A privacy-protected multi-region electric vehicle charging load prediction method and device

Abstract

This invention discloses a privacy-preserving method and apparatus for predicting electric vehicle charging load in multiple regions, belonging to the field of information security technology. The method includes: dividing acquired electric vehicle travel destination data into multiple regions; constructing an electric vehicle travel chain based on the divided regions; constructing a Markov chain of driving states based on the constructed electric vehicle travel chain; constructing a state transition probability matrix based on the constructed Markov chain; adding noise satisfying the differential privacy definition to each probability value in the state transition probability matrix to obtain a noisy state transition probability matrix; and predicting the next destination and charging load of the electric vehicle based on the probability values ​​in the noisy state transition probability matrix. This invention achieves accurate prediction of electric vehicle charging load while protecting residents' travel privacy, thereby optimizing the configuration of charging facilities in different regions and intelligent scheduling of the power distribution network.

Description

Technical Field

[0001] This invention relates to a method and apparatus for predicting electric vehicle charging load in multiple regions while protecting privacy, and belongs to the field of information security technology. Background Technology

[0002] Electric vehicles (EVs), as representatives of clean energy transportation, have received widespread attention in recent years. EV charging load forecasting has become an important issue in research on EV grid connection analysis, distribution network scheduling and control, and orderly residential charging. EV charging load forecasting aims to analyze and model the charging behavior of EV users to predict the grid's charging demand over a certain period. This process needs to consider multiple factors, including residents' travel destinations, charging habits, vehicle battery capacity and remaining charge, the distribution of charging infrastructure, and external environmental variables such as time. Currently, commonly used charging load forecasting methods mainly include traditional time series analysis, machine learning algorithms, and deep learning models.

[0003] The accuracy of charging load forecasting directly impacts the stability and security of the power system, and also affects the charging experience for electric vehicle users. However, charging load forecasting typically requires the collection and analysis of large amounts of personal data, such as users' charging habits, travel patterns, and geographic location information. This data is not only voluminous, geographically dispersed, and highly complex, but also involves user privacy. How to effectively protect user privacy while conducting charging load forecasting has become a pressing challenge. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and device for predicting electric vehicle charging load in multiple regions while protecting privacy. This method and device can accurately predict the charging load of electric vehicles while protecting the privacy of residents' travel, thereby optimizing the configuration of charging facilities in different regions and the intelligent scheduling of the power distribution network.

[0005] To achieve the above objectives, the present invention is implemented using the following technical solution:

[0006] In a first aspect, the present invention provides a privacy-preserving method for predicting the charging load of electric vehicles in multiple regions, comprising:

[0007] Obtain destination data for electric vehicle travel;

[0008] The acquired electric vehicle travel destination data is divided into multiple regions;

[0009] Construct an electric vehicle mobility chain based on the divided regions;

[0010] Based on the constructed electric vehicle travel chain, construct a Markov chain of driving status;

[0011] Based on the constructed Markov chain, construct a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination;

[0012] Add noise that satisfies the differential privacy definition to each probability value in the state transition probability matrix to obtain the noisy state transition probability matrix.

[0013] Based on the probability values ​​in the state transition probability matrix after adding noise, the next destination and charging load of electric vehicle travel can be predicted.

[0014] Furthermore, the acquired electric vehicle travel destination data is divided into multiple regions, including:

[0015] The acquired electric vehicle travel destination data is divided into residential areas (H), work areas (W), commercial areas (P), and other areas (O).

[0016] Furthermore, the construction of the electric vehicle mobility chain based on the divided multiple regions includes:

[0017] Based on residential area H, work area W, commercial area P, and other areas O, construct an electric vehicle mobility chain. …;in, Indicates the current driving location. This indicates the next destination, where a travel chain can have a maximum of four destinations.

[0018] Furthermore, the construction of a Markov chain of driving states based on the constructed electric vehicle travel chain includes:

[0019] Constructing a Markov chain representing the driving state: ,in, This represents the probability of moving from the current destination to the next destination. Let be the state transition probability matrix.

[0020] Furthermore, based on the constructed Markov chain, a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination is constructed, as shown in the following formula:

[0021] ;

[0022] in, This represents the probability that the vehicle will always be traveling within a residential area. This represents the probability of moving from a residential area to a commercial area. This represents the probability of moving from a residential area to a workplace. This represents the probability of moving from one residential area to another. This represents the probability of moving from a commercial area to a residential area. This represents the probability that the vehicle will always be traveling within a commercial area. This represents the probability of moving from the business area to the work area. This represents the probability of relocating from the commercial area to other areas. This represents the probability of moving from the workplace to the residential area. This represents the probability of moving from the work area to the business area. This represents the probability value of always traveling within the working area. This represents the probability of being transferred from one work area to another. This represents the probability of moving from other districts to a residential area. This represents the probability value of transferring from other areas to the work area. This represents the probability of relocating from other districts to the commercial district. This represents the probability that the vehicle will always travel in other zones.

[0023] in, Every element in the array is greater than or equal to 0. The sum of the elements in each row of the array is 1. Each element in the array is no greater than 1.

[0024] Furthermore, adding noise satisfying the differential privacy definition to each probability value in the state transition probability matrix to obtain a noisy state transition probability matrix includes:

[0025] Add noise that satisfies the differential privacy definition to the state transition matrix, with the noise scale being... The calculation formula is as follows:

[0026] ;

[0027] in, Indicates privacy budget, Indicates the relaxation factor;

[0028] State transition matrix with added noise The formula is as follows:

[0029] ;

[0030] in, This represents the probability that the vehicle will always travel within a residential area after noise has been added. This represents the probability of moving from a residential area to a commercial area after adding noise. This represents the probability of moving from a residential area to a work area after adding noise. This represents the probability value of moving from a residential area to another area after adding noise. This represents the probability of moving from a commercial area to a residential area after adding noise. This represents the probability that the vehicle will always travel within the commercial area after noise has been added. This represents the probability value of moving from the business area to the work area after adding noise. This represents the probability of moving from the commercial area to another area after adding noise. This represents the probability of moving from the work area to the residential area after adding noise. This represents the probability of moving from the work area to the business area after adding noise. This represents the probability that the vehicle will always stay within the working area after noise is added. This represents the probability value of moving from the working area to other areas after adding noise. This represents the probability value of the signal shifting from other areas to the residential area after noise is added. This represents the probability value of the noise being transferred from other areas to the working area. This represents the probability value of moving from other areas to the commercial area after adding noise. This represents the probability that the vehicle will always travel in other zones after noise is added.

[0031] Furthermore, the privacy budget The value range is 0.5 + 0.05 * λ, where λ is a natural number from 0 to 90.

[0032] Furthermore, predicting the next destination and charging load for electric vehicle travel based on the probability values ​​in the noise-added state transition probability matrix includes:

[0033] Based on the state transition matrix after adding noise The probability value is used to predict the next destination of the electric vehicle;

[0034] Get the departure time of the electric vehicle T 0 The current remaining battery power of the electric vehicle Value, judgment Is the value less than 30%?

[0035] if The formula for determining whether an electric vehicle needs to be charged at its current destination is as follows:

[0036] ,

[0037] in For electric vehicles to reach the current number Remaining battery power at each destination value; For the battery capacity of electric vehicles;

[0038] if It is assumed that the electric vehicle has enough battery power to reach the next destination, and then it begins its journey to the next destination. The time of arrival at the next destination... T 1 T 0 , Travel time;

[0039] calculate T 1 The charging load of an electric vehicle at any given time is given by the following formula:

[0040] ,

[0041] in express T 1 The charging load of electric vehicles at any given time. For charging power, Then it is T 1 The first moment n The charging status of an electric vehicle; when When =1, then the first n An electric vehicle is being charged when When =0, then the first n The car was not being charged.

[0042] Secondly, the present invention provides a privacy-protecting multi-region electric vehicle charging load prediction device, comprising:

[0043] The data acquisition module is used to acquire data on electric vehicle travel destinations;

[0044] The data segmentation module is used to divide the acquired electric vehicle travel destination data into multiple regions;

[0045] The first building module is used to construct electric vehicle mobility chains based on the divided regions;

[0046] The second building module is used to build a Markov chain of driving status based on the built electric vehicle travel chain;

[0047] The third building module is used to construct a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination based on the constructed Markov chain.

[0048] Add a module to add noise that satisfies the differential privacy definition to each probability value in the state transition probability matrix, and obtain the state transition probability matrix after adding noise;

[0049] The prediction module is used to predict the next destination and charging load of electric vehicle trips based on the probability values ​​in the state transition probability matrix after adding noise.

[0050] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0051] Fourthly, the present invention provides a computer device, comprising:

[0052] Memory, used to store computer programs / instructions;

[0053] A processor for executing the computer program / instructions to implement the steps of any of the methods described above.

[0054] Fifthly, the present invention provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of any of the methods described above.

[0055] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0056] This invention provides a privacy-preserving method and apparatus for predicting electric vehicle charging load in multiple regions. It utilizes electric vehicle travel destination data; divides the acquired electric vehicle travel destination data into multiple regions; and constructs an electric vehicle travel chain based on these regions.

[0057] Based on the constructed electric vehicle travel chain, a Markov chain of driving states is constructed. Noise satisfying the differential privacy definition is added to each probability value in the state transition probability matrix to obtain a noisy state transition probability matrix. Based on the probability values ​​in the noisy state transition probability matrix, the next destination and charging load of the electric vehicle travel can be predicted. In this way, the charging load of electric vehicles can be accurately predicted while protecting the privacy of residents' travel, thereby optimizing the configuration of charging facilities in different areas and the intelligent scheduling of the power distribution network. Attached Figure Description

[0058] Figure 1 This is a flowchart of a privacy-preserving multi-region electric vehicle charging load prediction method provided by an embodiment of the present invention. Detailed Implementation

[0059] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0060] Example 1: This example introduces a privacy-preserving method for predicting electric vehicle charging load in multiple regions, including:

[0061] Obtain destination data for electric vehicle travel;

[0062] The acquired electric vehicle travel destination data is divided into multiple regions;

[0063] Construct an electric vehicle mobility chain based on the divided regions;

[0064] Based on the constructed electric vehicle travel chain, construct a Markov chain of driving status;

[0065] Based on the constructed Markov chain, construct a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination;

[0066] Add noise that satisfies the differential privacy definition to each probability value in the state transition probability matrix to obtain the noisy state transition probability matrix.

[0067] Based on the probability values ​​in the state transition probability matrix after adding noise, the next destination and charging load of electric vehicle travel can be predicted.

[0068] like Figure 1 As shown in the figure, the privacy-preserving multi-region electric vehicle charging load prediction method provided in this embodiment involves the following steps in its application process:

[0069] S11. The data preprocessing process includes steps such as data review, cleaning, coding, transformation, handling of missing and outlier values, and using standard software Stata for data statistical analysis, classification and storage of data.

[0070] S12. Conduct statistical analysis on the number of daily trips, recording the first trip time of the electric vehicle, the driving time of the electric vehicle, the parking time of the electric vehicle, and the electric vehicle's... The system records and analyzes characteristic data such as the remaining battery level (the percentage of battery capacity remaining), the initial starting point of the electric vehicle, and the destination of the electric vehicle trip to determine the distribution of different electric vehicle trip data.

[0071] The first trip time of an electric vehicle follows a normal distribution, and its probability density function is:

[0072] ,

[0073] in The expected travel time. This represents the standard deviation of travel time.

[0074] The driving time of an electric vehicle follows a log-normal distribution, and its probability density function is:

[0075] ,

[0076] The expected value varies depending on the driving time of electric vehicles in different regions. and standard deviation They are also different. Electric vehicles come from residential areas. Residential area: From residential area Work area: , From residential area Business District: From residential area Other areas: From the work area Work area: From the work area Business District: From the work area Other areas: From the business district Business District: From the business district Other areas: From other districts Other areas: .

[0077] The parking time of electric vehicles follows a normal distribution, and its probability density function is:

[0078] ,

[0079] The expected value is that the parking time of electric vehicles varies in different areas. and standard deviation They are also different. Specifically, for residential areas: For the work area: For commercial areas: For other districts: .

[0080] The initial charge of the electric vehicle follows a normal distribution, and its probability density function is:

[0081] ,

[0082] in The expected value of the initial charge. The standard deviation of the initial charge level is given. Based on the existing probability density function, a large amount of sample data can be fitted to predict electric vehicle charging based on these characteristic distributions, thereby improving the prediction accuracy.

[0083] S13. Based on the distribution characteristics of travel data, divide the destination areas of residents' electric vehicle travel into four areas: residential area (Home, H), work area (Work, W), commercial area (Public, P), and other area (Other, O). Construct an electric vehicle travel chain, ensuring that the travel chain has a maximum of four destinations, such as: , Vehicles may stop at different destinations, meaning charging may occur in different locations. In claim 1, parking time is estimated as electric vehicle charging time.

[0084] In step S2, a Markov model is used to model the data, and a state transition probability matrix is ​​established based on the statistical results of electric vehicle travel data, including the following process:

[0085] S21. The Markov model is a stochastic process that studies the changes in a sequence of states. If the four destinations of an electric vehicle are each considered as a state, then the journey of the electric vehicle to different destinations can be regarded as a state transition. Therefore, the driving state of the electric vehicle is a Markov transition process.

[0086] S22. Construct a Markov chain for the driving state: ,in, This indicates the current location of the electric vehicle. Indicates the next destination. This represents the probability of moving from the current destination to the next destination;

[0087] S23. Construct a state transition matrix, forming a state transition probability matrix for all possible states of the electric vehicle traveling from its current location to its next destination:

[0088] ;

[0089] Driving state transition probability matrix It has the following characteristics:

[0090] (1) Every element in the array is greater than or equal to 0;

[0091] (2) The sum of the elements in each row is 1;

[0092] (3) Each element in the array is no greater than 1;

[0093] (4) One state transitions to another (e.g.) The probability of ) and the probability of the reverse state transition (e.g.) There is no direct connection.

[0094] In step S3, personalized privacy protection is provided. Users choose from 91 different privacy protection levels, and each user submits a personalized privacy budget. Then, Gaussian noise satisfying the differential privacy definition is added to each probability value of the state transition probability matrix according to the privacy level, including the following process:

[0095] S31. Regarding the constructed state transition matrix ,Give Noise is added to each probability value in the data, where the privacy budget... The value range is {0.5, 0.55, 0.60, 0.65, 0.70, 0.75, ..., 4.95, 5.0}, which is the privacy budget. The value range is 0.5 + 0.05* λ , λ The value is a natural number from 0 to 90, with 91 possible values, each corresponding to a different level of differential privacy protection. When... λ When =0, privacy budget Taking the minimum value of 0.5 provides the strongest privacy protection; when... λ =90, privacy budget The maximum value of 5.0 is selected, resulting in the weakest privacy protection. Users can choose one of these 91 different privacy budgets, meaning they have 91 different privacy protection levels to choose from. After the user selects a privacy budget, Gaussian noise that meets the corresponding privacy protection level is generated and applied to the state transition matrix. Noise is added to each probability value to obtain the perturbed state transition matrix. :

[0096] ;

[0097] S32, - Differential privacy definition: Given a random function It is to satisfy -Differential privacy, yes The set of all possible outputs, and , If and only if for any two adjacent datasets and Then there is

[0098] ,

[0099] in Indicates privacy budget, The smaller the size, the higher the level of privacy protection; The relaxation factor is the smallest parameter that can violate the probability ratio of differential privacy; generally speaking, or smaller, of which n It is the size of the dataset;

[0100] S33, Advanced Combinatorial Theorem: For all , - Differential privacy mechanism in - Satisfies under recombination -Differential privacy, in which ;

[0101] S34. Gaussian Mechanism Definition: Given a sensitive query function... , It is the domain of the dataset. It is the number of records in the dataset. It is the set of real numbers, for the input dataset Gaussian mechanism Defined as:

[0102] ,

[0103] in, It is a query function Sensitivity It is a noise scale. This indicates that the mean is 0 and the variance is . Gaussian distribution (normal distribution); in order for the Gaussian mechanism to satisfy - Differential privacy requires choosing an appropriate noise standard deviation; this can be derived from the probability density function of the Gaussian distribution. ;

[0104] S35. Parallel Combination Theorem: For A random mechanism Acting on disjoint datasets Its privacy budget is Then the combination algorithm satisfy -Differential privacy;

[0105] S36. According to the definition of the Gaussian mechanism, when adding Gaussian noise to the Markov state transition matrix, since the probability value range belongs to... Sensitivity , , . The selection of noise generation algorithms and parameters will be adaptively adjusted based on the user's privacy needs and data distribution to achieve higher data utilization and stricter privacy protection.

[0106] In step S4, the next destination and charging load for residents' electric vehicle travel are predicted based on the perturbation state transition probability matrix values. This process includes the following steps:

[0107] S41, the departure time of the electric vehicle is T 0 According to the perturbed Markov state transition matrix The probability value is used to predict the next destination and current state of the electric vehicle; due to privacy budgets Differences lead to Different values ​​can cause the predicted destination of each car to change, meaning that each car may charge at different times and locations, resulting in changes in the charging load.

[0108] S42, if The electric vehicle is assumed to have enough battery power to reach the next destination. The journey to the next destination begins. The time of arrival at the next destination is... T 1 T 0 , For driving time; updating electric vehicles The status is cleared, and the next stage of the journey begins;

[0109] S43. Determine the current remaining battery power of the electric vehicle. Is the value less than 30%? The system determines that the electric vehicle needs to be charged at its current destination; the formula for calculating charging conditions is as follows:

[0110] ,

[0111] in For electric vehicles to reach the current number Remaining battery power at each destination value; For the battery capacity of electric vehicles;

[0112] S44. Calculate the charging load of this area at the current time. The parking time of electric vehicles is considered as charging time. The formula for calculating the charging load of electric vehicles is as follows:

[0113] ,

[0114] in express T 1 The charging load of electric vehicles at any given time. For charging power, Then it isT 1 The first moment n The charging status of an electric vehicle; when When =1, then the first n An electric vehicle is being charged when When =0, then the first n The car was not charging;

[0115] S45, Update Charging time, update departure time After the stop, the next leg of the journey begins.

[0116] The following description, in conjunction with a preferred embodiment, illustrates the content involved in the above embodiments.

[0117] This embodiment applies the method provided in this experiment, using the real US Household Travel Survey (NHTS) 2022 dataset, which includes all travel information of households and individuals within a single day, with a total sample size of 30,174 records and 85 attributes. This embodiment performs statistical analysis on the residents' electric vehicle travel status in the raw data, using a Markov model based on differential privacy technology to construct a state transition probability matrix, thereby predicting the charging load of electric vehicles in residential areas, workplaces, commercial areas, and other areas. This embodiment sets 91 privacy protection levels in the differential privacy algorithm, with each privacy protection level corresponding to a privacy budget. The values ​​are 0.5, 0.55, 0.60, 0.65, 0.70, 0.75, ..., 4.95, 5.0. That is, the privacy budget. The value range is 0.5 + 0.05* λ , λ The value is a natural number from 0 to 90, with 91 possible values, each corresponding to a different level of differential privacy protection. When... λ When =0, privacy budget Taking the minimum value of 0.5 provides the strongest privacy protection; when... λ =90, privacy budget The maximum value of 5.0 is selected, which provides the weakest privacy protection. Users can choose one of these 91 different privacy budgets based on their specific needs; that is, users have 91 different privacy protection levels to choose from.

[0118] Using the electricity consumption of multiple areas over a 24-hour period as the baseline load, according to the attached... Figure 1 The process predicts the charging load of electric vehicles in multiple regions. The battery capacity of each electric vehicle is... The car charging power is The electricity consumption per kilometer is To measure the effectiveness of data privacy protection, this experiment provides... 0.5 and Simulation results for measuring the accuracy of electric vehicle charging load in residential, work, commercial and other areas under two privacy protection levels are shown in Tables 1 and 2.

[0119] Table 1: Privacy Budget Forecast values ​​of electric vehicle charging load (kW) in different regions within a 24-hour period.

[0120] Time(T) Home(H) Work(W) Public(P) Other(O) T=1 173.18 89.46 36.68 25.2 T=2 174.44 89.88 39.76 26.39 T=3 176.19 89.81 41.02 27.16 T=4 178.57 91.49 45.5 30.1 T=5 185.64 92.54 49.07 35.56 T=6 195.93 95.76 63.7 43.05 T=7 209.44 100.52 79.66 50.19 T=8 231.98 105.98 96.6 60.97 T=9 265.44 117.39 139.72 90.44 T=10 314.16 129.5 178.08 108.01 T=11 381.99 143.99 216.79 128.1 T=12 453.04 159.81 255.5 156.66 T=13 523.81 173.67 259.77 165.69 T=14 574 182.21 248.99 165.06 T=15 602.84 185.5 242.13 156.8 T=16 612.29 191.5 229.32 153.86 T=17 597.09 190.68 200.83 136.99 T=18 581.43 190.68 172.9 122.85 T=19 542.99 185.57 145.53 107.45 T=20 500.99 179.27 126.98 90.58 T=21 453.88 172.48 109.2 73.92 T=22 406.56 165.9 92.12 63.56 T=23 368.06 161.7 79.8 56.42 T=24 333.43 157.71 70.7 50.89

[0121] Table 2: Privacy Budget Forecast values ​​of electric vehicle charging load (kW) in different regions within a 24-hour period.

[0122] Time(T) Home(H) Work(W) Public(P) Other(O) T=1 164.64 87.43 35.35 25.41 T=2 165.76 88.76 38.5 26.32 T=3 168.07 89.25 39.34 26.46 T=4 170.87 91.42 43.82 30.17 T=5 177.73 92.05 49.49 35.63 T=6 185.15 96.18 64.82 42.49 T=7 200.76 98.91 82.6 49.07 T=8 224.28 104.09 96.11 58.59 T=9 255.99 114.17 140.84 85.96 T=10 306.67 128.66 175.56 104.86 T=11 362.88 145.53 217.21 125.51 T=12 433.37 162.12 257.04 151.55 T=13 509.32 176.12 268.52 160.72 T=14 560.91 186.83 257.74 159.88 T=15 596.82 189.98 238.56 155.89 T=16 607.53 194.04 225.05 150.71 T=17 600.04 190.75 193.55 132.51 T=18 580.51 188.58 169.4 123.83 T=19 540.82 187.81 144.06 108.57 T=20 486.22 182.42 121.24 93.1 T=21 448.49 175.28 97.58 77.63 T=22 404.32 167.09 82.11 66.36 T=23 361.69 160.93 73.01 58.38 T=24 324.38 156.17 65.94 50.75

[0123] Tables 1 and 2 show that, under different privacy budgets, the charging load of electric vehicles in different areas within 24 hours can be accurately predicted. The tables also indicate that, under the premise of protecting residents' travel privacy information, the impact of privacy disturbances on the accuracy of electric vehicle charging load prediction is relatively small. Furthermore, the charging load of electric vehicles varies across different areas and time periods throughout the day. The charging load in residential areas is significantly higher than in work areas, commercial areas, and other areas, with high charging loads during the period from 11:00 to 23:00. Peak charging load periods in commercial areas and other areas are concentrated between 9:00 and 18:00 and between 11:00 and 16:00, respectively. The peak charging load period in work areas is between 11:00 and 18:00. Based on the predicted charging load levels for different time periods, the installation of charging facilities and the scheduling of the power distribution network can be optimized.

[0124] Example 2: This example provides a privacy-preserving multi-area electric vehicle charging load prediction device, comprising:

[0125] The data acquisition module is used to acquire data on electric vehicle travel destinations;

[0126] The data segmentation module is used to divide the acquired electric vehicle travel destination data into multiple regions;

[0127] The first building module is used to construct electric vehicle mobility chains based on the divided regions;

[0128] The second building module is used to build a Markov chain of driving status based on the built electric vehicle travel chain;

[0129] The third building module is used to construct a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination based on the constructed Markov chain.

[0130] Add a module to add noise that satisfies the differential privacy definition to each probability value in the state transition probability matrix, and obtain the state transition probability matrix after adding noise;

[0131] The prediction module is used to predict the next destination and charging load of electric vehicle trips based on the probability values ​​in the state transition probability matrix after adding noise.

[0132] The specific functions of each module described above are explained in the relevant content of the method in Embodiment 1, and will not be repeated here.

[0133] Example 3: This example provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described in Example 1.

[0134] Example 4: This example provides a computer device, including:

[0135] Memory, used to store computer programs / instructions;

[0136] A processor for executing the computer program / instructions to implement the steps of any of the methods described in Embodiment 1.

[0137] Example 5: This example provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described in any one of Examples 1.

[0138] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0139] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure and not to limit its protection scope. Although this disclosure has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading this disclosure, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims.

Claims

1. A privacy-preserving method for predicting electric vehicle charging load in multiple regions, characterized in that, include: Obtain destination data for electric vehicle travel; The acquired electric vehicle travel destination data is divided into multiple regions; Construct an electric vehicle mobility chain based on the divided regions; Based on the constructed electric vehicle travel chain, construct a Markov chain of driving status; Based on the constructed Markov chain, construct a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination; Add Gaussian noise to the Markov state transition matrix values ​​to obtain the noisy state transition probability matrix; Noise scale The calculation formula is as follows: ； in, Indicates privacy budget, Indicates the relaxation factor; ; Based on the probability values ​​in the state transition probability matrix after adding noise, the next destination and charging load for electric vehicle trips are predicted; including: Based on the state transition matrix after adding noise The probability value is used to predict the next destination of the electric vehicle; Get the departure time of the electric vehicle T 0 The current remaining battery power of the electric vehicle Value, judgment Is the value less than 30%? if The formula for determining whether an electric vehicle needs to be charged at its current destination is as follows: ， in For electric vehicles to reach the current number Remaining battery power at each destination value; For the battery capacity of electric vehicles; if It is assumed that the electric vehicle has enough battery power to reach the next destination, and then it begins its journey to the next destination. The time of arrival at the next destination... T 1 T 0 , Travel time; calculate T 1 The charging load of an electric vehicle at any given time is given by the following formula: ， in express T 1 The charging load of electric vehicles at any given time. For charging power, Then it is T 1 The first moment n The charging status of an electric vehicle; when When =1, then the first n An electric vehicle is being charged when When =0, then the first n The car was not charging; renew Charging time, update departure time After the stop, the next leg of the journey begins.

2. The privacy-preserving multi-region electric vehicle charging load prediction method according to claim 1, characterized in that, The acquired electric vehicle travel destination data is divided into multiple regions, including: The acquired electric vehicle travel destination data is divided into residential areas (H), work areas (W), commercial areas (P), and other areas (O).

3. The privacy-preserving multi-region electric vehicle charging load prediction method according to claim 2, characterized in that, The construction of an electric vehicle mobility chain based on multiple defined regions includes: Based on residential area H, work area W, commercial area P, and other areas O, construct an electric vehicle mobility chain. …;in, Indicates the current driving location. This indicates the next destination, where a travel chain can have a maximum of four destinations.

4. The privacy-preserving multi-region electric vehicle charging load prediction method according to claim 3, characterized in that, The construction of a Markov chain representing the driving status based on the constructed electric vehicle travel chain includes: Constructing a Markov chain representing the driving state: ,in, This represents the probability of moving from the current destination to the next destination. Let be the state transition probability matrix.

5. The privacy-preserving multi-region electric vehicle charging load prediction method according to claim 4, characterized in that, Based on the constructed Markov chain, a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination is constructed, as shown in the following formula: ； in, This represents the probability that the vehicle will always be traveling within a residential area. This represents the probability of moving from a residential area to a commercial area. This represents the probability of moving from a residential area to a workplace. This represents the probability of moving from one residential area to another. This represents the probability of moving from a commercial area to a residential area. This represents the probability that the vehicle will always be traveling within a commercial area. This represents the probability of moving from the business area to the work area. This represents the probability of relocating from the commercial area to other areas. This represents the probability of moving from the workplace to the residential area. This represents the probability of moving from the work area to the business area. This represents the probability value of always traveling within the working area. This represents the probability of being transferred from one work area to another. This represents the probability of moving from other districts to a residential area. This represents the probability value of transferring from other areas to the work area. This represents the probability of relocating from other districts to the commercial district. This represents the probability that the vehicle will always travel in other zones. in, Every element in the array is greater than or equal to 0. The sum of the elements in each row of the array is 1. Each element in the array is no greater than 1.

6. The privacy-preserving multi-region electric vehicle charging load prediction method according to claim 5, characterized in that, State transition probability matrix with added noise The formula is as follows: ; in, This represents the probability that the vehicle will always travel within a residential area after noise has been added. This represents the probability of moving from a residential area to a commercial area after adding noise. This represents the probability of moving from a residential area to a work area after adding noise. This represents the probability value of moving from a residential area to another area after adding noise. This represents the probability of moving from a commercial area to a residential area after adding noise. This represents the probability that the vehicle will always travel within the commercial area after noise has been added. This represents the probability value of moving from the business area to the work area after adding noise. This represents the probability of moving from the commercial area to another area after adding noise. This represents the probability of moving from the work area to the residential area after adding noise. This represents the probability of moving from the work area to the business area after adding noise. This represents the probability that the vehicle will always stay within the working area after noise is added. This represents the probability value of moving from the working area to other areas after adding noise. This represents the probability value of the signal shifting from other areas to the residential area after noise is added. This represents the probability value of the noise being transferred from other areas to the working area. This represents the probability value of moving from other areas to the commercial area after adding noise. This represents the probability that the vehicle will always travel in other zones after noise is added.

7. The privacy-preserving multi-region electric vehicle charging load prediction method according to claim 6, characterized in that, privacy budget The value range is 0.5 + 0.05 * λ, where λ is a natural number from 0 to 90.

8. A privacy-preserving multi-region electric vehicle charging load prediction device, used to implement the privacy-preserving multi-region electric vehicle charging load prediction method according to any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire data on electric vehicle travel destinations; The data segmentation module is used to divide the acquired electric vehicle travel destination data into multiple regions; The first building module is used to construct electric vehicle mobility chains based on the divided regions; The second building module is used to build a Markov chain of driving status based on the built electric vehicle travel chain; The third building module is used to construct a state transition probability matrix containing the probability values ​​of transitioning from the current destination to the next destination based on the constructed Markov chain. Add a module to add noise that satisfies the differential privacy definition to each probability value in the state transition probability matrix, and obtain the state transition probability matrix after adding noise; The prediction module is used to predict the next destination and charging load of electric vehicle trips based on the probability values ​​in the state transition probability matrix after adding noise.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When executed by a processor, the program implements the steps of the method described in any one of claims 1-7.

Images