Power supply load forecasting method considering new energy vehicles

Abstract

The present invention provides a power supply load prediction method taking into account new energy vehicles. The method includes: obtaining the probability distribution characteristics of the travel behavior parameters of new energy vehicles, and using a Markov chain to construct a road congestion level state transition matrix; wherein the road congestion level state transition matrix is ​​determined based on the delay index corresponding to multiple time periods; clustering the urban road type and outdoor ambient temperature based on the K-means clustering algorithm to obtain clustering results, and determining a unit mileage power consumption model based on the clustering results; determining a travel power consumption model based on the probability distribution characteristics, the road congestion level state transition matrix, the clustering results, and the unit mileage power consumption model; establishing a residential area charging pile model based on the number of new energy vehicles in the residential area, and determining a load prediction model based on the probability distribution characteristics, the travel power consumption model, and the residential area charging pile model. The present invention can accurately calculate the load of new energy vehicles connected to charging piles.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid management, and in particular to a method for predicting power supply load taking into account new energy vehicles. Background Art

[0002] With the depletion of fossil fuels like coal and oil and environmental degradation, new energy vehicles are developing rapidly. Electric vehicles, in particular, are gradually replacing fuel-powered vehicles with their zero emissions, low noise, and low energy consumption, and are gaining widespread adoption worldwide. China has introduced numerous policies to support and promote the rapid development of the electric vehicle industry, leading to an increasing number of private car owners choosing electric vehicles as their means of transportation. As a crucial enabler of electric vehicle use and mobility, electric vehicle charging stations are inextricably linked to the development and promotion of electric vehicles.

[0003] Unlike traditional power loads, electric private cars, as mobile loads, are affected by people's travel patterns and the uncertainty of their choice behaviors. Their charging behavior is highly random and disordered in space and time, making the charging power of electric private car batteries intermittent and uncertain, making it difficult to calculate the load of new energy vehicles connected to charging piles. Summary of the Invention

[0004] The embodiment of the present invention provides a power supply load prediction method taking into account new energy vehicles, so as to solve the problem that the charging power of electric private car batteries is intermittent and uncertain, which makes it difficult to calculate the load of new energy vehicles connected to charging piles.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting power supply load taking into account new energy vehicles, comprising:

[0006] Obtaining probability distribution characteristics of new energy vehicle travel behavior parameters and constructing a road congestion level state transition matrix using a Markov chain; wherein the road congestion level state transition matrix is ​​determined based on delay indices corresponding to multiple time periods;

[0007] Clustering urban road types and outdoor ambient temperatures based on a K-means clustering algorithm to obtain clustering results, and determining a unit mileage power consumption model based on the clustering results;

[0008] Determining a travel power consumption model according to the probability distribution characteristics, the road congestion level state transition matrix, the clustering result, and the unit mileage power consumption model;

[0009] A residential area charging pile model is established according to the number of new energy vehicles in the residential area, and a load forecasting model is determined according to the probability distribution characteristics, the travel power consumption model and the residential area charging pile model.

[0010] In a possible implementation, determining the travel power consumption model according to the probability distribution characteristics, the road congestion level state transition matrix, and the unit mileage power consumption model includes:

[0011] Determine the initial probability of the road congestion level state corresponding to leaving the residential area according to the time probability density function of the first leaving the residential area and the road congestion level state transition matrix ;

[0012] According to the initial probability , determining the road congestion level state probability in each time period within the driving duration using the driving duration probability density function and the road congestion level state transition matrix;

[0013] The travel power consumption model is determined according to the road congestion level state probability in each time period and the unit mileage power consumption model.

[0014] Among them, the probability of road congestion level at the current moment is , discretize the driving time of new energy vehicles into several time periods , then the next period The probability of road congestion level state is:

[0015] .

[0016] In one possible implementation, clustering urban road types and outdoor ambient temperatures is performed based on a K-means clustering algorithm to obtain clustering results, and a unit mileage power consumption model is determined based on the clustering results, including:

[0017] Determine the corresponding basic power consumption per unit mileage based on the urban road types obtained by clustering; determine the temperature energy consumption ratio coefficient based on the outdoor ambient temperatures obtained by clustering;

[0018] A unit mileage power consumption model is determined according to the unit mileage basic power consumption and the temperature energy consumption proportional coefficient.

[0019] In one possible implementation, determining a travel power consumption model according to the probability distribution characteristics, the road congestion level state transition matrix, and the unit mileage power consumption model includes:

[0020] The proportion of road types in each city obtained by clustering , determine the probability of new energy vehicles driving on various types of roads, and calculate the proportion of outdoor ambient temperatures obtained by clustering , determine the distribution probability of outdoor ambient temperature on the day when new energy vehicles travel;

[0021] The travel power consumption model is determined by determining each time period within the travel time according to the probability density function of the time of first leaving the residential area and the probability density function of the travel time, and determining the power consumption within each time period.

[0022] In a possible implementation, the travel power consumption model is:

[0023]

[0024] in, It is the total power consumption of new energy vehicles during driving time; is the duration of each period when the new energy vehicle is traveling at a constant speed; for Driving speed within The power consumption per unit mileage.

[0025] In one possible implementation, a residential area charging pile model is established based on the number of new energy vehicles in the residential area, including:

[0026] Determine the total number of new energy vehicles in residential areas based on parking demand and the penetration rate of new energy vehicles;

[0027] A residential area charging pile model is established based on the ratio of the number of charging piles to new energy vehicles and the total number of new energy vehicles.

[0028] In one possible implementation, the total number of new energy vehicles in a residential area is determined based on parking demand and the penetration rate of new energy vehicles, including:

[0029] Determine parking requirements using the following formula:

[0030]

[0031] in, A specific area in a residential area Inside The total number of new energy vehicles that have parking needs at all times; For the region Estimated parking demand rate within the area; For the region The parking demand change per unit value curve is about time function; For the region usable area; For the region The parking demand rate deviation correction coefficient is related to the economic status, housing distribution, land utilization rate, population size and other characteristics of the corresponding residential area. When the time is 24 hours, , at this time, the number of all new energy vehicles in the residential area can be obtained .

[0032] The total number of new energy vehicles in residential areas is:

[0033]

[0034] Where, is the total number of new energy vehicles; The penetration rate of new energy vehicles.

[0035] The number of charging stations in residential areas is:

[0036]

[0037] Where, is the number of charging piles; It is the ratio of the number of charging piles to new energy vehicles, and its value is related to local policies.

[0038] In one possible implementation, determining a load forecasting model based on the probability distribution characteristics, the travel power consumption model, and the residential area charging pile model includes:

[0039] Determining a target state of charge for the new energy vehicle before the next day's trip based on the travel power consumption model;

[0040] Determining a charging probability model based on the probability density function of the initial state of charge upon arrival at the residential area and the target state of charge;

[0041] Determining a charging duration based on the charging probability model and the residential area charging pile model, and determining a charging cutoff time based on the charging start time probability density function and the charging duration;

[0042] A load prediction model is determined according to the charging start time and the charging end time.

[0043] In one possible implementation, the target state of charge of the new energy vehicle before the next day's trip is:

[0044]

[0045] Where, The state of charge that a new energy vehicle should meet before traveling the next day; It is the benchmark power, generally expressed by the rated capacity of the battery.

[0046] In one possible implementation, determining a charging probability model based on the probability density function of the initial state of charge upon arrival at the residential area and the target state of charge includes:

[0047] use It represents the number of users whose state of charge can meet their travel needs for the next day, and the charging behavior of users is subject to the parameter , Binomial distribution ;

[0048] Based on the binomial distribution, the user's charging selection behavior can be determined by the following two steps: First, set the user's charging probability to a certain value ; The second step is to set the random number for each new energy vehicle Uniform distribution , randomly generated , and with For comparison, when When the user chooses not to charge, When the user chooses to charge.

[0049] For the New energy vehicles, based on their initial state of charge when arriving at residential areas , and the charging time is calculated as:

[0050]

[0051] Where, Charging time for each new energy vehicle; is the rated capacity of the power battery.

[0052] Charging start time based on random sampling and charging time , the charging cut-off time is:

[0053]

[0054] Where, The charging cut-off time for each new energy vehicle.

[0055] The actual daily charging capacity of each new energy vehicle is:

[0056]

[0057] Where, The actual daily charging capacity of a single new energy vehicle; The daily charging capacity required for a single new energy vehicle; Battery charging efficiency for a single vehicle.

[0058] Based on the total number of new energy vehicles As well as the actual daily charging capacity of each new energy vehicle, the cumulative charging load of new energy vehicles in a day can be calculated:

[0059]

[0060] Where, The cumulative charging load of new energy vehicles; For the The actual daily charging capacity of new energy vehicles.

[0061] In one possible implementation, the method further includes: randomly extracting characteristic parameters of the travel behavior parameters that satisfy a certain probability distribution according to the Monte Carlo method, and randomly selecting the node position and voltage phase of the charging pile for each new energy vehicle; and calculating a curve of the load power of the charging pile at each node and each phase of the residential distribution network changing over time.

[0062] In a second aspect, an embodiment of the present invention provides a power supply load forecasting device taking into account new energy private cars, comprising:

[0063] An acquisition module is used to obtain the probability distribution characteristics of the travel behavior parameters of new energy vehicles and construct a road congestion level state transition matrix using a Markov chain; wherein the road congestion level state transition matrix is ​​determined based on the delay index corresponding to multiple time periods;

[0064] A clustering module, configured to cluster urban road types and outdoor ambient temperatures based on a K-means clustering algorithm to obtain clustering results, and to determine a unit mileage power consumption model based on the clustering results;

[0065] a model building module, configured to determine a travel power consumption model based on the probability distribution characteristics, the road congestion level state transition matrix, the clustering results, and the unit mileage power consumption model; and

[0066] A residential area charging pile model is established according to the number of new energy vehicles in the residential area, and a load forecasting model is determined according to the probability distribution characteristics, the travel power consumption model and the residential area charging pile model.

[0067] In a third aspect, an embodiment of the present invention provides a terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0068] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0069] Embodiments of the present invention provide a method for predicting power supply load that takes into account new energy vehicles. The method obtains the probability distribution characteristics of new energy vehicle travel behavior parameters and uses a Markov chain to construct a road congestion level state transition matrix. The road congestion level state transition matrix is ​​determined based on delay indices corresponding to multiple time periods. This construction of the road congestion level state transition matrix takes into account that road congestion during different time periods can cause vehicle speed fluctuations, thereby affecting power consumption. A K-means clustering algorithm is used to cluster urban road types and outdoor ambient temperatures to obtain clustering results. A unit mileage power consumption model is determined based on the clustering results, taking into account the impact of urban road type and outdoor ambient temperature on power consumption. A travel power consumption model is determined based on the probability distribution characteristics, the road congestion level state transition matrix, the clustering results, and the unit mileage power consumption model. A residential charging pile model is established based on the number of new energy vehicles in a residential area, and a load prediction model is determined based on the probability distribution characteristics, the travel power consumption model, and the residential charging pile model. The present invention integrates the road congestion level state transition matrix and the clustering results to determine the load prediction model, improving the accuracy of calculating the daily travel power consumption of new energy vehicles, accurately determining the charging needs of new energy vehicles, and thus accurately calculating the load of new energy vehicles connected to charging piles. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0071] Figure 1 1 is a flow chart of a method for predicting power supply load taking into account new energy vehicles, provided in one embodiment of the present invention;

[0072] Figure 2a A schematic diagram of a road congestion level state transition provided according to a specific embodiment;

[0073] Figure 2b According to a specific embodiment, Figure 2a Schematic diagram of the corresponding driving speed in each time period;

[0074] Figure 3 is a flow chart of a method for predicting power supply load taking into account new energy vehicles, provided in another embodiment of the present invention;

[0075] Figure 4 is a flow chart of a method for predicting power supply load taking into account new energy vehicles, provided in another embodiment of the present invention;

[0076] Figure 5This is a graph of new energy vehicle charging load prediction results at a node in a residential area distribution network provided according to a specific embodiment.

[0077] Figure 6 This is a diagram of the three-phase total charging load prediction results of each node in the residential area distribution network provided according to a specific embodiment.

[0078] Figure 7 1 is a schematic structural diagram of a method and apparatus for predicting power supply load taking into account new energy vehicles, provided in an embodiment of the present invention;

[0079] Figure 8 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0080] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0081] The new energy vehicles mentioned in this embodiment include hybrid electric vehicles and pure electric vehicles, all of which require charging stations. Existing literature analyzes the charging characteristics of taxis, buses, and private cars. This embodiment primarily focuses on power supply load forecasting for private cars, which are significantly affected by the uncertainty of people's travel patterns and choice behaviors.

[0082] Traditional power supply load forecasting schemes directly use travel survey data to model electric vehicle loads under pre-defined charging times and locations. The derived load demand shows that electric vehicle loads increase the peak-to-valley variation of the power grid. However, because travel survey data is based on traditional vehicles, traditional power supply load forecasting schemes assume fixed charging times and locations, typically charging at home after the last trip. Subsequently, some improved power supply load forecasting schemes have emerged that account for the randomness of charging start times, but still set charging durations to fixed values. In effect, the spatial distribution of electric vehicles is predetermined, and the temporal and spatial distribution of load caused by random movement and temperature effects of electric vehicles is not simulated.

[0083] Furthermore, not only is the charging behavior of electric vehicles affected by the spatial and temporal uncertainties of people's travel patterns and choices, but the voltage phase at the charging station is also uncertain. Specifically, slow-charging stations in residential areas are connected to the distribution network using a single phase. Their location and number vary depending on local policies, making the voltage phase uncertain when connecting electric vehicles to the stations. Consequently, calculating the load on electric vehicles connected to the stations is difficult.

[0084] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0085] Figure 1 Schematic diagram of a flow chart of a method for predicting power supply load of new energy vehicles provided in an embodiment of the present invention. Figure 1 As shown, the following steps are included:

[0086] S101, obtaining probability distribution characteristics of new energy vehicle travel behavior parameters, and constructing a road congestion level state transition matrix using a Markov chain; wherein the road congestion level state transition matrix is ​​determined based on delay indices corresponding to multiple time periods;

[0087] S102, clustering urban road types and outdoor ambient temperatures based on a K-means clustering algorithm to obtain clustering results, and determining a unit mileage power consumption model based on the clustering results;

[0088] S103, determining a travel power consumption model based on the probability distribution characteristics, the road congestion level state transition matrix, the clustering results, and the unit mileage power consumption model;

[0089] S104, establishing a residential area charging pile model according to the number of new energy vehicles in the residential area, and determining a load forecasting model according to the probability distribution characteristics, the travel power consumption model and the residential area charging pile model.

[0090] In an embodiment of the present invention, the probability distribution characteristics of new energy vehicle travel behavior parameters are obtained and a Markov chain is used to construct a road congestion level state transition matrix. The road congestion level state transition matrix is ​​determined based on the delay index corresponding to multiple time periods. This construction of the road congestion level state transition matrix takes into account that road congestion during different time periods can cause vehicle speed fluctuations, thereby affecting power consumption. A K-means clustering algorithm is used to cluster urban road types and outdoor ambient temperatures to obtain clustering results. A unit mileage power consumption model is determined based on the clustering results, taking into account the impact of urban road type and outdoor ambient temperature on power consumption. A travel power consumption model is determined based on the probability distribution characteristics, the road congestion level state transition matrix, the clustering results, and the unit mileage power consumption model. A residential charging pile model is established based on the number of new energy vehicles in a residential area, and a load forecasting model is determined based on the probability distribution characteristics, the travel power consumption model, and the residential charging pile model. The present invention integrates the road congestion level state transition matrix and the clustering results to determine the load forecasting model, improving the accuracy of calculating the daily travel power consumption of new energy vehicles, accurately determining the charging needs of new energy vehicles, and thus accurately calculating the load of new energy vehicles connected to charging piles.

[0091] In a possible implementation, in step S101, the road congestion level state transition matrix is:

[0092]

[0093] in, is the road congestion level state transfer matrix; For the Road congestion level to The transition probability of a road congestion level; The road congestion levels are divided according to the congestion delay index, which is as follows: smooth, basically smooth, slightly congested, moderately congested, and severely congested; is the probability of road congestion level transition The corresponding moment.

[0094] In a specific implementation, the changes in the congestion delay index within 24 hours are as follows:

[0095]

[0096] The driving speeds for different road grades and congestion levels are shown in the following table:

[0097]

[0098] like Figure 2a and 2b It is a schematic diagram of the state transition of road congestion levels and the corresponding driving speeds in each time period provided according to a specific embodiment.

[0099] In one possible implementation, in step S101, the travel behavior parameters of the new energy vehicle include a probability density function of the charging start time, a probability density function of the initial state of charge upon arrival at the residential area, a probability density function of the time of first leaving the residential area, and a probability density function of the driving time.

[0100] In one possible implementation, the probability density function of the charging start time is:

[0101]

[0102] in, is the probability density function of the charging start time; is the mean value of the probability density function of the charging start time; is the variance of the probability density function of the charging start time; The charging start time.

[0103] The probability density function of the initial state of charge upon arrival at a residential area is:

[0104]

[0105] in, is the probability density function of the initial state of charge; is the mean value of the probability density function of the initial state of charge; is the variance of the probability density function of the initial state of charge; is the initial state of charge.

[0106] Probability density function of the time of first leaving the residential area:

[0107]

[0108] in, is the probability density function of the time of first leaving the residential area; is the mean of the probability density function of the time of leaving the residential area for the first time; is the variance of the probability density function of the time of first leaving the residential area; The time when the person first leaves the residential area.

[0109] Driving time probability density function:

[0110]

[0111] Where, is the probability density function of driving time; is the mean of the probability density function of driving time; is the variance of the probability density function of driving time; The driving time.

[0112] In the specific implementation process, based on the above probability density function, for the Electric new energy vehicles, randomly select their charging start time , the initial state of charge when arriving at the residential area , the time of first leaving the residential area and driving time , which are used to calculate relevant parameters such as charging power, charging probability model and power consumption model.

[0113] In a specific embodiment, the values ​​of the parameter variables are as follows:

[0114]

[0115] In one possible implementation, a travel power consumption model is determined based on probability distribution characteristics, a road congestion level state transition matrix, and a unit mileage power consumption model, including:

[0116] Determine the initial probability of the road congestion level state corresponding to leaving the residential area according to the probability density function of the time of first leaving the residential area and the road congestion level state transition matrix ;

[0117] According to the initial probability , the probability density function of driving time and the state transition matrix of road congestion level determine the state probability of road congestion level in each period within the driving time;

[0118] The travel power consumption model is determined based on the road congestion level status probability and the unit mileage power consumption model in each time period.

[0119] Among them, the probability of road congestion level at the current moment is , discretize the driving time of new energy vehicles into several time periods , then the next period The probability of road congestion level state is:

[0120] .

[0121] In the specific implementation process, The time when new energy vehicles will leave residential areas for the first time As the starting time of the trip, determine the road congestion status at the starting time, based on the randomly selected single driving time , based on the above formula, determine the next time period The road congestion level status will be the current time and the next time period By superimposing and repeatedly updating the time, we can obtain the state transition curve of the road congestion level changing with time during the travel period of new energy vehicles.

[0122] Based on the speed ranges corresponding to different congestion levels in the "Urban Road Engineering Design Code," randomly selected speed values ​​were used as the average speed for the corresponding congestion level within that time period, generating speed curves for new energy vehicles at different congestion levels. To improve the accuracy of calculating the power consumption of new energy vehicles, different travel scenarios were clustered, taking into account external factors such as urban road type and weather temperature. A residential travel power consumption model was then established based on user preferences based on various external factors.

[0123] In one possible implementation, urban road types and outdoor ambient temperatures are clustered based on a K-means clustering algorithm to obtain clustering results, and a unit mileage power consumption model is determined based on the clustering results, including:

[0124] Determine the corresponding basic power consumption per unit mileage based on the urban road types obtained by clustering; determine the temperature energy consumption ratio coefficient based on the outdoor ambient temperatures obtained by clustering;

[0125] The power consumption model per unit mileage is determined based on the basic power consumption per unit mileage and the temperature energy consumption proportional coefficient.

[0126] The K-means clustering algorithm was used to cluster the power consumption per mileage on different types of urban roads on a daily basis. This generated a set of different travel scenarios and calculated the power consumption of new energy vehicles per trip under these scenarios. A year's worth of outdoor temperature data for a specific location was collected and clustered to construct typical scenarios for different outdoor temperatures. Different scenarios were associated with varying user willingness to use air conditioning during travel. These scenarios primarily included high summer temperatures and low winter temperatures.

[0127] Alternatively, a K-means clustering algorithm can be used to cluster the unit power consumption and outdoor ambient temperature of similar urban roads on a daily basis to obtain different travel scenario sets. This is mainly due to the fact that the air conditioner is used during part of the daily travel period due to the large temperature fluctuations throughout the day.

[0128] In one possible implementation, the basic power consumption per unit mileage of each urban road type is:

[0129]

[0130] in, For the The basic power consumption per unit mileage of each type of road, measured in Ah; The unit of measurement for the driving speed of new energy vehicles is km / h; , and Respectively The coefficients of different power driving speeds corresponding to different types of roads;

[0131] The relationship between the outdoor ambient temperature and time is:

[0132]

[0133] in, For the Types of outdoor ambient temperature; is the time variable within 24 hours; , , , , and Respectively The coefficients of different power time variables corresponding to different types of outdoor ambient temperatures;

[0134] The temperature energy consumption proportional coefficient is:

[0135]

[0136] in, is the outdoor ambient temperature; is the temperature energy consumption proportional coefficient.

[0137] Based on the user's willingness or need to turn on the air conditioner, the power consumption model per mileage is:

[0138]

[0139] in, It is the power consumption per unit mileage of new energy vehicles, and the unit of measurement is Ah; It is the power consumption per mile when the air conditioner is not turned on, and the unit of measurement is Ah; is the outdoor ambient temperature; The set temperature range corresponding to the air conditioner on state.

[0140] In one possible implementation, a travel power consumption model is determined based on probability distribution characteristics, a road congestion level state transition matrix, and a unit mileage power consumption model, including:

[0141] The proportion of road types in each city obtained by clustering , determine the probability of new energy vehicles driving on various types of roads, and calculate the proportion of outdoor ambient temperatures obtained by clustering , determine the distribution probability of outdoor ambient temperature on the day when new energy vehicles travel;

[0142] The travel power consumption model is determined by determining each time period within the travel time based on the probability density function of the time of first leaving the residential area and the probability density function of the travel time, and determining the power consumption within each time period.

[0143] In one possible implementation, the travel power consumption model is:

[0144]

[0145] in, It is the total power consumption of the new energy vehicle during driving time, and the unit of measurement is Ah; The duration of each period when the new energy vehicle is traveling at a constant speed, the unit of measurement is h; for The driving speed within the range is measured in km / h; It is the power consumption per unit mileage, and the unit of measurement is Ah.

[0146] In one possible implementation, a residential area charging pile model is established based on the number of new energy vehicles in the residential area, including:

[0147] Determine the total number of new energy vehicles in residential areas based on parking demand and the penetration rate of new energy vehicles;

[0148] A residential area charging pile model is established based on the ratio of charging piles to new energy vehicles and the total number of new energy vehicles.

[0149] In one possible implementation, the total number of new energy vehicles in a residential area is determined based on parking demand and the penetration rate of new energy vehicles, including:

[0150] Determine parking requirements using the following formula:

[0151]

[0152] in, A specific area in a residential area Inside The total number of new energy vehicles that have parking needs at any given time, measured in units of vehicles; For the region Estimated parking demand rate within the area; For the region The parking demand change per unit value curve is about time function; For the region usable area; For the region The parking demand rate deviation correction coefficient is related to the economic status, housing distribution, land utilization rate, population size and other characteristics of the corresponding residential area. When the time is 24 hours, , at this time, the number of all new energy vehicles in the residential area can be obtained .

[0153] In one possible implementation, the total number of new energy vehicles in a residential area is:

[0154]

[0155] Where, is the total number of new energy vehicles, measured in units of vehicles; The penetration rate of new energy vehicles.

[0156] In one possible implementation, the number of charging piles in a residential area is:

[0157]

[0158] Where, is the number of charging piles, the unit of measurement is unit; It is the ratio of the number of charging piles to new energy vehicles, and its value is related to local policies.

[0159] In a specific embodiment, the per-unit curve of regional parking demand changing with time is:

[0160] .

[0161] In one possible implementation, a load forecasting model is determined based on probability distribution characteristics, a travel power consumption model, and a residential area charging pile model, including:

[0162] Determine the target state of charge of the new energy vehicle before the next day's trip based on the travel power consumption model;

[0163] Determine a charging probability model based on the probability density function of the initial state of charge and the target state of charge when arriving at the residential area;

[0164] Determine the charging duration based on the charging probability model and the residential area charging pile model, and determine the charging cutoff time based on the charging start time probability density function and the charging duration;

[0165] The load forecasting model is determined based on the charging start time and charging end time.

[0166] In one possible implementation, the target state of charge of the new energy vehicle before the next day's trip is:

[0167]

[0168] Where, The state of charge that a new energy vehicle should meet before traveling the next day; It is the benchmark power, generally expressed by the rated capacity of the battery.

[0169] In the specific implementation process, New energy vehicles, and their initial charge state when arriving at the residential area and the state of charge that should be met before traveling the next day By comparison, the user's selection behavior is as follows: if the initial state of charge is less than the state of charge that should be met before traveling the next day, that is, the initial state of charge is less than the target state of charge, the user chooses to charge the vehicle; if the initial state of charge is greater than the state of charge that should be met before traveling the next day, the user can choose to charge or not.

[0170] In one possible implementation, a charging probability model is determined based on a probability density function of a starting state of charge upon arrival at a residential area and a target state of charge, including:

[0171] use It represents the number of users whose state of charge can meet their travel needs for the next day, and the charging behavior of users is subject to the parameter , Binomial distribution ;

[0172] Based on the binomial distribution, the user's charging selection behavior can be determined by the following two steps: First, set the user's charging probability to a certain value. ; The second step is to set the random number for each new energy vehicle Uniform distribution , randomly generated , and with For comparison, when When the user chooses not to charge, When the user chooses to charge.

[0173] In one possible implementation, based on the judgment of the charging probability of new energy vehicles and the charging pile model, the daily charging capacity required for each new energy vehicle is calculated as:

[0174]

[0175] in, The daily charging capacity required for a single vehicle, measured in kW; It is the charging power of new energy vehicles, measured in kW.

[0176] Specifically, the relationship between the charging power of new energy vehicles and time is:

[0177]

[0178] in, The maximum charging power of new energy vehicles, measured in kW; is the rated capacity of the power battery, measured in kWh; It is the initial charge state of the randomly selected new energy vehicles when they arrive at the residential area.

[0179] Figure 3 This is a flow chart of a method for predicting power supply load of new energy vehicles according to another embodiment of the present invention. Figure 3 As shown, the following steps are included:

[0180] Extract the initial state of charge of the electric private car when it arrives at the residential area ;

[0181] Calculate the target state of charge that an electric private car should meet before traveling the next day ;

[0182] exist ≥ In the case of ; And for each new energy vehicle, let the random number Uniform distribution , randomly generated , and with For comparison, when When the user chooses not to charge, Big continues to judge the next car. When the user chooses to charge;

[0183] During the charging process, based on the judgment of the charging probability of new energy vehicles and the charging pile model, the daily charging capacity required for each new energy vehicle is calculated. , the charging loads of multiple new energy vehicles are accumulated to calculate the load in residential areas.

[0184] In one possible implementation, for New energy vehicles, based on their initial state of charge when arriving at residential areas , and the charging time is calculated as:

[0185]

[0186] Where, The charging time of each new energy vehicle, measured in h; It is the rated capacity of the power battery, measured in kWh.

[0187] Charging start time based on random sampling and charging time , the charging cut-off time is:

[0188]

[0189] Where, The charging cut-off time for each new energy vehicle.

[0190] The actual daily charging capacity of each new energy vehicle is:

[0191]

[0192] Where, The actual daily charging capacity of a single new energy vehicle, measured in kW; The daily charging capacity required for a single new energy vehicle, measured in kW; Battery charging efficiency for a single vehicle.

[0193] Based on the total number of new energy vehicles As well as the actual daily charging capacity of each new energy vehicle, the cumulative charging load of new energy vehicles in a day can be calculated:

[0194]

[0195] Where, is the cumulative charging load of new energy vehicles, measured in kW; For the The actual daily charging capacity of a new energy vehicle is measured in kW.

[0196] In addition, considering that each node is equipped with a single-phase charging station, multiple new energy vehicles can be charged simultaneously. When different residents choose charging stations to charge their new energy vehicles, the node location and voltage phase of the charging station are random. Therefore, it is also important to accurately calculate the new energy vehicle charging load of each node in the residential area distribution network at each time.

[0197] In one possible implementation, the method further includes: randomly extracting characteristic parameters of travel behavior parameters that satisfy a certain probability distribution according to the Monte Carlo method, and randomly selecting the node position and voltage phase of the charging pile for each new energy vehicle; and calculating the curve of the load power of the charging pile at each node and each phase of the residential distribution network over time.

[0198] Figure 4 This is a flow chart of a method for predicting power supply load of new energy vehicles according to another embodiment of the present invention. Figure 4 As shown, the following steps are included:

[0199] Randomly select the node location and voltage phase of the connected charging pile;

[0200] Times of Day , ;in, ,by Divide time periods;

[0201] Establish a parking demand model to find the total number of new energy vehicles ;

[0202] Extract charging start time;

[0203] Calculate the state of charge that should be met before traveling the next day;

[0204] Determine whether the new energy vehicle needs to be charged; if charging is not required, the number of new energy vehicles with parking requirements is increased by 1; if charging is required, the charging duration of a single new energy vehicle is calculated;

[0205] The power demand of multiple new energy vehicles at a certain moment is accumulated and calculated comprehensively, so as to calculate the curve of the load power of the charging piles at each node and phase of the residential distribution network over time.

[0206] Figure 5 This is a graph of new energy vehicle charging load prediction results at a node in a residential area distribution network provided according to a specific embodiment.

[0207] Figure 6 This is a diagram of the three-phase total charging load prediction results of each node in the residential area distribution network provided according to a specific embodiment.

[0208] above Figure 5 and 6 This is an exemplary prediction result diagram, which is intended to illustrate the prediction results that can be achieved by the embodiment of the present invention, and does not limit the solutions in the embodiment of the present invention.

[0209] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0210] The following are device embodiments of the present invention. For details not fully described therein, reference may be made to the corresponding method embodiments described above.

[0211] Figure 7 A schematic diagram of a structure for power supply load prediction taking into account new energy private vehicles provided by an embodiment of the present invention is shown. For ease of explanation, only the portion related to the embodiment of the present invention is shown, which is described in detail as follows:

[0212] like Figure 7 As shown, a power supply load prediction device taking into account new energy private cars includes: an acquisition module 701, a clustering module 702 and a model building module 703.

[0213] The acquisition module 701 is used to obtain the probability distribution characteristics of the travel behavior parameters of new energy vehicles and use the Markov chain to construct a road congestion level state transition matrix; wherein the road congestion level state transition matrix is ​​determined based on the delay index corresponding to multiple time periods.

[0214] The clustering module 702 is configured to cluster urban road types and outdoor ambient temperatures based on a K-means clustering algorithm to obtain clustering results, and determine a unit mileage power consumption model based on the clustering results.

[0215] The model building module 703 is used to determine the travel power consumption model based on the probability distribution characteristics, the road congestion level state transition matrix, the clustering results and the unit mileage power consumption model; and to establish a residential charging pile model based on the number of new energy vehicles in the residential area, and to determine the load forecasting model based on the probability distribution characteristics, the travel power consumption model and the residential charging pile model.

[0216] In an embodiment of the present invention, the probability distribution characteristics of new energy vehicle travel behavior parameters are obtained and a Markov chain is used to construct a road congestion level state transition matrix. The road congestion level state transition matrix is ​​determined based on the delay index corresponding to multiple time periods. This construction of the road congestion level state transition matrix takes into account that road congestion during different time periods can cause vehicle speed fluctuations, thereby affecting power consumption. A K-means clustering algorithm is used to cluster urban road types and outdoor ambient temperatures to obtain clustering results. A unit mileage power consumption model is determined based on the clustering results, taking into account the impact of urban road type and outdoor ambient temperature on power consumption. A travel power consumption model is determined based on the probability distribution characteristics, the road congestion level state transition matrix, the clustering results, and the unit mileage power consumption model. A residential charging pile model is established based on the number of new energy vehicles in a residential area, and a load forecasting model is determined based on the probability distribution characteristics, the travel power consumption model, and the residential charging pile model. The present invention integrates the road congestion level state transition matrix and the clustering results to determine the load forecasting model, improving the accuracy of calculating the daily travel power consumption of new energy vehicles, accurately determining the charging needs of new energy vehicles, and thus accurately calculating the load of new energy vehicles connected to charging piles.

[0217] Figure 8 Schematic diagram of a terminal provided by an embodiment of the present invention. Figure 8 As shown, the terminal 8 of this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80. When the processor 80 executes the computer program 82, the steps in the above-mentioned embodiments of the power supply load prediction method taking into account new energy vehicles are implemented, for example Figure 1 Alternatively, when the processor 80 executes the computer program 82, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 7 Functions of modules 701 to 703 are shown.

[0218] Exemplarily, the computer program 82 may be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 82 in the terminal 8. For example, the computer program 82 may be divided into Figure 7 Modules 701 to 703 are shown.

[0219] The terminal 8 can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 8 can include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that Figure 8 It is only an example of terminal 8 and does not constitute a limitation on terminal 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0220] The processor 80 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0221] The memory 81 can be an internal storage unit of the terminal 8, such as a hard drive or memory of the terminal 8. Alternatively, the memory 81 can be an external storage device of the terminal 8, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 81 can include both an internal storage unit of the terminal 8 and an external storage device. The memory 81 is used to store the computer program and other programs and data required by the terminal. The memory 81 can also be used to temporarily store data that has been output or is about to be output.

[0222] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0223] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0224] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0225] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0226] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0227] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0228] If the integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the processes in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned embodiments of the method for power supply load prediction taking into account new energy vehicles. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0229] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for predicting power supply load taking into account new energy vehicles, characterized in that: include: Obtaining probability distribution characteristics of new energy vehicle travel behavior parameters and constructing a road congestion level state transition matrix using a Markov chain; wherein the road congestion level state transition matrix is ​​determined based on delay indices corresponding to multiple time periods; Clustering urban road types and outdoor ambient temperatures based on a K-means clustering algorithm to obtain clustering results, and determining a unit mileage power consumption model based on the clustering results; Determining a travel power consumption model according to the probability distribution characteristics, the road congestion level state transition matrix, the clustering result, and the unit mileage power consumption model; Establishing a residential area charging pile model based on the number of new energy vehicles in the residential area, and determining a load forecasting model based on the probability distribution characteristics, the travel power consumption model and the residential area charging pile model; Among them, the travel behavior parameters of new energy vehicles include the probability density function of charging start time, the probability density function of the initial state of charge when arriving at the residential area, the probability density function of the time of first leaving the residential area, and the probability density function of the driving time.

2. The power supply load prediction method according to claim 1, characterized in that: The road congestion level state transfer matrix is: in, is the road congestion level state transfer matrix; For the Road congestion level to The transition probability of the road congestion level; The road congestion levels are divided according to the congestion delay index, which is as follows: smooth, basically smooth, slightly congested, moderately congested, and severely congested; is the probability of road congestion level transition The corresponding moment.

3. The power supply load prediction method according to claim 1, characterized in that: The determining of the travel power consumption model according to the probability distribution characteristics, the road congestion level state transition matrix, and the unit mileage power consumption model includes: Determine the initial probability of the road congestion level state corresponding to leaving the residential area according to the time probability density function of the first leaving the residential area and the road congestion level state transition matrix ; According to the initial probability , determining the road congestion level state probability in each time period within the driving duration using the driving duration probability density function and the road congestion level state transition matrix; The travel power consumption model is determined according to the road congestion level state probability in each time period and the unit mileage power consumption model.

4. The power supply load prediction method according to claim 1, characterized in that: Clustering urban road types and outdoor ambient temperatures based on the K-means clustering algorithm to obtain clustering results, and determining a unit mileage power consumption model based on the clustering results, including: Determine the corresponding basic power consumption per unit mileage based on the urban road types obtained by clustering; determine the temperature energy consumption ratio coefficient based on the outdoor ambient temperatures obtained by clustering; A unit mileage power consumption model is determined according to the unit mileage basic power consumption and the temperature energy consumption proportional coefficient.

5. The power supply load prediction method according to claim 4, characterized in that: The basic power consumption per unit mileage of each urban road type is: in, For the Basic electricity consumption per unit mileage of different types of roads; is the driving speed of new energy vehicles; , and Respectively The coefficients of different power driving speeds corresponding to different types of roads; The relationship between the outdoor ambient temperature and time is: in, For the Types of outdoor ambient temperature; is the time variable; , , , , and Respectively The coefficients of different power time variables corresponding to different types of outdoor ambient temperatures; The temperature energy consumption proportional coefficient is: in, is the outdoor ambient temperature; is the temperature energy consumption proportional coefficient; The unit mileage power consumption model is: in, The power consumption per unit mileage of new energy vehicles; It is the power consumption per unit mileage when the air conditioner is not turned on; is the outdoor ambient temperature; The set temperature range corresponding to the air conditioner on state.

6. The power supply load prediction method according to claim 4 or 5, characterized in that: Determining a travel power consumption model according to the probability distribution characteristics, the road congestion level state transition matrix, and the unit mileage power consumption model includes: The proportion of road types in each city obtained by clustering , determine the probability of new energy vehicles driving on various types of roads, and calculate the proportion of outdoor ambient temperatures obtained by clustering , determine the distribution probability of outdoor ambient temperature on the day when new energy vehicles travel; The travel power consumption model is determined by determining each time period within the travel time according to the probability density function of the time of first leaving the residential area and the probability density function of the travel time, and determining the power consumption within each time period.

7. The power supply load prediction method according to claim 6, characterized in that: The travel power consumption model is: in, It is the total power consumption of new energy vehicles during driving time; is the duration of each period when the new energy vehicle is traveling at a constant speed; for Driving speed within The power consumption per unit mileage.

8. The power supply load prediction method according to claim 1, wherein: A residential charging pile model is established based on the number of new energy vehicles in the residential area, including: Determine the total number of new energy vehicles in residential areas based on parking demand and the penetration rate of new energy vehicles; A residential area charging pile model is established based on the ratio of the number of charging piles to new energy vehicles and the total number of new energy vehicles.

9. The power supply load prediction method according to claim 8, wherein: Determining a load forecasting model according to the probability distribution characteristics, the travel power consumption model, and the residential area charging pile model includes: Determining a target state of charge for the new energy vehicle before the next day's trip based on the travel power consumption model; Determining a charging probability model based on the probability density function of the initial state of charge upon arrival at the residential area and the target state of charge; Determining a charging duration based on the charging probability model and the residential area charging pile model, and determining a charging cutoff time based on the charging start time probability density function and the charging duration; A load prediction model is determined according to the charging start time and the charging end time.

Images