CN115018379B - Electric vehicle in-day response capability assessment method and system and computer storage medium - Google Patents
Electric vehicle in-day response capability assessment method and system and computer storage medium Download PDFInfo
- Publication number
- CN115018379B CN115018379B CN202210842200.6A CN202210842200A CN115018379B CN 115018379 B CN115018379 B CN 115018379B CN 202210842200 A CN202210842200 A CN 202210842200A CN 115018379 B CN115018379 B CN 115018379B
- Authority
- CN
- China
- Prior art keywords
- charging
- electric vehicle
- power
- electric
- lstm
- 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
Links
- 230000004044 response Effects 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000007599 discharging Methods 0.000 claims abstract description 57
- 238000013210 evaluation model Methods 0.000 claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000015654 memory Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 230000004043 responsiveness Effects 0.000 claims 3
- 239000000126 substance Substances 0.000 claims 1
- 229910052799 carbon Inorganic materials 0.000 abstract description 7
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 abstract description 6
- 238000009472 formulation Methods 0.000 abstract description 4
- 239000000203 mixture Substances 0.000 abstract description 4
- 238000006386 neutralization reaction Methods 0.000 abstract description 3
- 239000011159 matrix material Substances 0.000 description 8
- 210000004027 cell Anatomy 0.000 description 6
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
-
- 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
-
- 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
-
- 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
- Y02T10/7072—Electromobility specific charging systems or methods for batteries, ultracapacitors, supercapacitors or double-layer capacitors
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Power Engineering (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
Abstract
The invention discloses a method and a system for evaluating day-in response capability of an electric automobile and a computer storage medium, wherein the evaluation method comprises the steps of constructing an electric automobile charging capacity limit evaluation model; constructing a dynamic charging and discharging power evaluation model of the electric automobile, and determining upper and lower limits of charging and discharging power of the electric automobile; constructing an electric vehicle charging quantity prediction model based on the LSTM, and predicting the quantity of electric vehicles which can be used for charging and discharging; constructing a charging power evaluation model of the electric vehicle charging station; and (4) carrying out loop iteration to realize the evaluation of the day response capability of the electric automobile. The method can master the daily response capability of the electric automobile, correct the daily operation plan of the supporting power grid, improve the formulation quality of the power grid operation plan, improve the stable operation level of the power grid, and assist the power grid to realize the goals of carbon peak reaching and carbon neutralization as soon as possible.
Description
Technical Field
The invention discloses a method and a system for evaluating day-to-day response capability of an electric automobile and a computer storage medium, and belongs to the field of power systems.
Background
With the gradual increase of the proportion of low-carbon clean energy accessed into a power grid in the future, the new energy has the characteristics of high volatility, strong uncertainty and poor controllability, and compared with the traditional stable thermal power with good controllability, the new energy brings higher operation risk to the power grid and brings more threat to the stable operation of the power grid. The traditional power grid power regulation mainly depends on thermal power and hydropower, the thermal power proportion is gradually reduced in the future, load resources which can participate in regulation in the power grid are insufficient, the regulation resources on the load side of the power grid are urgently needed to be excavated, the power grid is participated in operation, the response capability in the day is excavated, and support is provided for the power grid to correct the operation plan in the day.
Disclosure of Invention
The invention provides an electric vehicle daily response capacity evaluation method, an electric vehicle daily response capacity evaluation system and a computer storage medium, and aims to fully excavate electric vehicle daily response capacity, master daily power upper and lower limit values, support power grid daily operation plan modification, improve power grid operation plan formulation level and boost a power grid to achieve power grid carbon peak reaching and carbon neutralization targets early.
In order to achieve the purpose, the invention provides the following technical scheme:
an LSTM-based electric vehicle in-day response capability assessment method comprises the following steps:
(1) Constructing an electric automobile charging capacity limit evaluation model based on t 0 Time of day data, determining t 0 At the moment of + delta t, the limit value of the charging capacity of the electric automobile in a charging, discharging and idle state;
(2) Constructing a dynamic charge-discharge power evaluation model of the electric automobile based on the t 0 Determining t according to charging capacity limit value of the electric automobile in charging, discharging and idle states at + delta t moment 0 The upper and lower limits of the charging and discharging power of the electric automobile at the + delta t moment;
(3) Constructing an electric vehicle charging quantity prediction model based on LSTM, and based on t 0 Time data, prediction t 0 The number of electric vehicles which can be used for charging and discharging at the + delta t moment;
(4) Constructing a charging power evaluation model of the electric vehicle charging station;
(5) Setting Δ t based on t 0 Time data, prediction t 0 + Δ t electromotiveVehicle response capability, based on t 0 Data at time + k Δ t, predicted t 0 And (5) evaluating the response capability of the electric automobile within the day by means of +/-k +1 delta t electric automobile response capability and circular iteration.
In the step (1), the step of constructing the electric vehicle charging capacity limit evaluation model comprises the following steps:
based on t 0 Time of day data, t is determined by equation (1) 0 At the moment of + delta t, the limit value of the charging capacity of the electric automobile in a charging, discharging and idle state;
in the formula: s. the ji (t 0 + Δ t) is t 0 Charging station j ith electric vehicle charging capacity limit value at + delta t moment; s. the ji (t 0 ) Is t 0 The charging capacity limit value of the ith electric vehicle at the charging station j at the moment,
charging and discharging efficiencies of the electric vehicle i respectively at t 0 Acquiring at any moment; d ji The battery capacity of the ith electric vehicle is the charging station j; />
I-th electric vehicle respectively being charging station j at t 0 The charging power and the discharging power value at the moment are acquired at the moment; delta ji (t 0 )＝0、δ ji (t 0 )＝1、δ ji (t 0 ) =2 ith electric vehicle representing charging station j at t 0 The time is in an idle state, a charging state and a discharging state.
In the step (2), the step of constructing the dynamic charge-discharge power evaluation model of the electric automobile comprises the following steps:
historical charging capacity limit data S of electric automobile ji (t) and charge and discharge power data at corresponding time
Constructing charging and discharging power of the electric automobile related to S through an LSTM long-short term memory network algorithm ji (t) prediction model>
Based on the found t 0 Obtaining t through a formula (5) by using the charging capacity limit value of the electric automobile at the moment of + delta t 0 The charging and discharging power of the electric automobile at + delta t moment;
f 1 () Model for electric vehicle quantity charging power LSTM prediction, f 2 () The discharge power LSTM prediction model is an electric vehicle quantity discharge power LSTM prediction model.
In the step (2), the evaluation t is determined 0 The upper and lower limits of the charging and discharging power of the electric automobile at + delta t moment:
in the formula:
the charging power upper limit value and the charging power lower limit value are respectively the ith electric vehicle charging power of the charging station j; s. the ji (t 0 + Δ t) is t 0 Charging station j ith electric vehicle charging capacity limit value at + delta t moment; />
A charging capacity threshold value of the ith electric vehicle for the charging station j; />
The charging end leaving time of the ith electric vehicle of the power station j can be t 0 Is collected at all times and is combined with>
Time required for forced charging of the ith electric vehicle according to the charging station j; />
Are each t 0 And the charging and discharging power of the electric automobile at the moment of + delta t.
The time required for the forced charging of the ith electric vehicle according to the charging station j
By the formula
Is obtained in which
Is t 0 And charging power of the ith electric vehicle of the charging station j at the moment.
In the step (3), an electric vehicle charging quantity prediction model based on the LSTM is constructed:
predicting t based on the number of electric vehicles in the charging state and the discharging state and the traffic index 0 The number of electric vehicles which can be used for charging and discharging at the moment of + delta t;
in the formula: f. of 3 () For the number of electric vehicles in the charging state LSTM prediction model, f 4 () For the LSTM prediction model of the number of electric vehicles in a discharge state,
the number of the electric vehicles which are in the charging state and the discharging state historically is determined respectively>
Are respectively preMeasure t 0 The number of electric vehicles available for charging and discharging at time + Δ t, JT t The traffic indexes of different time of day.
The electric vehicle charging quantity prediction model based on the LSTM trains an LSTM deep learning network based on input sample data and cell state information, and the training process is shown as a formula (7):
in the formula, sigma is an activation function; f. of t For forgetting the output of the gate, W f 、b f Is a corresponding forgetting gate matrix; i.e. i t For the output of the input gate, W i 、b i Is the corresponding input gate weight matrix; c t-1 As information on the state of the old cells,
to select to add candidate status information, C t For updated cell information, W C 、b C Is a corresponding neuron matrix; o is t To output the output of the gate, W o 、b o Is a corresponding matrix of output gates; h is t To output the result.
In the step (4), a charging power evaluation model of the electric vehicle charging station is constructed as shown in formulas (8) to (9):
in the formula:
are charging station j charging power upper and lower limit values, N 'respectively' 1 、N′ 2 、N′ 3 Respectively for the initial charging stationThe number of the charged, discharged and forcibly charged electric vehicles is greater or less>
The number of the electric vehicles which are newly connected into the charging station for charging and discharging in the time period delta t respectively, and the number of the electric vehicles which are charged and discharged is greater or less>
Is t 0 The average charging power of the electric automobile is judged at the moment>
Is t 0 The average discharge power of the electric automobile is judged at the moment>
Forced charging power for electric vehicle>
The charging end leaving time of the ith electric vehicle of the power station j can be t 0 Is collected at all times and is combined with>
Time required for forced charging of the ith electric vehicle according to the charging station j.
An LSTM-based electric vehicle in-day response capability assessment system, comprising: a network interface, a memory, and a processor; wherein, the first and the second end of the pipe are connected with each other,
the network interface is used for receiving and sending signals in the process of receiving and sending information with other external network elements;
the memory for storing a computer program operable on the processor;
the processor is used for executing the steps of the LSTM-based electric vehicle in-day response capability evaluation method when the computer program is run.
A computer storage medium, wherein the computer storage medium stores a program for LSTM-based intra-day response capability assessment of an electric vehicle, and the program for LSTM-based intra-day response capability assessment of an electric vehicle implements the steps of the LSTM-based intra-day response capability assessment method when executed by at least one processor.
The invention has the technical effects and advantages that: by utilizing the LSTM, the daily response capability of the electric automobile is fully excavated, the daily power upper and lower limit values of the electric automobile are mastered, the daily operation plan correction of the power grid is supported, the power grid operation plan formulation level is improved, and the power grid is assisted to realize the targets of power grid carbon peak reaching and carbon neutralization as soon as possible. By evaluating the day response capability of the electric automobile, support is provided for day operation plan modification, the power grid operation plan formulation quality is improved, the stable operation level of the power grid is improved, the controllability of power resources is improved, and the guarantee of saving and using the power resources is provided.
Drawings
FIG. 1 is a schematic view of a charge-discharge power curve of a single-body electric vehicle in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a model for predicting the charging and discharging quantity of an electric vehicle based on LSTM in the embodiment of the invention;
FIG. 3 is a schematic flow chart 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.
Referring to fig. 3, the LSTM-based method for evaluating the daytime response capability of an electric vehicle includes the following steps:
(1) Constructing an electric automobile charging capacity limit evaluation model based on t 0 Time of day data, determining t 0 At the time of + Δ t, the electric vehicle is at the charge capacity limit value in the charge, discharge, and idle states.
In the step (1), a model for evaluating the charge capacity limit of the electric automobile is constructed asAs shown in formula (1), because the charging and discharging instructions of the electric vehicle by the power grid in the delta t time period are unknown, the charging and discharging state of the electric vehicle is unknown, and the charging and discharging state is based on the current moment t 0 Data, evaluating the next time t 0 + Δ t electric vehicle charge capacity limit.
In the formula: s ji (t 0 + Δ t) is t 0 Charging station j ith electric vehicle SOC limit at time + Δ t. S. the ji (t 0 ) Is t 0 Charging station j at the moment, the SOC value of the ith electric vehicle,
charging and discharging efficiencies of the electric vehicle i respectively at t 0 And acquiring the time. D ji The battery capacity of the ith electric vehicle at the charging station j is given by a battery manufacturer and is a fixed value. />
The ith electric vehicle is at t 0 Charging power and discharging power at time t 0 And acquiring the time. Delta ji (t 0 )＝0、δ ji (t 0 )＝1、δ ji (t 0 ) =2 indicates that the ith electric vehicle of the charging station j is at t 0 The time is in an idle state, a charging state and a discharging state.
(2) Constructing a dynamic charge-discharge power evaluation model of the electric automobile based on the t 0 Determining t according to charging capacity limit value of the electric automobile in charging, discharging and idle states at + delta t moment 0 The upper and lower limits of the charging and discharging power of the electric automobile at the + delta t moment;
in the step (2), the constructed dynamic charge-discharge power evaluation model of the electric automobile is shown in formulas (2) - (3).
In the formula:
and the charging power upper and lower limit values are respectively the ith electric vehicle charging power of the charging station j. S ji (t 0 + Δ t) is t 0 Charging station j ith electric vehicle SOC limit at time + Δ t. />
And the charging capacity threshold value of the ith electric vehicle is the charging station j. />
The charging end leaving time of the ith electric vehicle of the power station j can be t 0 Is collected at all times and is combined with>
The time required for forced charging of the ith electric vehicle according to the charging station j can be calculated by the formula (4).
Are each t 0 The calculation process of the charging and discharging power of the electric automobile at the + delta t moment is shown as the formula (5).
The SOC values at any time are different, and the charging and discharging power values of the electric automobile are different. Based on historical SOC data S of electric vehicle ji (t) and charge and discharge power data at corresponding time
Constructing the relation between the charging and discharging power of the electric automobile and the S by means of LSTM (Long Short-Term Memory, LSTM) Long-Short Term Memory network algorithm ji (t) as shown in equation (5). Based on the found t 0 At time + Δ t, the SOC limit value of the electric vehicle can be calculated by equation (5) to obtain t 0 And the charging and discharging power of the electric automobile at the moment of + delta t. f. of 1 () LSTM prediction model of charging power for electric vehicle quantity, f 2 () The discharge power LSTM prediction model is an electric vehicle quantity discharge power LSTM prediction model.
(3) Constructing an electric vehicle charging quantity prediction model based on LSTM, and based on current time t 0 Data, predicting the next time t 0 + Δ t may be used for the number of electric vehicles that are charged and discharged.
In the step (3), an LSTM-based electric vehicle charging quantity prediction model is constructed as shown in a formula (6).
Predicting t mainly based on the number of electric vehicles in a charging state and a discharging state and traffic indexes 0 The number of electric vehicles available for charging and discharging at the time of + Δ t.
The training process of the model is shown in fig. 2, and the LSTM deep learning network is trained based on input sample data and cell state information, and the training process is shown in formula (7).
In the formula: f. of 3 () Number of electric vehicles LST in charging StateM prediction model, f 4 () For the LSTM prediction model of the number of electric vehicles in a discharge state,
the number of the electric vehicles in the charging state and the discharging state in the history is respectively. />
Are predicted t respectively 0 The number of electric vehicles available for charging and discharging at time + Δ t, JT t The traffic indexes of different time of day.
Wherein σ is an activation function; f. of t For forgetting the output of the gate, W f 、b f Is a corresponding forgetting gate matrix; i.e. i t To the output of the input gate, W i 、b i Is the corresponding input gate weight matrix; c t-1 Is the information of the state of old cells,
to choose to add candidate status information, C t For updated cell information, W c 、b c Is a corresponding neuron matrix; o is t To output the output of the gate, W o 、b o Is a corresponding output gate matrix; h is t Is the output result.
(4) And constructing a charging power evaluation model of the electric vehicle charging station. Based on t 0 Upper and lower limits of charging and discharging power of the electric automobile at + delta t moment, predicted t 0 The quantity of the electric vehicles which can be used for charging and discharging at the moment of + delta t, a model is constructed, and t is evaluated 0 And the charging power upper and lower limits of the electric vehicle charging station at the moment of + delta t.
In the step (4), the constructed electric vehicle charging station charging power evaluation model is shown in formulas (8) - (9).
In the formula:
are charging station j charging power upper and lower limit values, N 'respectively' 1 、N’ 2 、N’ 3 The number of the electric vehicles which can be charged, discharged and forcibly charged on the original charging station is respectively. />
The number of the electric vehicles which can be charged and discharged by newly connecting to the charging station in the delta t time period is respectively. />
Is t 0 And (4) average charging power of the electric automobile at the moment. />
Is t 0 And (4) average electric vehicle discharge power at the moment. />
And forcibly charging power for the electric automobile. />
The charging end leaving time of the ith electric vehicle of the power station j can be t 0 Is collected at moment and is judged>
The time required for forced charging of the ith electric vehicle according to the charging station j can be calculated by the formula (4).
(5) Evaluating day-to-day response capability of electric vehicle charging station by setting delta t based on t 0 Time of day data prediction t 0 + Δ t electric vehicle response capability based on t 0 Data prediction t at time + k Δ t 0 The response capability of the electric automobile with the value of + (k + 1) delta t is subjected to loop iteration, the response capability of the electric automobile charging station with different time scales (15 min, 1h, 2h \8230; 8230; etc.) in the future can be predicted according to the prediction requirement, and the day-by-day response capability of the electric automobile can be evaluated.
In one embodiment, an LSTM-based electric vehicle in-day response capability assessment system implements the above steps, the system comprising a network interface, a memory and a processor; the network interface realizes the receiving and sending of signals; a memory for storing a computer program operable on the processor; the processor is used for executing the steps of the LSTM-based electric vehicle in-day response capability assessment method when the computer program is run.
In one embodiment, a computer storage medium stores a program for LSTM-based in-day response capability assessment of an electric vehicle. The program of the LSTM-based electric vehicle day response capability evaluation method is executed by at least one processor to realize the steps of the LSTM-based electric vehicle day response capability evaluation method.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (9)
1. An LSTM-based electric vehicle in-day response capability assessment method is characterized by comprising the following steps:
(1) Constructing an electric automobile charging capacity limit evaluation model based on t 0 Time of day data, determining t 0 Charging capacity pole of electric automobile in charging, discharging and idle states at + delta t momentA limit value;
(2) Constructing a dynamic charge-discharge power evaluation model of the electric automobile based on the t 0 Determining t according to the limit value of the charging capacity of the electric automobile in the charging, discharging and idle states at the moment of + delta t 0 The upper and lower limits of the charging and discharging power of the electric automobile at + delta t moment;
(3) Constructing an electric vehicle charging quantity prediction model based on LSTM, and based on t 0 Time data, prediction t 0 The number of electric vehicles which can be used for charging and discharging at the moment of + delta t;
(4) Constructing a charging power evaluation model of the electric vehicle charging station;
(5) Setting Δ t based on t 0 Time data, electric vehicle charging station charging power evaluation model based prediction t 0 + Delta t electric vehicle response capability based on t 0 Data at time + k Δ t, predicted t 0 And (k + 1) delta t electric vehicle response capability, wherein k is iteration times, and the evaluation of the electric vehicle response capability in the day is realized through loop iteration.
2. The LSTM-based electric vehicle in-day response capability assessment method of claim 1, wherein in step (1), constructing the electric vehicle charge capacity limit assessment model comprises:
based on t 0 Time of day data, t is determined by equation (1) 0 At the moment of + delta t, the limit value of the charging capacity of the electric automobile in a charging, discharging and idle state;
in the formula: s ji (t 0 + Δ t) is t 0 Charging station j ith electric vehicle charging capacity limit value at + delta t moment; s ji (t 0 ) Is t 0 The charging capacity limit value of the ith electric vehicle at the charging station j at the moment,
are respectively electric vehiclesi charge and discharge efficiency at t 0 Acquiring time; d ji The battery capacity of the ith electric vehicle is the charging station j; />
I-th electric vehicle respectively being charging station j at t 0 Charging power and discharging power at time t 0 Acquiring time; delta ji (t)＝0、δ ji (t 0 )＝1、δ ji (t 0 ) =2 ith electric vehicle representing charging station j at t 0 The time is in an idle state, a charging state and a discharging state.
3. The LSTM-based electric vehicle in-day response capability assessment method of claim 1, wherein in step (2), constructing the electric vehicle dynamic charging and discharging power assessment model comprises:
historical charging capacity limit data S of electric automobile ji (t) and charge and discharge power data at corresponding time
Constructing charging and discharging power of the electric automobile related to S through an LSTM long-short term memory network algorithm ji (t) prediction model
Based on the found t 0 Obtaining t through a formula (5) by using the charging capacity limit value of the electric automobile at the moment of + delta t 0 The charging and discharging power of the electric automobile at + delta t moment;
f 1 () Model for electric vehicle quantity charging power LSTM prediction, f 2 () The discharge power LSTM prediction model is an electric vehicle quantity discharge power LSTM prediction model.
4. According to the claimThe method of claim 3, wherein in step (2), the evaluation t is determined 0 The upper and lower limits of the charging and discharging power of the electric automobile at the + delta t moment:
in the formula:
the charging power upper limit value and the charging power lower limit value are respectively the ith electric vehicle charging power of the charging station j; s ji (t 0 + Δ t) is t 0 Charging station j ith electric vehicle charging capacity limit value at + delta t moment; />
The charging capacity threshold value of the ith electric vehicle is a charging station j; />
The charging end leaving time of the ith electric vehicle of the power station j can be t 0 Is collected at all times and is combined with>
Time required for forced charging of the ith electric vehicle according to the charging station j; />
Are each t 0 And the charging and discharging power of the electric automobile at the moment of + delta t.
5. The LSTM-based electric vehicle in-day response capability assessment method according to claim 4, wherein the ith electric vehicle according to charging station jTime required for forced charging of automobile
By the formula
Is obtained in which
Is t 0 And charging power of the ith electric vehicle of the charging station j at the moment.
6. The LSTM-based electric vehicle in-day response capability assessment method according to claim 1, wherein in step (3), an LSTM-based electric vehicle charging quantity prediction model is constructed:
predicting t based on the number of electric vehicles in the charging state and the discharging state and the traffic index 0 The number of electric vehicles which can be used for charging and discharging at the + delta t moment;
in the formula: f. of 3 () Number of electric vehicles in charge LSTM prediction model, f 4 () For the LSTM prediction model of the number of electric vehicles in a discharge state,
the number of the electric vehicles which are in the charging state and the discharging state historically is determined respectively>
Are predicted t respectively 0 Number of electric vehicles available for charging and discharging at time + Δ t, JT t The traffic indexes are traffic indexes at different times in the day.
7. The LSTM-based electric vehicle in-day responsiveness assessment method according to claim 1, wherein in step (4), an electric vehicle charging station charging power assessment model is constructed as shown in equations (8) - (9):
in the formula:
are charging station j charging power upper and lower limit values, N 'respectively' 1 、N′ 2 、N′ 3 The number and the pressure of the electric vehicles which are respectively charged, discharged and forcibly charged on the initial charging station are judged>
The number of the electric vehicles which are newly connected into the charging station for charging and discharging in the time period delta t respectively, and the number of the electric vehicles which are charged and discharged is greater or less>
Is t 0 The average charging power of the electric automobile is judged at the moment>
Is t 0 The average discharge power of the electric automobile is judged at the moment>
The forced charging power is supplied to the electric automobile,
the charging end leaving time of the ith electric vehicle of the power station j can be t 0 Is collected at moment and is judged>
Time required for forced charging of the ith electric vehicle according to the charging station j.
8. LSTM-based electric vehicle intraday response capability evaluation system, characterized in that the evaluation system comprises: a network interface, a memory, and a processor; wherein the content of the first and second substances,
the network interface is used for receiving and sending signals in the process of receiving and sending information with other external network elements;
the memory for storing a computer program operable on the processor;
the processor, when executing the computer program, is configured to execute the steps of the LSTM-based electric vehicle in-day response capability assessment method according to any of claims 1 to 7.
9. A computer storage medium, characterized in that the computer storage medium stores a program for LSTM-based daily responsiveness assessment of an electric vehicle, which when executed by at least one processor implements the steps of the LSTM-based daily responsiveness assessment method of an electric vehicle according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210842200.6A CN115018379B (en) | 2022-07-18 | 2022-07-18 | Electric vehicle in-day response capability assessment method and system and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210842200.6A CN115018379B (en) | 2022-07-18 | 2022-07-18 | Electric vehicle in-day response capability assessment method and system and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115018379A CN115018379A (en) | 2022-09-06 |
| CN115018379B true CN115018379B (en) | 2023-04-07 |
Family
ID=83081470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210842200.6A Active CN115018379B (en) | 2022-07-18 | 2022-07-18 | Electric vehicle in-day response capability assessment method and system and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115018379B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011156776A2 (en) * | 2010-06-10 | 2011-12-15 | The Regents Of The University Of California | Smart electric vehicle (ev) charging and grid integration apparatus and methods |
| JP2019113998A (en) * | 2017-12-22 | 2019-07-11 | ダイムラー・アクチェンゲゼルシャフトＤａｉｍｌｅｒ ＡＧ | Power feeding vehicle operation management system |
| CN111211564B (en) * | 2020-01-17 | 2021-06-04 | 南京东博智慧能源研究院有限公司 | Demand response method considering electric vehicle charging load space-time distribution |
| CN112734077A (en) * | 2020-11-30 | 2021-04-30 | 中国电力科学研究院有限公司 | Day-ahead optimized operation method and system for electric vehicle charging station |
| CN113829934B (en) * | 2021-10-22 | 2023-03-21 | 华北电力大学 | Electric vehicle cluster aggregation response capacity determining method and scheduling method |
-
2022
- 2022-07-18 CN CN202210842200.6A patent/CN115018379B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115018379A (en) | 2022-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105024432B (en) | A kind of electric automobile discharge and recharge Optimization Scheduling based on virtual electricity price | |
| WO2022253038A1 (en) | Method and system for predicting state of health of lithium battery on basis of elastic network, and device and medium | |
| CN105680474B (en) | Control method for restraining rapid power change of photovoltaic power station through energy storage | |
| CN112488362A (en) | Energy storage optimization configuration method for coordinating electric automobile to participate in auxiliary service market | |
| CN111555355A (en) | Scheduling strategy and optimization method for water-light-storage combined power generation | |
| CN104698382A (en) | Method for predicting the SOC and SOH of battery pack | |
| CN113128672B (en) | Lithium ion battery pack SOH estimation method based on transfer learning algorithm | |
| CN111626527A (en) | Intelligent power grid deep learning scheduling method considering fast/slow charging/discharging form of schedulable electric vehicle | |
| CN111555347A (en) | Wind power prediction-based wind storage combined operation control method | |
| CN111244991A (en) | Energy storage power station operation control method and system considering battery life | |
| CN114819373A (en) | Energy storage planning method for sharing hybrid energy storage power station based on cooperative game | |
| CN117031310A (en) | Method for predicting residual service life of power battery of electric automobile | |
| CN112670999A (en) | Low-voltage distribution network real-time voltage control method based on user-side flexible resources | |
| CN115021295A (en) | Wind power plant hybrid energy storage capacity optimal configuration method and system for primary frequency modulation | |
| CN115308608A (en) | All-vanadium redox flow battery voltage prediction method, device and medium | |
| CN113011101B (en) | Control method and system for energy storage to participate in frequency modulation auxiliary service optimization | |
| CN116706963B (en) | Large-scale electric vehicle V2G scheduling method based on regional power load prediction | |
| CN115018379B (en) | Electric vehicle in-day response capability assessment method and system and computer storage medium | |
| CN113255205A (en) | Life cycle cost and battery temperature optimization method based on electric vehicle battery | |
| CN115764855A (en) | Real-time adjustable capacity and available electric quantity prediction method for electric vehicle quick charging station | |
| CN111740442B (en) | Retired battery echelon utilization control method applied to optical storage charging station | |
| CN115236526A (en) | Method and device for predicting residual charging time, storage medium and vehicle | |
| CN108183498B (en) | Vehicle storage hybrid configuration method under background of wind and light containing storage and distribution power grid | |
| Lian et al. | Real‐time energy management strategy for fuel cell plug‐in hybrid electric bus using short‐term power smoothing prediction and distance adaptive state‐of‐charge consumption | |
| CN117728465A (en) | Energy storage power station operation control method and device considering battery life cycle |
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 |