CN110929950A - Electric vehicle load prediction method and system - Google Patents
Electric vehicle load prediction method and system Download PDFInfo
- Publication number
- CN110929950A CN110929950A CN201911212935.5A CN201911212935A CN110929950A CN 110929950 A CN110929950 A CN 110929950A CN 201911212935 A CN201911212935 A CN 201911212935A CN 110929950 A CN110929950 A CN 110929950A
- Authority
- CN
- China
- Prior art keywords
- individuals
- electric automobile
- state
- chain
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a method and a system for predicting electric vehicle load. The method comprises the following steps: predicting the electric automobile holding quantity of the target area; predicting a random path of the electric vehicle in the target area; predicting the load distribution condition of the electric automobile in one day based on the holding amount and the random path; and optimizing the load distribution condition based on the electric energy interaction relation between the vehicle and the power grid to obtain the optimized load distribution of the electric vehicle. The invention can realize the prediction of the electric automobile load in a certain region.
Description
Technical Field
The invention relates to the field of load prediction, in particular to a method and a system for predicting electric vehicle load.
Background
Under the conditions of global resource shortage and global warming, the development of electric automobiles is promoted to relieve the global resource and climate pressure, so that the electric automobiles are concerned by people. However, with the increase of the holding capacity of the electric automobile, the electric automobile is connected to the power grid in a large scale, and the influence on the power grid is not negligible. The holding capacity of electric vehicles in a region has a large influence on the charging load of electric vehicles in the region, and the influence factor of the annual increase in the holding capacity of electric vehicles also has a large influence factor. The charging load influencing factors on the electric vehicle are mainly in space and time. Under the influence of space factors of electric automobile charging, the driving routes of the electric automobiles are different every day, and randomness is large. Under the condition of not being thorough, the daily load prediction of the electric automobile has great difficulty and great inaccuracy, and the driving route, the weather, the time and the personal intention of the electric automobile have certain influences. The charging time factor of the electric vehicle also has a great influence on the charging load of the electric vehicle. The spatial influence is mostly reflected in the spatial path of the electric vehicle. And the electric automobile is connected to the power grid in a large scale in the same time period, so that the peak value of the power grid is greatly influenced, and the stability of the power grid is influenced to a certain extent. Therefore, load prediction for electric vehicles is a key technical problem at present.
At present, the following two prediction methods are generally used for the load prediction problem of the electric automobile: (1) load prediction is carried out through a neural network by directly using historical data; (2) the data of the daily driving mileage counted abroad is used for prediction. Both the former and the latter prediction methods are too representative to accurately describe the load prediction of an electric vehicle in a certain area, and thus cannot be specifically adjusted based on the influence of the electric vehicle on the power grid.
Disclosure of Invention
The invention aims to provide a method and a system for predicting electric vehicle load, which can realize the prediction of the electric vehicle load in a certain area.
In order to achieve the purpose, the invention provides the following scheme:
an electric vehicle load prediction method comprises the following steps:
predicting the electric automobile holding quantity of the target area;
predicting a random path of the electric vehicle in the target area;
predicting the load distribution condition of the electric automobile in one day based on the holding amount and the random path;
and optimizing the load distribution condition based on the electric energy interaction relation between the vehicle and the power grid to obtain the optimized load distribution of the electric vehicle.
Optionally, the predicting the electric vehicle holding capacity of the target area specifically includes:
establishing a neural network model of the relation between the retention quantity influence factors and the retention quantity;
obtaining the value of each retention quantity influence factor;
and inputting the value of each retention quantity influence factor into the neural network model to obtain the retention quantity of the electric automobile in the target area.
Optionally, the predicting the random path of the electric vehicle in the target area specifically includes:
establishing a main chain by taking the destination as a first factor influencing the random path;
establishing a main chain and an auxiliary chain by taking weather as a second factor influencing a random path;
establishing a secondary auxiliary chain by taking the date as a third factor influencing the random path; the current state of the main chain is influenced by the state of the main chain at the previous moment and the state of the main and auxiliary chains at the previous moment, and the current state of the main and auxiliary chains is influenced by the state of the main and auxiliary chains at the previous moment and the state of the auxiliary chain at the next moment; the current state of the secondary auxiliary chain is influenced by the state of the secondary auxiliary chain at the previous moment;
calculating transition probabilities among states under the influence of the main chain and the auxiliary chain when the main chain and the auxiliary chain are in any state to obtain a first transition probability matrix;
calculating the transition probability between the states of the main chain and the auxiliary chain under the influence of the secondary chain when the secondary chain is in any state to obtain a second transition probability matrix;
and simulating a random path of the electric automobile by using the first transition probability matrix and the second transition probability matrix to obtain the random path of the electric automobile in the target area.
Optionally, the predicting the load distribution of the electric vehicle in one day based on the holding amount and the random path specifically includes:
when the charge state of the electric automobile is lower than a first charge threshold and the destination of the electric automobile is home, determining that the charging mode of the electric automobile is slow charging;
when the charge state of the electric automobile is lower than a first charge threshold value and the destination of the electric automobile is not home, determining that the charging mode of the electric automobile is quick charging;
when the charge state of the electric automobile is higher than the first charge threshold and lower than a second nuclear power threshold, determining that the charging mode of the electric automobile is slow charging;
when the state of charge of the electric vehicle is higher than the second charge threshold, determining that the electric vehicle is not charged;
and determining the charging power of all the electric automobiles in the charging state at any time according to the charging mode of each electric automobile, and obtaining a load curve in one day.
Optionally, the load distribution condition is optimized based on the electric energy interaction relationship between the vehicle and the power grid, so as to obtain optimized load distribution of the electric vehicle, and the method specifically includes:
according to the electric energy interactive relation between the vehicle and the power grid, determining that the maximum profit and the minimum load peak-valley difference are used as objective functions, optimizing the load distribution condition by using the limiting condition of discharge power and the constraint condition that the residual charge of the battery is greater than the minimum residual charge amount, and initializing the optimized solution into population individuals;
initializing iteration times;
solving a target function of each population individual to obtain a fitness value of each solution;
carrying out individual selection according to the fitness value, and carrying out cross and variation on the selected individuals to obtain offspring individuals;
calculating the crowding distances of the offspring individuals and the selected individuals, and carrying out non-inferior layering on each crowding distance to obtain non-inferior individuals;
carrying out pareto sequencing on the non-inferior individuals to obtain sequenced individuals;
dividing the sorted individuals into four parts according to the sequence, and solving the reverse solutions of the individuals of the middle two parts to obtain new individuals of the middle two parts;
calculating the crowding distance of the new individuals of the middle two parts, and carrying out non-inferior layering on the crowding distance of the new individuals of the middle two parts to obtain the non-inferior individuals after secondary layering;
carrying out pareto sequencing on the individuals of the first part and the non-inferior individuals after secondary layering to obtain individuals after secondary sequencing;
screening the first N individuals in the individuals subjected to secondary sorting, and judging whether the current iteration times are larger than or equal to the maximum iteration times to obtain a judgment result;
if the judgment result shows that the solution is not the target function of the population individuals, adding 1 to the iteration times, updating the population individuals to the first N screened individuals, and returning to the step of solving the target function of each population individual to obtain the fitness value of each solution;
and if the judgment result shows that the individual is the best solution, taking the first N screened individuals as the best solutions.
An electric vehicle load prediction system comprising:
the reserve quantity prediction module is used for predicting the reserve quantity of the electric automobile in the target area;
the path prediction module is used for predicting a random path of the electric automobile in the target area;
the load distribution prediction module is used for predicting the load distribution condition of the electric automobile in one day based on the holding amount and the random path;
and the optimization module is used for optimizing the load distribution condition based on the electric energy interaction relation between the vehicle and the power grid to obtain the optimized load distribution of the electric vehicle.
Optionally, the remaining amount prediction module includes:
the neural network model establishing unit is used for establishing a neural network model of the relation between the retention quantity influence factors and the retention quantity;
an input amount acquisition unit for acquiring a value of each of the holding amount influence factors;
and the neural network prediction unit is used for inputting the values of the influence factors of the holding quantity into the neural network model to obtain the holding quantity of the electric automobile in the target area.
Optionally, the path prediction module includes:
a main chain establishing unit for establishing a main chain by using the destination as a first factor influencing the random path;
the main and auxiliary chain establishing unit is used for establishing a main and auxiliary chain by taking weather as a second factor influencing the random path;
a secondary auxiliary chain establishing unit, configured to establish a secondary auxiliary chain using the date as a third factor affecting the random path; the current state of the main chain is influenced by the state of the main chain at the previous moment and the state of the main and auxiliary chains at the previous moment, and the current state of the main and auxiliary chains is influenced by the state of the main and auxiliary chains at the previous moment and the state of the auxiliary chain at the next moment; the current state of the secondary auxiliary chain is influenced by the state of the secondary auxiliary chain at the previous moment;
the first transition probability matrix calculating unit is used for calculating transition probabilities among the states under the influence of the main chain and the auxiliary chain when the main chain and the auxiliary chain are in any state, so as to obtain a first transition probability matrix;
the second transition probability matrix calculating unit is used for calculating the transition probability between the states of the main chain and the auxiliary chain under the influence of the secondary chain when the secondary chain is in any state, so as to obtain a second transition probability matrix;
and the random path simulation unit is used for simulating a random path of the electric automobile by using the first transition probability matrix and the second transition probability matrix to obtain the random path of the electric automobile in the target area.
Optionally, the load distribution predicting module includes:
the first charging mode determining unit is used for determining that the charging mode of the electric automobile is slow charging when the charge state of the electric automobile is lower than a first charge threshold and the destination of the electric automobile is home;
the second charging mode determining unit is used for determining that the charging mode of the electric automobile is quick charging when the charge state of the electric automobile is lower than the first charge threshold and the destination of the electric automobile is not home;
the third charging mode determining unit is used for determining that the charging mode of the electric automobile is slow charging when the charge state of the electric automobile is higher than the first charge threshold and lower than the second nuclear power threshold;
the fourth charging mode determining unit is used for determining that the electric automobile is not charged when the state of charge of the electric automobile is higher than the second charge threshold;
and the load curve construction unit is used for determining the charging power of all the electric automobiles in the charging state at any time according to the charging mode of each electric automobile so as to obtain a load curve in one day.
Optionally, the optimization module includes:
the optimization solution calculation unit is used for determining that the maximum profit and the minimum load peak-valley difference are used as objective functions according to the electric energy interaction relation between the vehicle and the power grid, optimizing the load distribution condition by using the limiting condition of the discharge power and the constraint condition that the residual charge of the battery is greater than the minimum residual charge amount as constraint conditions, and initializing the optimized solution into population individuals;
the iteration initialization unit is used for initializing iteration times;
the fitness value calculation unit is used for solving a target function of each population individual to obtain the fitness value of each solution;
the genetic unit is used for carrying out individual selection according to the fitness value and carrying out cross and variation on the selected individuals to obtain filial generation individuals;
the first non-inferior layering unit is used for calculating the crowding distances of the descendant individuals and the selected individuals, and performing non-inferior layering on each crowding distance to obtain non-inferior individuals;
the first sequencing unit is used for carrying out pareto sequencing on the non-inferior individuals to obtain sequenced individuals;
the reverse solution calculation unit is used for dividing the sorted individuals into four parts according to the sequence, and solving the reverse solutions of the individuals of the middle two parts to obtain new individuals of the middle two parts;
the second non-inferior layering unit is used for calculating the crowding distance of the new individuals of the middle two parts and performing non-inferior layering on the crowding distance of the new individuals of the middle two parts to obtain the non-inferior individuals after secondary layering;
the second sorting unit is used for carrying out pareto sorting on the individuals of the first part and the non-inferior individuals after secondary layering to obtain individuals after secondary sorting;
the screening and judging unit is used for screening the first N individuals in the individuals subjected to secondary sorting, judging whether the current iteration times are larger than or equal to the maximum iteration times or not, and obtaining a judgment result;
an update returning unit, configured to add 1 to the iteration count if the determination result indicates no, update the population individuals to the first N screened individuals, and return the population individuals to the fitness value calculating unit;
and the optimal solution determining unit is used for taking the first N screened individuals as optimal solutions if the judgment result shows that the individuals are positive.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: according to the method and the system for predicting the electric automobile load, the electric automobile holding amount and the electric automobile path in the target area are predicted, so that the electric automobile load in the target area is predicted. Therefore, the present invention can predict the electric vehicle load in a certain area.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a flowchart of a method for predicting a load of an electric vehicle according to embodiment 1 of the present invention;
FIG. 2 is a state transition diagram of a multi-chain Markov model;
fig. 3 is a system configuration diagram of an electric vehicle load prediction system according to embodiment 3 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example 1:
fig. 1 is a flowchart of a method for predicting a load of an electric vehicle according to embodiment 1 of the present invention.
Referring to fig. 1, the method for predicting the load of the electric vehicle includes:
step 101: and predicting the electric vehicle holding quantity of the target area.
The step 101 specifically includes:
establishing a neural network model of the relation between the retention quantity influence factors and the retention quantity;
obtaining the value of each retention quantity influence factor;
and inputting the value of each retention quantity influence factor into the neural network model to obtain the retention quantity of the electric automobile in the target area.
Step 102: and predicting the random path of the electric vehicle in the target area.
The step 102 specifically includes:
establishing a main chain by taking the destination as a first factor influencing the random path;
establishing a main chain and an auxiliary chain by taking weather as a second factor influencing a random path;
establishing a secondary auxiliary chain by taking the date as a third factor influencing the random path; the current state of the main chain is influenced by the state of the main chain at the previous moment and the state of the main and auxiliary chains at the previous moment, and the current state of the main and auxiliary chains is influenced by the state of the main and auxiliary chains at the previous moment and the state of the auxiliary chain at the next moment; the current state of the secondary auxiliary chain is influenced by the state of the secondary auxiliary chain at the previous moment;
calculating transition probabilities among states under the influence of the main chain and the auxiliary chain when the main chain and the auxiliary chain are in any state to obtain a first transition probability matrix;
calculating the transition probability between the states of the main chain and the auxiliary chain under the influence of the secondary chain when the secondary chain is in any state to obtain a second transition probability matrix;
and simulating a random path of the electric automobile by using the first transition probability matrix and the second transition probability matrix to obtain the random path of the electric automobile in the target area.
Step 103: and predicting the load distribution condition of the electric automobile in one day based on the holding amount and the random path.
The step 103 specifically includes:
when the charge state of the electric automobile is lower than a first charge threshold and the destination of the electric automobile is home, determining that the charging mode of the electric automobile is slow charging;
when the charge state of the electric automobile is lower than a first charge threshold value and the destination of the electric automobile is not home, determining that the charging mode of the electric automobile is quick charging;
when the charge state of the electric automobile is higher than the first charge threshold and lower than a second nuclear power threshold, determining that the charging mode of the electric automobile is slow charging;
when the state of charge of the electric vehicle is higher than the second charge threshold, determining that the electric vehicle is not charged;
and determining the charging power of all the electric automobiles in the charging state at any time according to the charging mode of each electric automobile, and obtaining a load curve in one day.
Step 104: and optimizing the load distribution condition based on the electric energy interaction relation between the vehicle and the power grid to obtain the optimized load distribution of the electric vehicle.
The step 104 specifically includes:
according to the electric energy interactive relation between the vehicle and the power grid, determining that the maximum profit and the minimum load peak-valley difference are used as objective functions, optimizing the load distribution condition by using the limiting condition of discharge power and the constraint condition that the residual charge of the battery is greater than the minimum residual charge amount, and initializing the optimized solution into population individuals;
initializing iteration times;
solving a target function of each population individual to obtain a fitness value of each solution;
carrying out individual selection according to the fitness value, and carrying out cross and variation on the selected individuals to obtain offspring individuals;
calculating the crowding distances of the offspring individuals and the selected individuals, and carrying out non-inferior layering on each crowding distance to obtain non-inferior individuals;
carrying out pareto sequencing on the non-inferior individuals to obtain sequenced individuals;
dividing the sorted individuals into four parts according to the sequence, and solving the reverse solutions of the individuals of the middle two parts to obtain new individuals of the middle two parts;
calculating the crowding distance of the new individuals of the middle two parts, and carrying out non-inferior layering on the crowding distance of the new individuals of the middle two parts to obtain the non-inferior individuals after secondary layering;
carrying out pareto sequencing on the individuals of the first part and the non-inferior individuals after secondary layering to obtain individuals after secondary sequencing;
screening the first N individuals in the individuals subjected to secondary sorting, and judging whether the current iteration times are larger than or equal to the maximum iteration times to obtain a judgment result;
if the judgment result shows that the solution is not the target function of the population individuals, adding 1 to the iteration times, updating the population individuals to the first N screened individuals, and returning to the step of solving the target function of each population individual to obtain the fitness value of each solution;
and if the judgment result shows that the individual is the best solution, taking the first N screened individuals as the best solutions.
Example 2:
this embodiment 2 is a more specific embodiment of embodiment 1.
The basic principle of this embodiment 2 is as follows: the method comprises the steps of predicting the holding capacity of the electric automobile based on a BP neural network, establishing a Markov model of a multi-chain electric automobile path, and predicting the distribution of loads in one day by using Monte Carlo. Optimization was performed using V2G (Vehicle-to-grid) at the peak for the predicted load.
The procedure of this example 2 is as follows:
(1) and classifying factors influencing the electric automobile holding capacity, and establishing a BP neural network model to predict the electric automobile holding capacity.
(2) And establishing a random path model of the electric automobile, dividing factors influencing the random path into main factors and secondary factors, and performing simulation modeling by establishing a multi-chain Markov model.
The method is characterized in that a main influence factor of a random path of the electric automobile in a region is weather, a secondary influence factor of the random path is time, a certain mutual influence exists between the main influence factor and the secondary influence factor, and the path of the electric automobile in one day in the region is predicted by establishing a model of the random path.
(3) And predicting the load distribution condition of the electric vehicle in one day by adopting Monte Carlo simulation according to the predicted holding amount of the target area and the simulation result of the random path of the electric vehicle in the target area.
The modeling prediction is realized by calculating the charging power at each moment by judging whether the state of the SOC (state of charge) of the electric automobile needs to be charged or not and selecting a charging mode.
(4) According to the established load distribution condition of the electric automobile in one day, the peak-valley difference of the load distribution of the electric automobile is large, and the peak-valley difference is optimized through V2G, so that the functions of peak clipping and valley filling are realized.
The optimization is carried out by taking the maximum gain obtained by the user and the peak clipping and valley filling as the objective function, so that the stability of the power grid can be improved while the peak clipping and valley filling are realized.
The specific scheme of the step (1) is as follows:
the electric automobile holding capacity has many influencing factors, the most important of which are the population number, the economic level and the government support, and the main influencing factors are closely related to the holding capacity of the electric automobile. Under the influence factors of the reserve capacity of the electric automobile which are comprehensively considered, the population, the distribution of charging piles, the total domestic production value of everyone, the urban financial income and the highway passenger capacity are selected as important influence indexes, and the 5 factors are selected as input indexes of a reserve capacity prediction model of the electric automobile.
The establishment process of the electric automobile inventory prediction model based on the BP neural network comprises the following steps:
sample data of input layer is
X＝(x1,x2,…,xI) (1)
Wherein x1The 1 st relevant influence index representing the electric vehicle holding capacity; x is the number of2A2 nd correlation influence index representing the electric vehicle holding amount; x is the number ofiThe ith relevant influence index represents the electric vehicle holding capacity; x is the number ofIThe I-th correlation influence index represents the electric vehicle holding quantity.
Output layer corresponding to input layer in prediction model
Y＝y (2)
The input of each unit of the hidden layer is
Wherein ω isijExpressed as input layer to implicit layer connection weights, θjThe threshold value is expressed as the unit threshold value of the hidden layer, J is expressed as the number of the hidden layers, and J is the number of each unit of the hidden layer.
The transfer function adopts sigmoid function
The hidden layer unit output is
The input of the output layer unit is
LχIs the input to the output layer unit. χ is the unit of the output layer.
The output of the output layer unit is
Where c is the output of the output layer unit, vjχExpressed as the link weight, γ, of the hidden layer to the output layerχIs the threshold of the output layer unit.
The specific scheme of the step (2) is as follows:
definition 1: the Markov process of the electric vehicle random path means that the state at the time t of the electric vehicle path selection is only determined by the state at the time t-1. This characteristic is called the Markov property of the electric vehicle random path and can be expressed as
Pr{Xt+1＝it+1|X1＝i1,X2＝i2,...,Xt＝it}＝Pr{Xt+1＝it+1|Xt＝it} (8)
In the above formula: prIs a conditional probability, Xt、Xt+1Respectively representing the state variables, i, of the electric vehicle at time t and at time t +1t、it+1Are each Xt、Xt+1The corresponding specific state.
In this embodiment 2, the single-chain markov based on definition 1 is converted into the multi-chain markov to simulate the random path, and a random path model is established, which includes the following steps:
x in Multi-chain Markov as shown in FIG. 21,X2,...XtRepresents the state of the Markov main chain at 1-t, Y1,Y2,...,YtRepresenting the state of the Markov's primary and secondary chains at 1-t, Z1,Z2,...,ZtRepresenting the state of the markov's secondary chain at 1-t. The state of the Markov main chain at the time t is influenced by the state of the main chain at the time t-1 and the state of the main and auxiliary chains at the time t-1. Similarly, when the state of the main chain and the auxiliary chain of the Markov at the time t is influenced by the state of the main chain and the auxiliary chain at the time t-1, the state of the auxiliary chain at the time t-1 is also influenced by the state of the auxiliary chain at the time t-1, and the time t of the auxiliary chain is only influenced by the state of the auxiliary chain at the time t-1. In this embodiment 2, a multi-chain markov model is constructed by using the selection of the electric vehicle path as a main chain, the weather as a main auxiliary chain and the date as a secondary auxiliary chain.
S1-home, company, mall, other };
S2-sunny, cloudy, rainy, snowy, other };
S3tuesday, wednesday, thursday, friday, saturday, sunday };
S1,S2,S3respectively representing N state sets of a Markov main chain, M state sets of a Markov main chain and an auxiliary chain and K state sets of a Markov secondary chain.
Initial state probability matrix pi1,π2,π3Probability matrices each representing 1 as the initial time t of the main chain, the main-auxiliary chain, and the secondary-auxiliary chain。
The set of state transition probability matrices includes a and B. A comprises A1,A2,...AMWaiting M state transition probability matrices, where the element A in AmAnd the transition probability among N states of the Markov main chain is shown when the Markov main chain and auxiliary chain state is m. Set B contains B1,B2,...BKWaiting K state transition probability matrices, where BkAnd the transition probability among M states of the Markov main-auxiliary chain when the Markov secondary-auxiliary chain state is k is shown.
After the selection of the path of the electric automobile (private automobile) in 3 months in Qinhuang island and the collection and processing of the historical data of weather and time, the obtained 3 groups of data divide the selection of the path, the historical data of weather and time into N, M, K respectively, and the selection of the path, the weather and the time sequence are mapped into a state set S1,S2,S3。
In the case of sufficient data, the probability is replaced by a frequency, and the probability P of each state transition is calculated, which can be expressed as:
in the formula AmElement p in (1)dfRepresenting the probability that the selection of a path is transposed from state d to state f, BkElement p in (1)ghRepresenting the probability that the selection of a path is transposed from state g to state h, 0 ≦ pdf≤1，0≤pgh≤1，
Obtaining a multi-chain Markov's backbone X using X, Y, Z as a sequence of path selections, weather, and time, respectivelytAnd main and auxiliary chains YtAnd a secondary auxiliary chain ZtCarrying out data statistics on the state transition matrix A to obtain a state transition matrix Am，BkAnd respectively representing a state transition matrix of m steps of weather on path selection and a state transition matrix of k steps of time on weather.
The calculation process of the total state transition matrix of which the main chain is influenced is as follows:
1. and calculating a state transition matrix of the secondary auxiliary chain, and recording the state transition matrix as a matrix L1.
2. And calculating a state transition matrix of the secondary auxiliary chain on the main auxiliary chain, and recording the state transition matrix as a matrix L2.
3. And calculating a state transition matrix of the main chain and the auxiliary chain, and recording the state transition matrix as a matrix L3.
4. And performing joint operation on L1, L2 and L3 to obtain a main-auxiliary chain overall transfer matrix L4.
5. And calculating a main chain self-transition matrix (recorded as a matrix L5) and a state transition matrix (recorded as a matrix L6) of the main chain and the auxiliary chain influencing the main chain.
6. Multiplication of L4, L5 and L6 yields the total state transition matrix for which the backbone is affected.
The specific scheme of the step (3) is as follows:
the capacity of the initial battery of the electric automobile and the time of travel are randomly extracted, and the route of the electric automobile is simulated.
Selectively charging the electric vehicle by judging the state of the battery capacity:
SOCt＜SOC*30％ (11)
SOC*30％＜SOCt＜SOC*80％ (12)
SOC*80％＜SOCt(13)
SOCtthe state of charge of the electric vehicle at the moment t; the SOC is a state of full charge of the electric vehicle.
When the charge state of the electric vehicle satisfies the formula (11) and the destination of the route is home, selecting the charging mode as slow charging; when the state of charge of the electric vehicle satisfies equation (11) and the end point of the route is not home, the charging mode is selected as fast charging. When the state of charge of the electric vehicle satisfies equation (12), the charging mode is selected to be slow charging. When the state of charge of the electric vehicle satisfies equation (13), the charging mode is selected as no charging.
Finally, the time of charging is calculated, and then the power of charging at the moment t can be calculated, so as to obtain a load curve in one day.
The specific scheme of the step (4) is as follows:
the electric automobile has strong flexibility, can be charged through a power grid, and can also discharge to the power grid in the peak of power utilization, so that ordered charging and discharging of a user are realized, and the effects of peak clipping and valley filling are further realized, and the win-win situation is realized between the user and the power grid. In this embodiment 2, it is assumed that 45% of electric vehicle users enter into an agreement with the power grid to participate in the scheduling of user-side discharging. The participation of the user in the discharging can meet the requirement that the user realizes the maximum benefit and simultaneously enables the peak-valley difference of the load curve of the electric automobile to be minimum, and simultaneously considers the conditions that the discharging power is limited and the residual charge of the battery is not lower than 20 percent.
The objective function and the constraint condition are
In the above formula: pimaxIs the maximum value of daily load; piminIs the minimum value of daily load; pddtThe power of the discharge; pcctPower for charging; pricedtThe electricity price at the moment of discharge; pricectElectricity price at the time of charging, η efficiency of battery charging and discharging, EVlossLoss of batteries of electric vehicles; EV (electric vehicle)socThe remaining capacity of the battery of the electric vehicle; EV (electric vehicle)MAXSOCTotal battery capacity of the electric vehicle; pddtmaxThe maximum discharge power; pddtIs the power of the discharge.
The calculation of equation (14) was optimized using NSGA2 (Non-dominant ordering genetic Algorithm II). The chromosome is coded by adopting a binary system, the power grid is connected with the electric automobile in only two states (charging and discharging), and a line-by-line coding method is adopted in the method. When the gene value is 1, the electric automobile is in a charging state; conversely, when the gene value is 0, it indicates that the electric vehicle is in a discharged state. The length of the chromosome is equivalent to the time length of access to the power grid in one day.
The specific optimization process is as follows:
initializing iteration times;
solving a target function of each population individual to obtain a fitness value of each solution;
carrying out individual selection according to the fitness value, and carrying out cross and variation on the selected individuals to obtain offspring individuals;
calculating the crowding distances of the offspring individuals and the selected individuals, and carrying out non-inferior layering on each crowding distance to obtain non-inferior individuals;
carrying out pareto sequencing on the non-inferior individuals to obtain sequenced individuals;
dividing the sorted individuals into four parts according to the sequence, and solving the reverse solutions of the individuals of the middle two parts to obtain new individuals of the middle two parts;
the calculation formula of the reverse solution is as follows:
wherein Xi,dIs the individual who is to be presented with the inverse solution,
is a reverse solution.
The most ranked optimal individuals, i.e. the individuals with the greatest crowding distance,
the worst individual after the sorting, namely the individual with the minimum crowding distance.
μ∈[0,1]Since the search boundary is dynamically moved, when the reverse solution exceeds the search boundary, let
And rand () is a random value function.
Calculating the crowding distance of the new individuals of the middle two parts, and carrying out non-inferior layering on the crowding distance of the new individuals of the middle two parts to obtain the non-inferior individuals after secondary layering;
carrying out pareto sequencing on the individuals of the first part and the non-inferior individuals after secondary layering to obtain individuals after secondary sequencing;
screening the first N individuals in the individuals subjected to secondary sorting, and judging whether the current iteration times are larger than or equal to the maximum iteration times to obtain a judgment result;
if the judgment result shows that the solution is not the target function of the population individuals, adding 1 to the iteration times, updating the population individuals to the first N screened individuals, and returning to the step of solving the target function of each population individual to obtain the fitness value of each solution;
and if the judgment result shows that the individual is the best solution, taking the first N screened individuals as the best solutions.
Example 3:
fig. 3 is a system configuration diagram of an electric vehicle load prediction system according to embodiment 3 of the present invention.
Referring to fig. 3, the electric vehicle load prediction system includes:
the inventory prediction module 301 is used for predicting the inventory of the electric vehicles in the target area;
a path prediction module 302, configured to predict a random path of the electric vehicle in the target area;
the load distribution prediction module 303 is configured to predict a load distribution condition of the electric vehicle in one day based on the holding amount and the random path;
and the optimization module 304 is configured to optimize the load distribution condition based on an electric energy interaction relationship between the vehicle and the power grid, so as to obtain optimized load distribution of the electric vehicle.
Optionally, the remaining amount predicting module 301 includes:
the neural network model establishing unit is used for establishing a neural network model of the relation between the retention quantity influence factors and the retention quantity;
an input amount acquisition unit for acquiring a value of each of the holding amount influence factors;
and the neural network prediction unit is used for inputting the values of the influence factors of the holding quantity into the neural network model to obtain the holding quantity of the electric automobile in the target area.
Optionally, the path prediction module 302 includes:
a main chain establishing unit for establishing a main chain by using the destination as a first factor influencing the random path;
the main and auxiliary chain establishing unit is used for establishing a main and auxiliary chain by taking weather as a second factor influencing the random path;
a secondary auxiliary chain establishing unit, configured to establish a secondary auxiliary chain using the date as a third factor affecting the random path; the current state of the main chain is influenced by the state of the main chain at the previous moment and the state of the main and auxiliary chains at the previous moment, and the current state of the main and auxiliary chains is influenced by the state of the main and auxiliary chains at the previous moment and the state of the auxiliary chain at the next moment; the current state of the secondary auxiliary chain is influenced by the state of the secondary auxiliary chain at the previous moment;
the first transition probability matrix calculating unit is used for calculating transition probabilities among the states under the influence of the main chain and the auxiliary chain when the main chain and the auxiliary chain are in any state, so as to obtain a first transition probability matrix;
the second transition probability matrix calculating unit is used for calculating the transition probability between the states of the main chain and the auxiliary chain under the influence of the secondary chain when the secondary chain is in any state, so as to obtain a second transition probability matrix;
and the random path simulation unit is used for simulating a random path of the electric automobile by using the first transition probability matrix and the second transition probability matrix to obtain the random path of the electric automobile in the target area.
Optionally, the load distribution predicting module 303 includes:
the first charging mode determining unit is used for determining that the charging mode of the electric automobile is slow charging when the charge state of the electric automobile is lower than a first charge threshold and the destination of the electric automobile is home;
the second charging mode determining unit is used for determining that the charging mode of the electric automobile is quick charging when the charge state of the electric automobile is lower than the first charge threshold and the destination of the electric automobile is not home;
the third charging mode determining unit is used for determining that the charging mode of the electric automobile is slow charging when the charge state of the electric automobile is higher than the first charge threshold and lower than the second nuclear power threshold;
the fourth charging mode determining unit is used for determining that the electric automobile is not charged when the state of charge of the electric automobile is higher than the second charge threshold;
and the load curve construction unit is used for determining the charging power of all the electric automobiles in the charging state at any time according to the charging mode of each electric automobile so as to obtain a load curve in one day.
Optionally, the optimization module 304 includes:
the optimization solution calculation unit is used for determining that the maximum profit and the minimum load peak-valley difference are used as objective functions according to the electric energy interaction relation between the vehicle and the power grid, optimizing the load distribution condition by using the limiting condition of the discharge power and the constraint condition that the residual charge of the battery is greater than the minimum residual charge amount as constraint conditions, and initializing the optimized solution into population individuals;
the iteration initialization unit is used for initializing iteration times;
the fitness value calculation unit is used for solving a target function of each population individual to obtain the fitness value of each solution;
the genetic unit is used for carrying out individual selection according to the fitness value and carrying out cross and variation on the selected individuals to obtain filial generation individuals;
the first non-inferior layering unit is used for calculating the crowding distances of the descendant individuals and the selected individuals, and performing non-inferior layering on each crowding distance to obtain non-inferior individuals;
the first sequencing unit is used for carrying out pareto sequencing on the non-inferior individuals to obtain sequenced individuals;
the reverse solution calculation unit is used for dividing the sorted individuals into four parts according to the sequence, and solving the reverse solutions of the individuals of the middle two parts to obtain new individuals of the middle two parts;
the second non-inferior layering unit is used for calculating the crowding distance of the new individuals of the middle two parts and performing non-inferior layering on the crowding distance of the new individuals of the middle two parts to obtain the non-inferior individuals after secondary layering;
the second sorting unit is used for carrying out pareto sorting on the individuals of the first part and the non-inferior individuals after secondary layering to obtain individuals after secondary sorting;
the screening and judging unit is used for screening the first N individuals in the individuals subjected to secondary sorting, judging whether the current iteration times are larger than or equal to the maximum iteration times or not, and obtaining a judgment result;
an update returning unit, configured to add 1 to the iteration count if the determination result indicates no, update the population individuals to the first N screened individuals, and return the population individuals to the fitness value calculating unit;
and the optimal solution determining unit is used for taking the first N screened individuals as optimal solutions if the judgment result shows that the individuals are positive.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: according to the method and the system for predicting the electric automobile load, the electric automobile holding amount and the electric automobile path in the target area are predicted, so that the electric automobile load in the target area is predicted. Therefore, the present invention can predict the electric vehicle load in a certain area.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. An electric vehicle load prediction method is characterized by comprising the following steps:
predicting the electric automobile holding quantity of the target area;
predicting a random path of the electric vehicle in the target area;
predicting the load distribution condition of the electric automobile in one day based on the holding amount and the random path;
and optimizing the load distribution condition based on the electric energy interaction relation between the vehicle and the power grid to obtain the optimized load distribution of the electric vehicle.
2. The method for predicting the electric vehicle load according to claim 1, wherein the predicting the electric vehicle holding capacity of the target area specifically comprises:
establishing a neural network model of the relation between the retention quantity influence factors and the retention quantity;
obtaining the value of each retention quantity influence factor;
and inputting the value of each retention quantity influence factor into the neural network model to obtain the retention quantity of the electric automobile in the target area.
3. The method for predicting the electric vehicle load according to claim 1, wherein the predicting the random path of the electric vehicle in the target area specifically comprises:
establishing a main chain by taking the destination as a first factor influencing the random path;
establishing a main chain and an auxiliary chain by taking weather as a second factor influencing a random path;
establishing a secondary auxiliary chain by taking the date as a third factor influencing the random path; the current state of the main chain is influenced by the state of the main chain at the previous moment and the state of the main and auxiliary chains at the previous moment, and the current state of the main and auxiliary chains is influenced by the state of the main and auxiliary chains at the previous moment and the state of the auxiliary chain at the next moment; the current state of the secondary auxiliary chain is influenced by the state of the secondary auxiliary chain at the previous moment;
calculating transition probabilities among states under the influence of the main chain and the auxiliary chain when the main chain and the auxiliary chain are in any state to obtain a first transition probability matrix;
calculating the transition probability between the states of the main chain and the auxiliary chain under the influence of the secondary chain when the secondary chain is in any state to obtain a second transition probability matrix;
and simulating a random path of the electric automobile by using the first transition probability matrix and the second transition probability matrix to obtain the random path of the electric automobile in the target area.
4. The method for predicting the load of the electric vehicle according to claim 1, wherein the predicting the load distribution of the electric vehicle in a day based on the holding amount and the random path specifically comprises:
when the charge state of the electric automobile is lower than a first charge threshold and the destination of the electric automobile is home, determining that the charging mode of the electric automobile is slow charging;
when the charge state of the electric automobile is lower than a first charge threshold value and the destination of the electric automobile is not home, determining that the charging mode of the electric automobile is quick charging;
when the charge state of the electric automobile is higher than the first charge threshold and lower than a second nuclear power threshold, determining that the charging mode of the electric automobile is slow charging;
when the state of charge of the electric vehicle is higher than the second charge threshold, determining that the electric vehicle is not charged;
and determining the charging power of all the electric automobiles in the charging state at any time according to the charging mode of each electric automobile, and obtaining a load curve in one day.
5. The method for predicting the load of the electric vehicle according to claim 1, wherein the load distribution is optimized based on an electric energy interaction relationship between a vehicle and a power grid to obtain the optimized load distribution of the electric vehicle, and specifically comprises:
according to the electric energy interactive relation between the vehicle and the power grid, determining that the maximum profit and the minimum load peak-valley difference are used as objective functions, optimizing the load distribution condition by using the limiting condition of discharge power and the constraint condition that the residual charge of the battery is greater than the minimum residual charge amount, and initializing the optimized solution into population individuals;
initializing iteration times;
solving a target function of each population individual to obtain a fitness value of each solution;
carrying out individual selection according to the fitness value, and carrying out cross and variation on the selected individuals to obtain offspring individuals;
calculating the crowding distances of the offspring individuals and the selected individuals, and carrying out non-inferior layering on each crowding distance to obtain non-inferior individuals;
carrying out pareto sequencing on the non-inferior individuals to obtain sequenced individuals;
dividing the sorted individuals into four parts according to the sequence, and solving the reverse solutions of the individuals of the middle two parts to obtain new individuals of the middle two parts;
calculating the crowding distance of the new individuals of the middle two parts, and carrying out non-inferior layering on the crowding distance of the new individuals of the middle two parts to obtain the non-inferior individuals after secondary layering;
carrying out pareto sequencing on the individuals of the first part and the non-inferior individuals after secondary layering to obtain individuals after secondary sequencing;
screening the first N individuals in the individuals subjected to secondary sorting, and judging whether the current iteration times are larger than or equal to the maximum iteration times to obtain a judgment result;
if the judgment result shows that the solution is not the target function of the population individuals, adding 1 to the iteration times, updating the population individuals to the first N screened individuals, and returning to the step of solving the target function of each population individual to obtain the fitness value of each solution;
and if the judgment result shows that the individual is the best solution, taking the first N screened individuals as the best solutions.
6. An electric vehicle load prediction system, comprising:
the reserve quantity prediction module is used for predicting the reserve quantity of the electric automobile in the target area;
the path prediction module is used for predicting a random path of the electric automobile in the target area;
the load distribution prediction module is used for predicting the load distribution condition of the electric automobile in one day based on the holding amount and the random path;
and the optimization module is used for optimizing the load distribution condition based on the electric energy interaction relation between the vehicle and the power grid to obtain the optimized load distribution of the electric vehicle.
7. The electric vehicle load prediction system of claim 6, wherein the hold quantity prediction module comprises:
the neural network model establishing unit is used for establishing a neural network model of the relation between the retention quantity influence factors and the retention quantity;
an input amount acquisition unit for acquiring a value of each of the holding amount influence factors;
and the neural network prediction unit is used for inputting the values of the influence factors of the holding quantity into the neural network model to obtain the holding quantity of the electric automobile in the target area.
8. The electric vehicle load prediction system of claim 6, wherein the path prediction module comprises:
a main chain establishing unit for establishing a main chain by using the destination as a first factor influencing the random path;
the main and auxiliary chain establishing unit is used for establishing a main and auxiliary chain by taking weather as a second factor influencing the random path;
a secondary auxiliary chain establishing unit, configured to establish a secondary auxiliary chain using the date as a third factor affecting the random path; the current state of the main chain is influenced by the state of the main chain at the previous moment and the state of the main and auxiliary chains at the previous moment, and the current state of the main and auxiliary chains is influenced by the state of the main and auxiliary chains at the previous moment and the state of the auxiliary chain at the next moment; the current state of the secondary auxiliary chain is influenced by the state of the secondary auxiliary chain at the previous moment;
the first transition probability matrix calculating unit is used for calculating transition probabilities among the states under the influence of the main chain and the auxiliary chain when the main chain and the auxiliary chain are in any state, so as to obtain a first transition probability matrix;
the second transition probability matrix calculating unit is used for calculating the transition probability between the states of the main chain and the auxiliary chain under the influence of the secondary chain when the secondary chain is in any state, so as to obtain a second transition probability matrix;
and the random path simulation unit is used for simulating a random path of the electric automobile by using the first transition probability matrix and the second transition probability matrix to obtain the random path of the electric automobile in the target area.
9. The electric vehicle load prediction system of claim 6, wherein the load distribution prediction module comprises:
the first charging mode determining unit is used for determining that the charging mode of the electric automobile is slow charging when the charge state of the electric automobile is lower than a first charge threshold and the destination of the electric automobile is home;
the second charging mode determining unit is used for determining that the charging mode of the electric automobile is quick charging when the charge state of the electric automobile is lower than the first charge threshold and the destination of the electric automobile is not home;
the third charging mode determining unit is used for determining that the charging mode of the electric automobile is slow charging when the charge state of the electric automobile is higher than the first charge threshold and lower than the second nuclear power threshold;
the fourth charging mode determining unit is used for determining that the electric automobile is not charged when the state of charge of the electric automobile is higher than the second charge threshold;
and the load curve construction unit is used for determining the charging power of all the electric automobiles in the charging state at any time according to the charging mode of each electric automobile so as to obtain a load curve in one day.
10. The electric vehicle load prediction system of claim 1, wherein the optimization module comprises:
the optimization solution calculation unit is used for determining that the maximum profit and the minimum load peak-valley difference are used as objective functions according to the electric energy interaction relation between the vehicle and the power grid, optimizing the load distribution condition by using the limiting condition of the discharge power and the constraint condition that the residual charge of the battery is greater than the minimum residual charge amount as constraint conditions, and initializing the optimized solution into population individuals;
the iteration initialization unit is used for initializing iteration times;
the fitness value calculation unit is used for solving a target function of each population individual to obtain the fitness value of each solution;
the genetic unit is used for carrying out individual selection according to the fitness value and carrying out cross and variation on the selected individuals to obtain filial generation individuals;
the first non-inferior layering unit is used for calculating the crowding distances of the descendant individuals and the selected individuals, and performing non-inferior layering on each crowding distance to obtain non-inferior individuals;
the first sequencing unit is used for carrying out pareto sequencing on the non-inferior individuals to obtain sequenced individuals;
the reverse solution calculation unit is used for dividing the sorted individuals into four parts according to the sequence, and solving the reverse solutions of the individuals of the middle two parts to obtain new individuals of the middle two parts;
the second non-inferior layering unit is used for calculating the crowding distance of the new individuals of the middle two parts and performing non-inferior layering on the crowding distance of the new individuals of the middle two parts to obtain the non-inferior individuals after secondary layering;
the second sorting unit is used for carrying out pareto sorting on the individuals of the first part and the non-inferior individuals after secondary layering to obtain individuals after secondary sorting;
the screening and judging unit is used for screening the first N individuals in the individuals subjected to secondary sorting, judging whether the current iteration times are larger than or equal to the maximum iteration times or not, and obtaining a judgment result;
an update returning unit, configured to add 1 to the iteration count if the determination result indicates no, update the population individuals to the first N screened individuals, and return the population individuals to the fitness value calculating unit;
and the optimal solution determining unit is used for taking the first N screened individuals as optimal solutions if the judgment result shows that the individuals are positive.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911212935.5A CN110929950B (en) | 2019-12-02 | 2019-12-02 | Electric automobile load prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911212935.5A CN110929950B (en) | 2019-12-02 | 2019-12-02 | Electric automobile load prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110929950A true CN110929950A (en) | 2020-03-27 |
| CN110929950B CN110929950B (en) | 2023-09-26 |
Family
ID=69848136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911212935.5A Active CN110929950B (en) | 2019-12-02 | 2019-12-02 | Electric automobile load prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929950B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111983480A (en) * | 2020-08-19 | 2020-11-24 | 华晟（青岛）智能装备科技有限公司 | AGV electric quantity state prediction method and system based on Mahalanobis process |
| CN114611811A (en) * | 2022-03-21 | 2022-06-10 | 特斯联科技集团有限公司 | Low-carbon park optimal scheduling method and system based on EV load participation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105591433A (en) * | 2016-01-15 | 2016-05-18 | 国家电网公司 | Electric automobile charging load optimization method based on electric automobile charging power dynamic distribution |
| CN108944531A (en) * | 2018-07-24 | 2018-12-07 | 河海大学常州校区 | A kind of orderly charge control method of electric car |
| CN110363332A (en) * | 2019-06-21 | 2019-10-22 | 国网天津市电力公司电力科学研究院 | A kind of electric car charging load spatial and temporal distributions prediction technique based on individual behavior characteristic |
| CN115456180A (en) * | 2022-08-17 | 2022-12-09 | 上海电机学院 | Electric vehicle quantity prediction method based on three-chain Markov model |
-
2019
- 2019-12-02 CN CN201911212935.5A patent/CN110929950B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105591433A (en) * | 2016-01-15 | 2016-05-18 | 国家电网公司 | Electric automobile charging load optimization method based on electric automobile charging power dynamic distribution |
| CN108944531A (en) * | 2018-07-24 | 2018-12-07 | 河海大学常州校区 | A kind of orderly charge control method of electric car |
| CN110363332A (en) * | 2019-06-21 | 2019-10-22 | 国网天津市电力公司电力科学研究院 | A kind of electric car charging load spatial and temporal distributions prediction technique based on individual behavior characteristic |
| CN115456180A (en) * | 2022-08-17 | 2022-12-09 | 上海电机学院 | Electric vehicle quantity prediction method based on three-chain Markov model |
Non-Patent Citations (2)
| Title |
|---|
| FENGLEI LI: "Optimal Scheduling Strategy of Distribution Network Based on Electric Vehicle Forecasting" * |
| 康树祝: "基于改进NSGA2 的临近空间通信网络优化设计" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111983480A (en) * | 2020-08-19 | 2020-11-24 | 华晟（青岛）智能装备科技有限公司 | AGV electric quantity state prediction method and system based on Mahalanobis process |
| CN114611811A (en) * | 2022-03-21 | 2022-06-10 | 特斯联科技集团有限公司 | Low-carbon park optimal scheduling method and system based on EV load participation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110929950B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Expansion planning of active distribution networks with multiple distributed energy resources and EV sharing system | |
| Panahi et al. | Forecasting plug-in electric vehicles load profile using artificial neural networks | |
| Lin et al. | Optimized allocation of scooter battery swapping station under demand uncertainty | |
| CN103745110B (en) | Method of estimating operational driving range of all-electric buses | |
| CN110826841A (en) | Charging station planning method considering user charging experience and power distribution network operation risk | |
| CN109800917A (en) | A kind of planing method in electric car parking lot, device and calculate equipment | |
| CN111626492B (en) | Fuzzy multi-target opportunity constraint planning method for electric vehicle charging network | |
| CN112507506B (en) | Multi-objective optimization method for sharing automobile pricing planning model based on genetic algorithm | |
| CN110929950A (en) | Electric vehicle load prediction method and system | |
| CN111222705B (en) | Nonlinear charging vehicle path optimization method | |
| Tadayon‐Roody et al. | Multi‐objective locating of electric vehicle charging stations considering travel comfort in urban transportation system | |
| CN109978241B (en) | Method and device for determining charging load of electric automobile | |
| CN113964854A (en) | Intelligent charging and discharging method for V2G of electric vehicle | |
| CN111626493B (en) | Charging network planning method considering charging service capacity and operation efficiency | |
| Helmus et al. | SEVA: A data driven model of electric vehicle charging behavior | |
| Ma et al. | An agent-based training system for optimizing the layout of AFVs' initial filling stations | |
| CN116702404A (en) | Fuzzy double-target electric vehicle charging station planning optimization method considering target priority | |
| CN114139794A (en) | Regional public parking lot charging demand prediction method based on parking big data | |
| CN114444802A (en) | Electric vehicle charging guide optimization method based on graph neural network reinforcement learning | |
| CN114548564A (en) | Battery distribution path optimization method and device, computer equipment and storage medium | |
| CN114707292A (en) | Voltage stability analysis method for power distribution network containing electric automobile | |
| CN114169624A (en) | Electric vehicle charging station planning method and device | |
| CN114329783A (en) | Multi-target electric vehicle charging network planning method | |
| CN113836735A (en) | Method for establishing two-stage model of electric bus cluster battery charging and replacing strategy in battery replacing mode | |
| CN111369741B (en) | System for matching multiple parking lots with shared parking spaces and electric vehicles in electric power market |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |