CN115000999B - Day-ahead response capability assessment method for electric automobile - Google Patents

Day-ahead response capability assessment method for electric automobile Download PDF

Info

Publication number
CN115000999B
CN115000999B CN202210842199.7A CN202210842199A CN115000999B CN 115000999 B CN115000999 B CN 115000999B CN 202210842199 A CN202210842199 A CN 202210842199A CN 115000999 B CN115000999 B CN 115000999B
Authority
CN
China
Prior art keywords
day
ahead
charging
electric vehicles
electric
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.)
Active
Application number
CN202210842199.7A
Other languages
Chinese (zh)
Other versions
CN115000999A (en
Inventor
刘盼盼
章锐
周吉
钱俊良
邰伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Dongbo Intelligent Energy Research Institute Co ltd
Liyang Research Institute of Southeast University
Original Assignee
Nanjing Dongbo Intelligent Energy Research Institute Co ltd
Liyang Research Institute of Southeast University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Dongbo Intelligent Energy Research Institute Co ltd, Liyang Research Institute of Southeast University filed Critical Nanjing Dongbo Intelligent Energy Research Institute Co ltd
Priority to CN202210842199.7A priority Critical patent/CN115000999B/en
Publication of CN115000999A publication Critical patent/CN115000999A/en
Application granted granted Critical
Publication of CN115000999B publication Critical patent/CN115000999B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
    • H02J3/322—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means the battery being on-board an electric or hybrid vehicle, e.g. vehicle to grid arrangements [V2G], power aggregation, use of the battery for network load balancing, coordinated or cooperative battery charging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
    • H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/24—Arrangements for preventing or reducing oscillations of power in networks
    • H02J3/241—The oscillation concerning frequency
    • 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
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/60—Other road transportation technologies with climate change mitigation effect
    • Y02T10/70—Energy storage systems for electromobility, e.g. batteries

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The invention discloses a day-ahead response capability assessment method for an electric vehicle, which comprises the steps of carrying out information acquisition on charging station information in an electric vehicle day; training the quantity of the electric vehicles in the controllable state and the forced charging state at different time in the day to obtain the quantity of the electric vehicles in the charging state and the discharging state at different time in the day and the predicted value of the quantity of the forced charging electric vehicles; constructing a day-ahead response capability evaluation model of the electric vehicle charging station, and predicting the response capability of the electric vehicle charging station in different time periods in the day-ahead; constructing a day-ahead electric vehicle arrival charging time correction model based on traffic index correction, and determining a day-ahead arrival charging time correction factor of the electric vehicle; and constructing a traffic index correction-based electric vehicle charging station day-ahead response capability evaluation model. The invention can master the day-ahead response capability of the electric automobile, make the day-ahead operation plan of the support power grid and improve the making quality of the operation plan of the novel power system.

Description

Day-ahead response capability assessment method for electric automobile
Technical Field
The invention discloses a method for evaluating day-ahead response capability of an electric automobile, and belongs to the field of power systems.
Background
With the development of global clean energy, the number of stable thermal power generating units mainly based on fossil energy in a power grid is gradually reduced, new energy units with uncertainty, randomness, volatility and uncontrollable property are gradually increased, such as wind power and photovoltaic, until 2020, the total scale of a renewable energy power generation and installation machine in China reaches 9.3 hundred million kilowatts, the proportion of the renewable energy power generation and installation machine in China reaches 42.4%, and the renewable energy power generation and installation machine is increased by 14.6 percentage points in 2012. Wherein: 3.7 hundred million kilowatts of water and electricity, 2.8 million kilowatts of wind electricity, 2.5 million kilowatts of photovoltaic power generation and 2952 million kilowatts of biomass power generation, which are respectively and continuously 16 years, 11 years, 6 years and 3 years and stably live in the first position of the world. Compared with the traditional power grid, the stable operation level of the novel power system taking new energy as a main body is relatively low, and the load side adjustment resources need to be excavated. In recent years, the number of electric vehicles is rapidly increased, the electric vehicles are large in scale, can participate in peak regulation, voltage regulation and the like of a power grid in the charging process, have certain response capability, are good adjustable resources, evaluate the day-ahead response capability of the electric vehicles, actively upload the response capability to the power grid, reasonably arrange a day-ahead plan for the power grid, support power grid dispatching and reduce the dispatching pressure of the power grid, and have important significance.
However, with the increasing number of electric vehicles, the day-ahead response capability of the electric vehicle is difficult to effectively evaluate, the making of a day-ahead power grid operation plan is difficult to effectively support, and negative effects on the stable operation of the power grid are increasingly prominent.
Disclosure of Invention
The invention aims to provide a method for evaluating the day-ahead response capability of an electric vehicle, which aims at fully excavating the day-ahead response capability of the electric vehicle, mastering the upper and lower limit values of the day-ahead response power of the electric vehicle, providing support for the formulation of a day-ahead power grid operation plan, supporting the formulation of the day-ahead power grid operation plan and improving the safe and stable operation level of a novel power system.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention discloses a method for evaluating day-ahead response capability of an electric automobile, which comprises the following steps of:
step (1): acquiring information of charging stations in the electric automobile day;
step (2): establishing an ARMA-RESN-based electric vehicle day-ahead charging and discharging quantity prediction model based on the collected charging station information of the electric vehicle in the day, and training the quantity of the electric vehicles in controllable states and forced charging states at different times in the day based on a time sequence model ARMA and a regularized echo state network model RESN to obtain predicted values of the quantity of the electric vehicles in the charging states and the discharging states at different times in the day and the quantity of the forced charging electric vehicles;
and (3): constructing a day-ahead response capability evaluation model of the electric vehicle charging station based on the predicted values of the charging states and the discharging states of the electric vehicles at different time periods in the day ahead and the number of the electric vehicles to be forcibly charged, and predicting the response capability of the electric vehicle charging station in different time periods in the day ahead;
and (4): collecting day-ahead charging station information, analyzing road congestion time difference of the electric automobile based on the difference between a day-ahead traffic index and a day-ahead traffic index, correcting arrival charging time of the electric automobile, constructing a day-ahead arrival charging time correction model of the electric automobile based on traffic index correction, and calculating a day-ahead arrival charging time correction factor of the electric automobile;
and (5): and modifying the day-ahead response capability evaluation model of the electric vehicle charging station based on the day-ahead arrival charging time modification factor of the electric vehicle, and constructing the day-ahead response capability evaluation model of the electric vehicle charging station based on traffic index modification.
In the step (1), the collected charging station information in the day includes the number of electric vehicles in a charging state, the number of electric vehicles in a discharging state, and a road traffic index, and the charging station information is expressed by a mode shown in formula (1):
Figure 534646DEST_PATH_IMAGE001
（1）
in the formula (I), the compound is shown in the specification,
Figure 639743DEST_PATH_IMAGE002
represent
Figure 836369DEST_PATH_IMAGE003
The information of the charging station at the moment,
Figure 528381DEST_PATH_IMAGE004
represent
Figure 468655DEST_PATH_IMAGE003
The number of electric vehicles that are in a charged state at the moment,
Figure 696768DEST_PATH_IMAGE005
to represent
Figure 798716DEST_PATH_IMAGE003
The number of electric vehicles that are in a discharge state at the moment,
Figure 118970DEST_PATH_IMAGE006
to represent
Figure 95891DEST_PATH_IMAGE003
And (4) performing time alignment processing on the acquired data at different times according to the road traffic indexes at the moment.
In the step (2), an ARMA-RESN-based electric vehicle day-ahead charging and discharging quantity prediction model is constructed, and is shown in formulas (2) to (5):
Figure 411466DEST_PATH_IMAGE007
（2）
Figure 949895DEST_PATH_IMAGE008
（3）
Figure 10908DEST_PATH_IMAGE009
（4）
Figure 558564DEST_PATH_IMAGE010
（5）
in the formula:
Figure 728646DEST_PATH_IMAGE011
is composed oftThe linear change predicted value of the number of the electric vehicles at any moment,
Figure 202090DEST_PATH_IMAGE012
for input of
Figure 231357DEST_PATH_IMAGE013
The information of the charging station at the moment,
Figure 51546DEST_PATH_IMAGE014
for input
Figure 843177DEST_PATH_IMAGE015
The information of the charging station at the moment,
Figure 723409DEST_PATH_IMAGE016
for inputting the number of samples,
Figure 99027DEST_PATH_IMAGE017
Is a sample
Figure 722906DEST_PATH_IMAGE018
A charge information factor estimation parameter,
Figure 631694DEST_PATH_IMAGE019
Is a sample
Figure 682826DEST_PATH_IMAGE020
White noise factor estimationThe parameters are measured, and the parameters are calculated,
Figure 545740DEST_PATH_IMAGE021
，
Figure 707731DEST_PATH_IMAGE022
is composed oftWhite noise with zero mean value at the moment,
Figure 733675DEST_PATH_IMAGE023
is composed of
Figure 424551DEST_PATH_IMAGE024
An n-th order zero-mean white noise estimate at time,
Figure 712444DEST_PATH_IMAGE025
is composed of
Figure 442240DEST_PATH_IMAGE026
An n-th order zero-mean white noise estimate at time,
Figure 561506DEST_PATH_IMAGE027
is composed oftThe nonlinear change prediction value of the number of electric vehicles at any moment,
Figure 220020DEST_PATH_IMAGE028
in order to activate the function(s),
Figure 791947DEST_PATH_IMAGE029
、
Figure 938151DEST_PATH_IMAGE030
respectively an input connection vector and a connection matrix inside the reserve pool,
Figure 177502DEST_PATH_IMAGE031
、
Figure 6918DEST_PATH_IMAGE032
are respectively astThe input vector at the time and the pool mapping state vector,
Figure 564676DEST_PATH_IMAGE033
is composed of
Figure 137740DEST_PATH_IMAGE034
The internal state vector of the reserve pool at the moment,
Figure 231598DEST_PATH_IMAGE035
in order to output the connection vector for regression,
Figure 966336DEST_PATH_IMAGE036
for vector of input samplesiIs determined by the estimated parameters of (a) and (b),
Figure 274039DEST_PATH_IMAGE037
as vectors of input samplesiThe transpose of (a) is performed,ris a state matrix
Figure 119636DEST_PATH_IMAGE038
The rank of (c) is determined,lin order to train the number of samples,
Figure 208945DEST_PATH_IMAGE039
as a matrix of states
Figure 613120DEST_PATH_IMAGE040
The singular value of (a) is,
Figure 178093DEST_PATH_IMAGE041
in order to disturb the signal(s),pin order to be an auto-regressive term,qtaking 0,1,2 as the moving average number of terms;
Figure 30643DEST_PATH_IMAGE042
is composed oftThe predicted value of the number of the electric vehicles in the charging and discharging states before the moment,
Figure 334979DEST_PATH_IMAGE043
、
Figure 552464DEST_PATH_IMAGE044
in the day front for charging stations respectivelytPredicted value of controllable number of charged electric vehicles at any time and forced charging electric vehicle numberA predicted value of the amount.
In the step (2), the number of electric vehicles in controllable states and forced charging states at different times in the day is trained to obtain the predicted values of the number of electric vehicles in charging states and discharging states and the number of forced charging electric vehicles at different times in the day ahead; the following method is adopted:
(2-1) predicting the linear change of the number of electric vehicles in the past by adopting ARMA linear fitting based on a time series model ARMA to obtain a predicted value of the linear change of the number of electric vehicles;
(2-2) predicting the nonlinear change of the number of the electric vehicles by adopting a nonlinear prediction RESN based on the regularized echo state network model RESN to obtain a predicted value of the nonlinear change of the number of the electric vehicles;
and (2-3) fusing the predicted value of the linear change of the number of the electric vehicles and the predicted value of the nonlinear change of the number of the electric vehicles to obtain the predicted values of the number of the electric vehicles in the charging state and the discharging state at different time in the day and the number of the electric vehicles in the forced charging state.
In the step (3), a day-ahead response capability evaluation model of the electric vehicle charging station is constructed, and is shown in a formula (6):
Figure 244215DEST_PATH_IMAGE045
（6）
in the formula:
Figure 697193DEST_PATH_IMAGE046
、
Figure 991121DEST_PATH_IMAGE047
electric vehicle charging station for respectively predictionjDay-ahead maximum response capability, minimum response capability,
Figure 504142DEST_PATH_IMAGE048
、
Figure 246970DEST_PATH_IMAGE049
at day-ahead for charging stations, respectivelytThe predicted value of the controllable number of the charging electric vehicles and the predicted value of the forced number of the charging electric vehicles at the moment,
Figure 503639DEST_PATH_IMAGE050
、
Figure 779637DEST_PATH_IMAGE051
、
Figure 197980DEST_PATH_IMAGE052
are respectively astAverage charging power, average discharging power and average forced charging power of the electric vehicle at the moment.
In the step (4), the road congestion time difference of the electric automobile is analyzed based on the difference between the day-ahead traffic index and the day-inside traffic index, the arrival charging time of the electric automobile is corrected, a day-ahead arrival charging time correction model of the electric automobile based on traffic index correction is constructed, as shown in a formula (7) and a formula (8),
Figure 959263DEST_PATH_IMAGE053
（7）
Figure 754044DEST_PATH_IMAGE054
（8）
in the formula (I), the compound is shown in the specification,
Figure 294003DEST_PATH_IMAGE055
the traffic index of the city is shown as the urban traffic index,
Figure 148826DEST_PATH_IMAGE056
is a time factor for the traffic jam,
Figure 131826DEST_PATH_IMAGE057
the correction factor of the charging time of the electric automobile arriving at the station in the day ahead,
Figure 228832DEST_PATH_IMAGE058
、
Figure 980888DEST_PATH_IMAGE059
respectively serving as an intra-day traffic jam time factor and a day-ahead traffic jam time factor of the city;
according to the urban traffic index
Figure 741033DEST_PATH_IMAGE055
Obtaining the traffic index before the day and the traffic index in the day of the city
Figure 945750DEST_PATH_IMAGE060
、
Figure 601376DEST_PATH_IMAGE061
And respectively calculating the traffic jam time factors in the city day by combining the formula (7)
Figure 207938DEST_PATH_IMAGE062
Day-ahead traffic congestion time factor
Figure 279930DEST_PATH_IMAGE063
According to the time factor of traffic jam in the day
Figure 470478DEST_PATH_IMAGE062
Day-ahead traffic congestion time factor
Figure 145173DEST_PATH_IMAGE063
Obtaining the charging time correction factor of the electric automobile arriving at the station in the day ahead
Figure 606241DEST_PATH_IMAGE057
。
In the step (5), the correction factor is based on the day-ahead arrival charging time of the electric automobile
Figure 973769DEST_PATH_IMAGE057
Correcting the day-ahead response capability evaluation model of the electric vehicle charging station, and constructing the day-ahead response capability evaluation model of the electric vehicle charging station based on traffic index correctionThe response capability evaluation model is shown in equation (9):
Figure 12132DEST_PATH_IMAGE064
（9）
in the formula:
Figure 726403DEST_PATH_IMAGE065
、
Figure 307557DEST_PATH_IMAGE066
the maximum response capability and the minimum response capability of the electric automobile after the correction at the time t are respectively,
Figure 580407DEST_PATH_IMAGE067
、
Figure 247011DEST_PATH_IMAGE068
at day-ahead for charging stations, respectivelytThe predicted value of the quantity of the controllable charging electric vehicles and the predicted value of the quantity of the forced charging electric vehicles after the time correction,
Figure 699727DEST_PATH_IMAGE069
、
Figure 135388DEST_PATH_IMAGE070
、
Figure 844718DEST_PATH_IMAGE071
are respectively astAnd the average charging power, the average discharging power and the average forced charging power of the electric vehicle after the time correction.
The invention has the technical effects and advantages that:
the method for evaluating the day-ahead response capability of the electric automobile can master the day-ahead response capability of the electric automobile, can participate in peak regulation and voltage regulation of a power grid in the charging process of the electric automobile, effectively regulates power distribution resources, has certain response capability, evaluates the day-ahead response capability of the electric automobile, and actively uploads the day-ahead response capability to the power grid, so that a day-ahead plan is reasonably arranged for the power grid, the power grid is supported to be scheduled, the power grid scheduling pressure is reduced, the day-ahead operation plan of the support power grid is formulated, the formulation quality of a novel power system operation plan is improved, and the power grid is assisted to realize a double-carbon target in the early days.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of a model for predicting the number of electric vehicles in the day ahead.
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.
Aiming at the problems that the number of electric automobiles is rapidly increased in recent years, the electric automobiles are large in scale, and adverse effects are brought to power grid peak regulation, voltage regulation and the like in the charging peak period of the electric automobiles, a novel power system is oriented, and support is provided for the planning of the power grid operation in the future.
The invention provides a method for evaluating day-ahead response capability of an electric automobile, which comprises the following steps of:
step (1), an electric vehicle charging and discharging information acquisition technology is provided, information acquisition is carried out on the charging and discharging conditions of an electric vehicle, charging station information in a day is acquired by taking a charging station as a research object, the charging station information comprises the number of electric vehicles in a charging state, the number of electric vehicles in a discharging state and a road traffic index, and the charging station information is expressed in a mode shown in a formula (1):
Figure 369590DEST_PATH_IMAGE072
（1）
in the formula (I), the compound is shown in the specification,
Figure 48833DEST_PATH_IMAGE073
to represent
Figure 11104DEST_PATH_IMAGE074
The information of the charging station at the moment,
Figure 389871DEST_PATH_IMAGE075
to represent
Figure 31068DEST_PATH_IMAGE074
The number of electric vehicles that are in a charged state at the moment,
Figure 389368DEST_PATH_IMAGE076
represent
Figure 799621DEST_PATH_IMAGE074
The number of electric vehicles that are in a discharge state at the moment,
Figure 352218DEST_PATH_IMAGE077
to represent
Figure 215132DEST_PATH_IMAGE074
And (4) performing time alignment processing on the acquired data at different times according to the road traffic indexes at the moment. And (2) constructing an ARMA-RESN-based electric vehicle day-ahead charging and discharging quantity prediction model based on the charging station information in the collection day, training the quantity of electric vehicles in controllable and forced charging states at different times in the day based on a time sequence model ARMA (autoregestive Moving Average model), a Regularized Echo State Network model RESN (RESN), predicting the quantity of electric vehicles in charging and discharging states at different times in the day, and obtaining the predicted values of the quantity of electric vehicles in charging and discharging states at different times in the day and the quantity of forced charging electric vehicles.
The constructed ARMA-RESN-based electric vehicle day-ahead charging and discharging quantity prediction model is shown in figure 2 as formulas (2) to (5):
Figure 518068DEST_PATH_IMAGE078
（2）
Figure 15783DEST_PATH_IMAGE079
（3）
Figure 96872DEST_PATH_IMAGE080
（4）
Figure 447082DEST_PATH_IMAGE081
（5）
in the formula:
Figure 412764DEST_PATH_IMAGE082
is composed oftThe linear change predicted value of the number of the electric automobiles at the moment,
Figure 532030DEST_PATH_IMAGE083
for input of
Figure 154991DEST_PATH_IMAGE084
The information of the charging station at the moment,
Figure 992497DEST_PATH_IMAGE085
for input of
Figure 496291DEST_PATH_IMAGE086
The information of the charging station at the moment,
Figure 735642DEST_PATH_IMAGE087
、
Figure 532435DEST_PATH_IMAGE088
、
Figure 794920DEST_PATH_IMAGE089
all parameters to be estimated are obtained by least square estimation;
Figure 102404DEST_PATH_IMAGE090
is composed oftWhite noise with zero mean value at the moment,
Figure 432148DEST_PATH_IMAGE091
is composed of
Figure 166886DEST_PATH_IMAGE092
An n-th order zero-mean white noise estimate at time,
Figure 854350DEST_PATH_IMAGE093
is composed of
Figure 464061DEST_PATH_IMAGE094
White noise estimation value of zero mean value of n-order at time;
Figure 678004DEST_PATH_IMAGE095
is composed oftNonlinear change prediction values of the number of electric vehicles at any moment;
Figure 583644DEST_PATH_IMAGE096
in order to activate the function(s),
Figure 617459DEST_PATH_IMAGE097
、
Figure 762351DEST_PATH_IMAGE098
respectively are input and connection matrixes inside the reserve pool;
Figure 565222DEST_PATH_IMAGE099
、
Figure 907342DEST_PATH_IMAGE100
are respectively astAn input vector of time and a reserve pool internal state vector;
Figure 694032DEST_PATH_IMAGE101
in order to output the connection vector,
Figure 379966DEST_PATH_IMAGE102
to be transportedVector of input samplesiIs determined by the estimated parameters of (a) and (b),
Figure 302923DEST_PATH_IMAGE103
as vectors of input samplesiThe transpose of (a) is performed,ris a state matrix
Figure 550365DEST_PATH_IMAGE104
The rank of (c) is determined,lin order to train the number of samples,
Figure 558772DEST_PATH_IMAGE105
is a state matrix
Figure 51327DEST_PATH_IMAGE104
The singular value of (a) is,
Figure 828790DEST_PATH_IMAGE106
in order to disturb the signal(s),pin order to be an auto-regressive term,qfor moving average number of terms, 0,1,2 is generally selected;
Figure 247133DEST_PATH_IMAGE107
is composed oftThe predicted value of the number of the electric vehicles in the charging and discharging states before the moment;
Figure 477257DEST_PATH_IMAGE108
、
Figure 770573DEST_PATH_IMAGE109
at day-ahead for charging stations, respectivelytThe predicted value of the quantity of the controllable charging electric vehicles and the predicted value of the quantity of the forced charging electric vehicles at the moment.
Considering that the number of the electric vehicles in the controllable state and the forced charging state not only has the linear change characteristics, but also has the nonlinear change characteristics such as randomness and chaotic mutant types, therefore, the method adopts the following method to train the number of the electric vehicles in the controllable state and the forced charging state at different times in the day:
(2-1) firstly, predicting the linear change of the number of the electric vehicles in the past by adopting the strong linear fitting capacity of the ARMA based on a time series model ARMA to obtain a predicted value of the linear change of the number of the electric vehicles;
(2-2) predicting the non-linear change of the number of the electric vehicles by adopting the RESN with better non-linear prediction capability based on the regularized echo state network model RESN to obtain a predicted value of the non-linear change of the number of the electric vehicles;
and (2-3) finally, fusing the linear change predicted value and the nonlinear change predicted value of the number of the electric vehicles, specifically, superposing and summing the linear part and the nonlinear part to obtain more accurate predicted values of the number of the electric vehicles in the charging state and the discharging state at different times in the day ahead and the number of the electric vehicles in the forced charging state.
And (3) constructing a day-ahead response capability evaluation model of the electric vehicle charging station based on the predicted values of the number of the electric vehicles in the charging state and the discharging state at different time in the day and the number of the electric vehicles in the forced charging state, and predicting the response capability of the electric vehicle charging station in different time periods in the day based on the predicted charging state and the predicted number of the electric vehicles in the discharging state at different time in the day.
Constructing a response capability evaluation model of an electric vehicle charging station in the day ahead, as shown in formula (6):
Figure 402542DEST_PATH_IMAGE110
（6）
in the formula:
Figure 991787DEST_PATH_IMAGE111
、
Figure 974786DEST_PATH_IMAGE112
electric vehicle charging station with predictionjMaximum response capability, minimum response capability in the day ahead,
Figure 826721DEST_PATH_IMAGE113
、
Figure 313198DEST_PATH_IMAGE114
at day-ahead for charging stations, respectivelytThe predicted value of the controllable number of the charging electric vehicles and the predicted value of the forced number of the charging electric vehicles at the moment,
Figure 338922DEST_PATH_IMAGE115
、
Figure 543639DEST_PATH_IMAGE116
、
Figure 178757DEST_PATH_IMAGE117
are respectively astAverage charging power, average discharging power and average forced charging power of the electric vehicle at the moment.
And (4) acquiring day-ahead charging station information according to the step (1), analyzing the road congestion time difference of the electric automobile based on the difference between the day-ahead traffic index and the day-ahead traffic index, correcting the arrival charging time of the electric automobile, and constructing a day-ahead arrival charging time correction model of the electric automobile based on traffic index correction.
The model for correcting the arrival charging time of the electric vehicle before day based on the traffic index correction is shown in the formula (7) and the formula (8),
Figure 660685DEST_PATH_IMAGE118
（7）
Figure 122891DEST_PATH_IMAGE119
（8）
in the formula (I), the compound is shown in the specification,
Figure 316368DEST_PATH_IMAGE120
the traffic index of the city is shown as the urban traffic index,
Figure 991063DEST_PATH_IMAGE121
is a time factor for the traffic jam,
Figure 717710DEST_PATH_IMAGE122
a correction factor for the charging time of the electric automobile arriving at the station in the day ahead,
Figure 85238DEST_PATH_IMAGE123
、
Figure 763082DEST_PATH_IMAGE124
respectively serving as an intra-day traffic jam time factor and a day-ahead traffic jam time factor of the city;
according to
Figure 458112DEST_PATH_IMAGE120
For the urban traffic index, the day-ahead traffic index and the day-inside traffic index of the city are obtained
Figure 39266DEST_PATH_IMAGE125
、
Figure 312115DEST_PATH_IMAGE126
And respectively calculating the traffic jam time factors in the city day by combining the formula (7)
Figure 477255DEST_PATH_IMAGE127
Day-ahead traffic congestion time factor
Figure 759332DEST_PATH_IMAGE128
According to the time factor of traffic jam in the day
Figure 194992DEST_PATH_IMAGE127
Day-ahead traffic congestion time factor
Figure 638743DEST_PATH_IMAGE128
Calculating the correction factor of the charging time of the electric automobile arriving at the station in the day ahead
Figure 553829DEST_PATH_IMAGE122
。
And (5) modifying a day-ahead electric vehicle arrival charging time modification model based on traffic index modification, modifying the day-ahead response capability of the electric vehicle, and constructing an electric vehicle charging station day-ahead response capability evaluation model based on traffic index modification.
Day-ahead arrival charging time correction factor based on electric automobile
Figure 374017DEST_PATH_IMAGE122
Correcting the electric vehicle charging station day-ahead response capability evaluation model, and constructing the electric vehicle charging station day-ahead response capability evaluation model based on traffic index correction as shown in a formula (9):
Figure 664184DEST_PATH_IMAGE129
（9）
in the formula:
Figure 544416DEST_PATH_IMAGE130
、
Figure 418568DEST_PATH_IMAGE131
the maximum response capability and the minimum response capability of the electric automobile after the correction at the time t are respectively,
Figure 917814DEST_PATH_IMAGE132
、
Figure 593646DEST_PATH_IMAGE133
at day-ahead for charging stations, respectivelytThe predicted value of the quantity of the controllable charging electric vehicles and the predicted value of the quantity of the forced charging electric vehicles after the time correction,
Figure 880664DEST_PATH_IMAGE134
、
Figure 743578DEST_PATH_IMAGE135
、
Figure 905569DEST_PATH_IMAGE136
are respectively astAnd the average charging power, the average discharging power and the average forced charging power of the electric vehicle after the time correction.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still make modifications to the technical solutions described in the foregoing embodiments, or make equivalent substitutions and improvements to part of the technical features of the foregoing embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (7)

1. A day-ahead response capability assessment method for an electric vehicle is characterized by comprising the following steps:
step (1): acquiring information of charging stations in the day of the electric automobile;
step (2): establishing an ARMA-RESN-based electric vehicle day-ahead charging and discharging quantity prediction model based on the collected charging station information of the electric vehicle in the day, and training the quantity of the electric vehicles in controllable states and forced charging states at different times in the day based on a time sequence model ARMA and a regularized echo state network model RESN to obtain predicted values of the quantity of the electric vehicles in the charging states and the discharging states at different times in the day and the quantity of the forced charging electric vehicles;
and (3): constructing a day-ahead response capability evaluation model of the electric vehicle charging station based on the predicted values of the charging states and the discharging states of the electric vehicles at different time periods in the day ahead and the number of the electric vehicles to be forcibly charged, and predicting the response capability of the electric vehicle charging station in different time periods in the day ahead;
and (4): collecting day-ahead charging station information, analyzing road congestion time difference of the electric automobile based on the difference between a day-ahead traffic index and a day-ahead traffic index, correcting arrival charging time of the electric automobile, constructing a day-ahead arrival charging time correction model of the electric automobile based on traffic index correction, and calculating a day-ahead arrival charging time correction factor of the electric automobile;
and (5): and modifying the day-ahead response capability evaluation model of the electric vehicle charging station based on the day-ahead arrival charging time modification factor of the electric vehicle, and constructing the day-ahead response capability evaluation model of the electric vehicle charging station based on traffic index modification.
2. The method for evaluating day-ahead response capability of an electric vehicle according to claim 1, wherein in step (1), the collected day-ahead charging station information includes the number of electric vehicles in a charging state, the number of electric vehicles in a discharging state and a road traffic index, and the charging station information is expressed as shown in formula (1):
Figure 290737DEST_PATH_IMAGE001
（1）
in the formula (I), the compound is shown in the specification,
Figure 896293DEST_PATH_IMAGE002
to represent
Figure 535085DEST_PATH_IMAGE003
The information of the charging station at the moment,
Figure 867977DEST_PATH_IMAGE004
represent
Figure 636344DEST_PATH_IMAGE003
The number of electric vehicles that are in a charged state at the moment,
Figure 396490DEST_PATH_IMAGE005
to represent
Figure 991419DEST_PATH_IMAGE003
The number of electric vehicles that are in a discharge state at a moment,
Figure 878735DEST_PATH_IMAGE006
to represent
Figure 750876DEST_PATH_IMAGE003
And (4) performing time alignment processing on the acquired data at different times according to the road traffic indexes at the moments.
3. The method for evaluating the day-ahead response capability of the electric vehicle according to claim 2, wherein in the step (2), an ARMA-RESN-based electric vehicle day-ahead charge and discharge quantity prediction model is constructed as shown in formulas (2) to (5):
Figure 196770DEST_PATH_IMAGE007
（2）
Figure 888782DEST_PATH_IMAGE008
（3）
Figure 573930DEST_PATH_IMAGE009
（4）
Figure 425211DEST_PATH_IMAGE010
（5）
in the formula:
Figure 792738DEST_PATH_IMAGE011
is composed oftThe linear change predicted value of the number of the electric automobiles at the moment,
Figure 722779DEST_PATH_IMAGE012
for input of
Figure 201165DEST_PATH_IMAGE013
The information of the charging station at the moment,
Figure 297166DEST_PATH_IMAGE014
for input of
Figure 570016DEST_PATH_IMAGE015
The information of the charging station at the moment,
Figure 252932DEST_PATH_IMAGE016
for inputting the number of samples,
Figure 269429DEST_PATH_IMAGE017
Is a sample
Figure 95303DEST_PATH_IMAGE019
A charge information factor estimation parameter,
Figure 352103DEST_PATH_IMAGE020
Is a sample
Figure 896217DEST_PATH_IMAGE019
The white noise factor estimation parameter is set to be,
Figure 716405DEST_PATH_IMAGE021
，
Figure 40462DEST_PATH_IMAGE022
is composed oftWhite noise with zero mean value at the moment,
Figure 920694DEST_PATH_IMAGE023
is composed of
Figure 811158DEST_PATH_IMAGE024
An n-th order zero-mean white noise estimate at time,
Figure 169458DEST_PATH_IMAGE025
is composed of
Figure 471389DEST_PATH_IMAGE026
An n-th order zero-mean white noise estimate at time,
Figure 771789DEST_PATH_IMAGE027
is composed oftThe nonlinear change prediction value of the number of the electric automobiles at any moment,
Figure 634703DEST_PATH_IMAGE028
in order to activate the function(s),
Figure 547426DEST_PATH_IMAGE029
、
Figure 546606DEST_PATH_IMAGE030
respectively an input connection vector and a connection matrix inside the reserve pool,
Figure 283487DEST_PATH_IMAGE031
、
Figure 633697DEST_PATH_IMAGE032
are respectively astThe input vector at the time and the pool mapping state vector,
Figure 615690DEST_PATH_IMAGE033
is composed of
Figure 734956DEST_PATH_IMAGE034
The internal state vector of the reserve pool at the moment,
Figure 377159DEST_PATH_IMAGE035
in order to output the connected vectors for the regression,
Figure 214665DEST_PATH_IMAGE036
for vector of input samplesiThe estimated parameters of (2) are set,
Figure 604277DEST_PATH_IMAGE037
for vector of input samplesiThe transpose of (a) is performed,ris a state matrix
Figure 92896DEST_PATH_IMAGE038
The rank of (c) is determined,lin order to train the number of samples,
Figure 391153DEST_PATH_IMAGE039
is a state matrix
Figure 466688DEST_PATH_IMAGE038
The singular value of (a) is,
Figure 774173DEST_PATH_IMAGE040
in order to disturb the signal(s),pin order to be an auto-regressive term,qtaking 0,1,2 as the moving average number of terms;
Figure 851719DEST_PATH_IMAGE041
is composed oftThe predicted value of the quantity of the electric vehicles in the charging and discharging states before the moment,
Figure 852036DEST_PATH_IMAGE042
、
Figure 414867DEST_PATH_IMAGE043
at day-ahead for charging stations, respectivelytThe predicted value of the quantity of the controllable charging electric vehicles and the predicted value of the quantity of the forced charging electric vehicles at the moment.
4. The day-ahead response capability assessment method for electric vehicles according to claim 3, wherein in the step (2), the number of electric vehicles in controllable state and forced charging state at different time of day is trained to obtain the predicted values of the number of electric vehicles in charging state and discharging state and the forced charging state at different time of day; the following method is adopted:
(2-1) predicting the linear change of the number of the electric vehicles in the day ahead by adopting ARMA linear fitting based on a time series model ARMA to obtain a predicted value of the linear change of the number of the electric vehicles;
(2-2) predicting the nonlinear change of the number of the electric vehicles by adopting a nonlinear prediction RESN based on the regularized echo state network model RESN to obtain a predicted value of the nonlinear change of the number of the electric vehicles;
and (2-3) fusing the predicted value of the linear change of the number of the electric vehicles and the predicted value of the nonlinear change of the number of the electric vehicles to obtain the predicted values of the number of the electric vehicles in the charging state and the discharging state at different time in the day and the number of the electric vehicles in the forced charging state.
5. The method for evaluating the day-ahead response capability of the electric vehicle according to claim 4, wherein in the step (3), a day-ahead response capability evaluation model of the electric vehicle charging station is constructed, as shown in formula (6):
Figure 526042DEST_PATH_IMAGE044
（6）
in the formula:
Figure 989253DEST_PATH_IMAGE045
、
Figure 894892DEST_PATH_IMAGE046
electric vehicle charging station with predictionjDay-ahead maximum response capability, minimum response capability,
Figure 679440DEST_PATH_IMAGE047
、
Figure 718940DEST_PATH_IMAGE048
at day-ahead for charging stations, respectivelytThe predicted value of the controllable number of the charging electric vehicles and the predicted value of the forced number of the charging electric vehicles at the moment,
Figure 521811DEST_PATH_IMAGE049
、
Figure 343224DEST_PATH_IMAGE050
、
Figure 864336DEST_PATH_IMAGE051
are respectively astAverage charging power, average discharging power and average forced charging power of the electric vehicle at the moment.
6. The day-ahead response capability assessment method for electric vehicles according to claim 1, wherein in step (4), the road congestion time difference of electric vehicles is analyzed based on the difference between the day-ahead traffic index and the day-in traffic index, the arrival charging time of electric vehicles is corrected, and a day-ahead arrival charging time correction model based on traffic index correction is constructed, as shown in formula (7) and formula (8),
Figure 301002DEST_PATH_IMAGE052
（7）
Figure 223959DEST_PATH_IMAGE053
（8）
in the formula (I), the compound is shown in the specification,
Figure 487712DEST_PATH_IMAGE054
the index of urban traffic is the index of urban traffic,
Figure 27278DEST_PATH_IMAGE055
is a time factor for the traffic jam,
Figure 408581DEST_PATH_IMAGE056
a correction factor for the charging time of the electric automobile arriving at the station in the day ahead,
Figure 936776DEST_PATH_IMAGE057
、
Figure 355119DEST_PATH_IMAGE058
respectively serving as an intra-day traffic jam time factor and a day-ahead traffic jam time factor of the city;
according to the urban traffic index
Figure 834511DEST_PATH_IMAGE054
Obtaining the traffic index of the city before day and the traffic index of the city in day
Figure 629292DEST_PATH_IMAGE059
、
Figure 11994DEST_PATH_IMAGE060
And respectively calculating the traffic jam time factors in the city day by combining the formula (7)
Figure 866817DEST_PATH_IMAGE057
Day-ahead traffic congestion time factor
Figure 364663DEST_PATH_IMAGE058
According to the time factor of traffic jam in the day
Figure 697556DEST_PATH_IMAGE057
Day-ahead traffic congestion time factor
Figure 194484DEST_PATH_IMAGE058
Obtaining the charging time correction factor of the electric automobile arriving at the station in the day ahead
Figure 220209DEST_PATH_IMAGE056
。
7. The method for evaluating day-ahead response capability of an electric vehicle according to claim 6, wherein in the step (5), the correction factor is based on the day-ahead arrival charging time of the electric vehicle
Figure 674193DEST_PATH_IMAGE056
Correcting the electric vehicle charging station day-ahead response capability evaluation model, and constructing the electric vehicle charging station day-ahead response capability evaluation model based on traffic index correction as shown in a formula (9):
Figure 702454DEST_PATH_IMAGE061
（9）
in the formula:
Figure 43437DEST_PATH_IMAGE062
、
Figure 489330DEST_PATH_IMAGE063
the maximum response capability and the minimum response capability of the electric automobile after the correction at the time t are respectively,
Figure 181343DEST_PATH_IMAGE064
、
Figure 606770DEST_PATH_IMAGE065
at day-ahead for charging stations, respectivelytThe predicted value of the quantity of the controllable charging electric vehicles and the predicted value of the quantity of the forced charging electric vehicles after the time correction,
Figure 333418DEST_PATH_IMAGE066
、
Figure 950213DEST_PATH_IMAGE067
、
Figure 129521DEST_PATH_IMAGE068
are respectively astAnd the average charging power, the average discharging power and the average forced charging power of the electric vehicle after the time correction.
CN202210842199.7A 2022-07-18 2022-07-18 Day-ahead response capability assessment method for electric automobile Active CN115000999B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210842199.7A CN115000999B (en) 2022-07-18 2022-07-18 Day-ahead response capability assessment method for electric automobile

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210842199.7A CN115000999B (en) 2022-07-18 2022-07-18 Day-ahead response capability assessment method for electric automobile

Publications (2)

Publication Number Publication Date
CN115000999A CN115000999A (en) 2022-09-02
CN115000999B true CN115000999B (en) 2023-01-31

Family

ID=83020917

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210842199.7A Active CN115000999B (en) 2022-07-18 2022-07-18 Day-ahead response capability assessment method for electric automobile

Country Status (1)

Country Link
CN (1) CN115000999B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110378548A (en) * 2019-05-22 2019-10-25 国网江苏省电力有限公司盐城供电分公司 A kind of electric car virtual plant Multiple Time Scales responding ability assessment models construction method
CN114640133A (en) * 2022-03-15 2022-06-17 国网江苏省电力有限公司苏州供电分公司 Urban power grid electric vehicle cooperative regulation and control method and system based on real-time information

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110378548A (en) * 2019-05-22 2019-10-25 国网江苏省电力有限公司盐城供电分公司 A kind of electric car virtual plant Multiple Time Scales responding ability assessment models construction method
CN114640133A (en) * 2022-03-15 2022-06-17 国网江苏省电力有限公司苏州供电分公司 Urban power grid electric vehicle cooperative regulation and control method and system based on real-time information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Accurate Charging Demand Estimation of Electric Vehicle via Multi-Data Sources;Bofu Jin等;《2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education (ICISCAE)》;20201029;第1-8页 *
计及需求响应的主动配电网短期负荷预测;苏小林等;《电力系统自动化》;20180525;第42卷(第10期);第60-67页 *

Also Published As

Publication number Publication date
CN115000999A (en) 2022-09-02

Similar Documents

Publication Publication Date Title
Mirzapour et al. A new prediction model of battery and wind-solar output in hybrid power system
Hu et al. A review of second-life lithium-ion batteries for stationary energy storage applications
CN112103946A (en) Particle swarm algorithm-based microgrid energy storage optimization configuration method
CN112488362A (en) Energy storage optimization configuration method for coordinating electric automobile to participate in auxiliary service market
WO2012002001A1 (en) Power control method, program, and power control device
CN106384175B (en) A kind of electric car real-time control method based on schedulable ability
CN111626527B (en) Intelligent power grid deep learning scheduling method considering fast/slow charging/discharging form of schedulable electric vehicle
CN109948823B (en) Self-adaptive robust day-ahead optimization scheduling method for light storage charging tower
CN113193553B (en) New energy power generation side power prediction method and system combining energy storage control system
CN109086928A (en) Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model
CN107590607A (en) A kind of micro-capacitance sensor Optimal Scheduling and method based on photovoltaic prediction
CN116151486B (en) Multi-time-scale random optimization method and device for photovoltaic charging station with energy storage system
Kasturi et al. Optimal planning of charging station for EVs with PV-BES unit in distribution system using WOA
CN111553750A (en) Energy storage bidding strategy method considering power price uncertainty and loss cost
CN110852495A (en) Site selection method for distributed energy storage power station
CN115000999B (en) Day-ahead response capability assessment method for electric automobile
CN114640133B (en) Urban power grid electric automobile cooperative regulation and control method and system based on real-time information
CN115545429A (en) Multi-scene low-voltage renewable resource load prediction method based on CPSS framework
CN116054286A (en) Residential area capacity optimal configuration method considering multiple elastic resources
Huang et al. Power prediction method of distributed photovoltaic digital twin system based on GA-BP
CN113052450B (en) Urban energy Internet planning method suitable for electric energy substitution development strategy
Engel Sizing of a photovoltaic system with battery on the basis of the multi-agent adaptive fuzzy neuronet
Tian et al. Analysis method of the influence of electric bus optimal charging on the renewable energy power consumption
Nguyen et al. Complementary grid power prediction using artificial neural network in the energy management system of a disaster prevention smart solar microgrid
CN117578533B (en) Electro-hydrogen fusion collaborative optimization configuration method oriented to electro-hydrogen supply capability improvement

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