the overall load conditions of charging piles in the region; considering the demand response characteristics of electric vehicles, establishing a load dynamic adjustment model with the optimization objectives of minimizing the charging cost of electric vehicles and the charging optimization strategy according to the time-of-use electricity price.

[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 region is obtained through statistics. The activities of residents in the same region are periodic, and the period is one day. Therefore, the charging demand in the region is simulated for twenty-four hours in units of one hour, and a spatiotemporal distribution model of the overall load conditions of charging piles in the region is established according to the spatiotemporal distribution of charging demand in the region.

[0081] In a specific embodiment, the real-time adjustment of the charging plan according to market electricity prices, charging and discharging strategies and user demands, the dynamic adjustment of loads at different time scales and the application of flexible load strategies to reduce charging loads in time-of-use electricity price periods further include:

[0082] Considering the properties of the traffic road network, a traffic road network model is established, and the congestion conditions of roads are considered in the traffic road network model. Specifically, a directed traffic road network graph is established based on graph theory; the Dijkstra algorithm based on the greedy and breadth-first search is widely used in shortest path search, and this algorithm is used to plan the travel path of electric vehicles with the shortest travel time, search the path with the minimum weight between all nodes in the road network through the Dijkstra algorithm, and obtain the travel time and distance of the planned path between nodes; 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; a particle swarm algorithm with a penalty term is used to solve the scheduling optimization model with constraints.

[0083] In a specific embodiment, the addition of time constraints and scheduling scale constraints to the established scheduling optimization model includes:

[0084] Assume that the car owner reserves a time period to accept reasonable charging scheduling, and a constraint condition is constructed as follows:

[0085]

[0086] In the formula, x k and t k respectively represent the ordered charging time and the unordered charging time of the kth electric vehicle, and the inequality constraint represents that the charging time of the electric vehicle after scheduling should not be more than the expected time of the car owner.

[0087] In order to avoid that the ordered charging method schedules too many electric vehicles to cause a new load peak, a constraint condition is constructed as follows: Where, |K i | represents the total number of electric vehicles with charging demand at the ith node, θ is a proportion factor, the formula stipulates that the number of scheduled electric vehicles at the node cannot exceed the stipulated proportion of the total number of electric vehicles at the node, and ρ k is a scheduling identifier indicating whether the kth electric vehicle is scheduled, which is a bool type variable, and is specifically as follows: If there is a deviation between the ordered charging time and the unordered charging time, it means that the electric vehicle is scheduled, at this time, ρ k = 1, if there is no deviation, it means that the electric vehicle is not scheduled, at this time, ρ k = 0.

[0088] In the specific embodiment, the solving of the scheduling optimization model with constraints by using the particle swarm algorithm with a penalty term includes:

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

[0090] S1: First, set the related parameters of the algorithm, randomly initialize the position and speed 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 speed of each dimension of the particle with reference to the individual historical optimum and the global historical optimum,

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

[0093] S4: If the current optimal fitness value of the population is better than the global historical optimum Leader kthe global historical optimal Leader of the next generation is updated k the position and fitness value of (t+1)

[0094] S5: When the evolution times of the population reach the set upper limit, the algorithm iteration is completed and the position of the current global historical optimal is output, that is, the ordered charging scheduling optimization scheme of the electric vehicle with the lowest total charging cost on the optimization node, and if the evolution times of the population do not reach the upper limit, return to execute S2.

[0095] Further, the charging optimization strategy comprises: constructing a charging optimization model according to a battery SoC model, battery parameters and charging operations of the electric vehicle, and predicting battery life.

[0096] Further, the load dynamic adjustment model is established according to the time-of-use electricity price, and the optimization objective is to minimize the charging cost of the electric vehicle and the charging optimization strategy, comprising: a multi-objective solving model is established with the optimization objective of minimizing the charging cost of the electric vehicle and minimizing the battery life loss.

[0097] In the specific embodiment, the multi-objective solving model is established with the optimization objective of minimizing the charging cost of the electric vehicle and minimizing the battery life loss, comprising:

[0098] (1) determining the optimization objective: minimizing the charging cost to minimize the electricity fee at the charging station or the home charging; minimizing the battery life loss, the use cycle, the charging depth (DOD), the charging speed (C-rate) and the like of the battery will affect the health state and the service life of the battery.

[0099] (2) determining the decision variable: charging time: deciding when to charge, taking advantage of the time-of-use electricity price difference; charging power: controlling the power during charging, affecting the charging speed and the battery life; charging frequency: deciding when to charge to reduce the loss caused by deep discharge.

[0100] (3) establishing the model: using the objective function to represent the above two optimization objectives, and using the weighting method or the Pareto optimization to form a multi-objective optimization model.

[0101] Objective function

[0102] Charging cost:

[0103]

[0104] wherein, P electric (t) represents the electricity price at time t, E charge (t) represents the electricity quantity charged at time t.

[0105] Battery life loss:

[0106]

[0107] Here, f is a function that can calculate the health loss of the battery according to the depth of discharge and the charging rate.

[0108] Constraints:

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

[0110] Time constraints of charging and discharging state.

[0111] Power demand limit, ensuring that the power can meet the use requirements of the vehicle.

[0112] (4) Optimization solution

[0113] The simulated annealing algorithm is used to solve this multi-objective optimization problem. According to the Pareto optimization theory, a balance 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 result, the charging cost and battery life loss of different schemes are compared, and the efficiency and economy are evaluated.

[0116] Further, the consideration of the demand response characteristics of the electric vehicle includes:

[0117] Based on the environmental data corresponding to the target area in the target time period in the historical data, the driving habit data of the user, and the operating parameters of the electric vehicle, 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 decision tree model determines the power consumption parameter situation of the electric vehicle during operation;

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

[0120] In a specific embodiment, a flexible load-based electric vehicle multi-scale regulation system, as shown in Figure 2 , includes:

[0121] A load response model establishment module is used to establish a load response model according to charging habits, charging time periods, and charging demands;

[0122] A multi-layer control layer module is used to construct a multi-layer control layer and collect load data, power grid state information, and user charging behavior of the charging pile in real time according to the multi-layer control layer;

[0123] Load dynamic adjustment module: used for combining multi-layer control layer and load response model to construct load dynamic adjustment under different time scales;

[0124] Regulation module: used for adjusting charging plan in real time according to market electricity price, charging and discharging strategy and user demand, exerting flexible load strategy on load dynamic adjustment under different time scales, and reducing charging load in time-of-use electricity price period.

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

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

Claims

1. A flexible load-based multi-scale regulation method for electric vehicles, characterized in that, The method comprises the following steps: establishing a load response model according to charging habits, charging time periods and charging demands; the step of establishing a load response model according to charging habits, charging time periods and charging demands comprises: determining charging habits and charging time periods of a user according to historical charging data collected; predicting charging demands of the user in each time period according to time-of-use electricity price information of a power grid; calculating an intention factor of electric vehicle charging and determining a load response model of the electric vehicle according to the charging habits, the charging time periods and the charging demands of the user; Intention factor K for electric vehicles c,i represents the influence of the real-time state of the electric vehicle on the user's charging behavior, and its calculation formula is as follows: ； In the formula, M n,i,t is the running electricity cost value of the electric vehicle for the period t, M s,i,t is the electricity cost value corresponding to the period of the lowest electricity price of the electric vehicle, E u is the set of electric vehicles; the step of determining charging habits of a user according to historical charging data collected comprises: obtaining charging data of the user, calculating daily charging quantity according to the charging data, and dividing the daily charging quantity into a plurality of primary time intervals with a month as a first-level time interval; calculating daily average charging quantity in each primary time interval, and marking high charging days and low charging days; judging whether dates of the high charging days and the low charging days conform to a preset clustering rule to obtain the charging habits of the user; constructing a multi-layer control layer, and collecting load data of charging piles, state information of the power grid and charging behaviors of the user in real time according to the multi-layer control layer; the step of constructing the multi-layer control layer comprises: constructing a micro layer, a macro layer and a super-macro layer, and coordinating and regulating at different time scales, the micro layer is for charging optimization of individual electric vehicles, the macro layer is for overall load management of charging piles, and the super-macro layer is for load balance of the power grid; combining the multi-layer control layer and the load response model to construct load dynamic adjustment at different time scales; adjusting a charging plan in real time according to market electricity prices, charging and discharging strategies and user demands, applying a flexible load strategy to the load dynamic adjustment at different time scales, and reducing charging load in time-of-use electricity price periods; the step of adjusting a charging plan in real time according to market electricity prices, charging and discharging strategies and user demands, applying a flexible load strategy to the load dynamic adjustment at different time scales, and reducing charging load in time-of-use electricity price periods comprises: considering battery conditions of electric vehicles, constructing a charging optimization strategy of the electric vehicles; considering overall load conditions of charging piles in a region, establishing a time-space distribution model of the overall load conditions of the charging piles in the region by using a Monte Carlo method; and considering demand response characteristics of the electric vehicles, establishing a load dynamic adjustment model according to time-of-use electricity prices, with the minimum charging cost of the electric vehicles and the charging optimization strategy as an optimization objective.

2. The method of claim 1, wherein the method is based on a flexible load of the electric vehicle. after judging whether dates of the high charging days and the low charging days conform to a preset clustering rule, the method further comprises: if the dates of the high charging days and the low charging days both conform to the preset clustering rule, calculating a difference value between a first average charging quantity of the high charging days and a second average charging quantity of the low charging days, and if the difference value is greater than a preset charging proportion of the daily average charging quantity, marking as a new charging habit; analyzing fluctuation of charging quantity based on charging data of the user, judging whether the charging habits and payment levels of the user have an influence on charging levels, accurately identifying a new charging habit, and re-judging whether dates of high charging days and low charging days conform to a preset clustering rule to obtain a new charging habit of the user.

3. The method of claim 1, wherein the method is based on a flexible load. The charging optimization strategy comprises: constructing a charging optimization model according to a battery SoC model, battery parameters and charging operation of the electric vehicle, and predicting battery life.

4. The method of claim 3, wherein the method is based on a flexible load. The load dynamic adjustment model is established according to the time-of-use electricity price, and the optimization target is to minimize the charging cost of the electric vehicle and the charging optimization strategy, which comprises: establishing a multi-objective solution model with the optimization target of minimizing the charging cost of the electric vehicle and minimizing the loss of battery life.

5. The method of claim 1, wherein, The demand response characteristics of the electric vehicle are considered, which comprises: Based on the environmental data, user driving habit data and electric vehicle operation parameters of the target region in the target time period in the historical data, a trained electric vehicle operation parameter prediction model is obtained to obtain the operation parameters of the electric vehicle; In combination 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 parameter conditions of the electric vehicle in the running process are determined; In combination with the operation parameters and the power consumption parameters, the demand response of the electric vehicle is accurately evaluated and calculated.

6. A flexible load-based multi-scale regulation system for electric vehicles, characterized in that, Comprise: The load response model establishment module is used to establish a load response model according to the charging habit, charging time period and charging demand; The load response model establishment module is used to establish a load response model according to the charging habit, charging time period and charging demand, which comprises: According to the collected historical charging data, the charging habit and charging time period of the user are determined; According to the time-of-use electricity price information of the power grid, the charging demand of the user in each time period is predicted and determined; According to the charging habit, charging time period and charging demand of the user, the intention factor of the electric vehicle charging is calculated, and the load response model of the electric vehicle is determined; Intention factor K for electric vehicles c,i to represent the influence of the real-time state of the electric vehicle on the user's charging behavior, and its calculation formula is as follows: ； In the formula, M n,i,t is the running electricity cost value of the electric vehicle in the t period, M s,i,t is the electricity cost value corresponding to the electric vehicle in the lowest electricity price period, E u is the electric vehicle set; The charging habit of the user is determined according to the collected historical charging data, which comprises: The charging data of the user is obtained, the daily charging capacity is calculated according to the charging data, the daily charging capacity is divided into a plurality of primary time intervals with month span as the primary time interval; The daily average charging capacity in each primary time interval is calculated, and the high charging day and the low charging day are marked; It is judged whether the dates of the high charging day and the low charging day conform to the preset clustering rule, and the charging habit of the user is obtained; The multi-layer control layer module is used to construct a multi-layer control layer, and real-time acquisition of the load data of the charging pile, the state information of the power grid and the charging behavior of the user is performed according to the multi-layer control layer; The multi-layer control layer comprises: constructing a micro layer, a macro layer and a super macro layer, and coordinating and regulating at different time scales, the micro layer is for charging optimization of individual electric vehicles, the macro layer is for overall load management of the charging pile, and the super macro layer considers load balance of the power grid; The load dynamic adjustment module is used to construct the load dynamic adjustment at different time scales in combination with the multi-layer control layer and the load response model; The control module is used to real-time adjust the charging plan according to the market electricity price, the charging and discharging strategy and the user demand, to exert a flexible load strategy on the load dynamic adjustment at different time scales, and to reduce the charging load in the time-of-use electricity price period. The method comprises the following steps: adjusting the charging plan in real time according to the market electricity price, the charging and discharging strategy and the user demand; dynamically adjusting the load at different time scales and applying the flexible load strategy to reduce the charging load in the time-of-use electricity price period; considering the battery condition of the electric vehicle, constructing the charging optimization strategy of the electric vehicle; considering the overall load condition of the charging pile in the region, adopting the Monte Carlo method to establish the space-time distribution model of the overall load condition of the charging pile in the region; considering the demand response characteristics of the electric vehicle, establishing a load dynamic adjustment model according to the time-of-use electricity price, and taking the minimization of the charging cost and the charging optimization strategy of the electric vehicle as the optimization target.

Images