CN113675866B - Dynamic gridding pyramid scheduling method for large-scale electric automobile - Google Patents
Dynamic gridding pyramid scheduling method for large-scale electric automobile Download PDFInfo
- Publication number
- CN113675866B CN113675866B CN202010414980.5A CN202010414980A CN113675866B CN 113675866 B CN113675866 B CN 113675866B CN 202010414980 A CN202010414980 A CN 202010414980A CN 113675866 B CN113675866 B CN 113675866B
- Authority
- CN
- China
- Prior art keywords
- electric automobile
- electric
- scheduling
- dispatching
- electric vehicle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000006399 behavior Effects 0.000 claims abstract description 45
- 238000005457 optimization Methods 0.000 claims abstract description 25
- 238000009826 distribution Methods 0.000 claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 230000000306 recurrent effect Effects 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000004146 energy storage Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000007599 discharging Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000006386 memory function Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000003860 storage Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 4
- 230000002354 daily effect Effects 0.000 description 4
- 238000005096 rolling process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- 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
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Power Engineering (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Educational Administration (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a dynamic gridding pyramid scheduling method for a large-scale electric automobile, and belongs to the field of intelligent power distribution networks. According to the invention, the bottom-up transmission of the electric vehicle information and the top-down release of an optimal scheduling scheme are realized, the recurrent neural network with short-time memory is adopted to predict the electric vehicle user behavior according to the historical continuity of the electric vehicle behavior, the electric vehicle with similar behavior is divided into grid units by utilizing the grid-based multi-resolution clustering technology on the basis of a prediction result, a high-capacity distributed schedulable storage battery is formed, and in a scheduling stage, a multi-objective optimization model for maximizing user satisfaction and minimizing power distribution network load fluctuation is established so as to balance the competition relationship between the user travel demand and power distribution network side scheduling, and the economic operation level of a power grid and the participation degree and satisfaction degree of electric vehicle users are improved.
Description
Technical Field
The invention relates to a dispatching method of a large-scale electric automobile, in particular to a dynamic gridding pyramid dispatching method of the large-scale electric automobile, and belongs to the technical field of intelligent power grids.
Background
With the continuous development of global economy and the gradual exhaustion of fossil fuels, energy shortage and environmental pollution have become the problems to be solved in countries around the world. The electric automobile has incomparable advantages in the aspects of energy conservation, emission reduction, climate warming restraint, petroleum supply guarantee and the like. However, the strong randomness of the electric automobile users brings significant uncertainty to the operation and control of the electric power system, and even the loss and voltage level of the power distribution network can be influenced, so that the problems of local overload of the load, power quality of the power distribution network and the like are caused. The large-scale electric automobile dispatching technology can positively exert the function of the electric automobile as distributed energy storage by reasonably guiding the access time of the automobile on the premise of meeting the daily use vehicle of a user, and reduces the negative influence of the electric automobile on the safety and economic operation of an electric power system. Therefore, along with the increasing of the electric automobile scale, how to realize reasonable dispatching of large-scale electric automobiles on the premise of ensuring user satisfaction and power distribution network operation requirements is a problem which needs to be solved in the field of intelligent power grids at present.
The optimal scheduling method of the electric automobile mainly comprises centralized control scheduling, rolling type optimal scheduling, layered distributed scheduling and the like. The centralized dispatching is a direct dispatching mode by a dispatching mechanism of the power transmission system, so that a global optimal solution of dispatching problems can be ensured theoretically, but as the quantity of electric vehicles is increased, dimension disasters occur to the centralized dispatching optimization problems, extremely high requirements are put on the communication reliability and bandwidth between the dispatching mechanism and each vehicle, and the centralized dispatching can not be effectively implemented in a large-scale power system under the prior art condition. The rolling optimization scheduling strategy is used for scheduling and managing the real-time charging power of the electric automobile in a rolling optimization mode aiming at the controllability of the electric automobile. The method has better robustness on the prediction error, but still suffers from the disaster of calculating dimension, by acquiring the latest state of the network-access electric vehicle at each moment and performing prospective optimization and issuing the charging optimization result at the next moment to each network-access vehicle. In order to solve the dimension disasters and solving difficulties generated by centralized dispatching, a hierarchical dispatching method has the core ideas that a power system is divided into two or more layers according to voltage levels, then the layers representing a power distribution system are further divided into a plurality of areas according to regions, and the power distribution system or a third party electric automobile agent takes charge of electric automobile dispatching in the areas.
The large-scale electric automobile dispatching needs to take basic information and historical behavior records of the electric automobile as basic data to carry out optimization decision, and a common method is to enable electric automobile users to upload required data every day (or every N hours), so that inconvenience of the users in using the electric automobile is increased, protection of privacy of the users is omitted, and how to guarantee experience and income of the electric automobile users is worth deeply thinking. Therefore, in order to ensure the participation of the electric vehicle users and the safe and stable operation of the power grid, it is necessary to combine the advanced intelligent computing technology to perform predictive analysis on the user behavior mode and balance the competition relationship between the electric vehicle users and the operation of the electric power system in the optimization process, which has important significance for maximizing the positive influence of the large-scale electric vehicle on the operation of the power grid and the economic operation, reducing the emission of greenhouse gases, slowing down the exhaustion speed of fossil energy and the like.
Disclosure of Invention
The invention aims to provide a dynamic gridding pyramid scheduling method for a large-scale electric automobile, which adopts electric automobile behavior prediction and multi-objective optimization to improve the participation degree and satisfaction degree of users. The pyramid-based electric automobile scheduling model comprises a four-layer structure, wherein a recurrent neural network (Recurrent Neural Network, RNN) is applied to establish an electric automobile behavior prediction model to describe the space-time distribution of the electric automobile behavior; secondly, dividing an electric vehicle gridding cluster according to a behavior prediction result, and dynamically adjusting grids according to the behavior change of the electric vehicle; and finally, establishing a multi-objective optimization model for electric vehicle dispatching, balancing benefits of electric vehicle customers and a power distribution system, and realizing optimized dispatching of large-scale electric vehicles so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a dynamic gridding pyramid scheduling method for a large-scale electric automobile comprises four aspects of pyramid scheduling frame model, electric automobile user behavior prediction, electric automobile cluster grid dynamic division and multi-target optimization scheduling, wherein:
the pyramid scheduling frame model comprises a 4-layer structure, and the whole scheduling process of the electric automobile is as follows: the electric automobile information adopts a bottom-up transmission mode, namely the information of the electric automobile is from the bottom layer to the upper layer of the pyramid. Then, a prediction model is applied to track and predict the behavior of the electric vehicle in the next scheduling period. And dividing the electric vehicles with similar behavior trends into dynamic clusters to form high-capacity distributed energy storage units, performing multi-objective optimization solution to obtain an optimal scheduling strategy, and finally sending back to each electric vehicle in a top-down mode.
And the electric automobile user behavior prediction is carried out, and a prediction model is established by adopting RNN according to the continuity of the electric automobile behavior. During the training of the recurrent neural network, the daily record of the electric automobile, such as battery capacity, charging position, starting charging time, daily driving mileage, expected battery State of charge (SOC), travel requirement and the like, are taken as input samples, the learning parameters of the RNN are solved by utilizing a back propagation algorithm, and finally the schedulable place, time and capacity information of the electric automobile are output to be taken as the behavior prediction result of the electric automobile user.
According to the electric automobile grid cluster dynamic division, electric automobiles with similar behaviors are divided into different grid clusters according to the behavior prediction results of electric automobile users, so that all electric automobiles in the same grid can be uniformly scheduled. In consideration of stronger randomness of the user behavior of the electric automobile, when errors exist between the prediction result and the actual behavior, the clusters are dynamically adjusted, and the influence of the errors on subsequent optimization calculation is reduced.
The multi-objective optimal scheduling of the electric automobile aims at maximizing user satisfaction and minimizing load fluctuation of a power distribution system, a multi-objective optimal model is established, and an NSGA-II algorithm is adopted for solving, so that an optimal scheduling scheme for balancing electric automobile users and an electric power system is obtained.
Compared with the prior art, the invention has the beneficial effects that: the electric automobile optimization scheduling method takes the prediction of user behaviors and multi-objective optimization as cores, and can be applied to network access scheduling of large-scale electric automobiles. According to the method, complicated labor of users in the process of participating in electric automobile dispatching can be reduced through recurrent learning of the neural network, and the user participation degree and income are improved while the stable operation of the power grid is ensured.
Drawings
Fig. 1 is a pyramid frame of a large-scale electric vehicle dispatch of the present invention;
FIG. 2 is a schematic diagram of a recurrent neural network of the present invention;
fig. 3 is a flow chart of the electric automobile dispatching.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
According to the invention, a user behavior prediction link is added in the electric vehicle dispatching, so that a user is released from the tedious daily electric vehicle information reporting work; meanwhile, satisfaction analysis on user travel and benefits is increased in an optimal scheduling stage, participation and satisfaction of electric automobile users are comprehensively improved, and effective implementation of clustered electric automobile scheduling is guaranteed. The dynamic gridding pyramid scheduling method of the large-scale electric automobile can be divided into the following four steps:
step one: pyramid scheduling architecture for establishing electric automobile
The pyramid scheduling model architecture of the large-scale electric automobile comprises four layers (as shown in fig. 1), wherein the four layers are respectively as follows: the electric vehicle comprises an electric vehicle local response layer, a cluster grid dividing layer, an optimization calculation layer and a power distribution network dispatching control layer. The whole scheduling process is as follows: according to the response information of the electric automobile in a bottom-up mode, the cluster grid division layer predicts information such as a time period, expected charging completion time, expected SOC and the like of the electric automobile in the next day of access to a system by adopting a neural network method according to historical behavior habits of each automobile. Then, dividing the electric automobile cluster dynamic grids by adopting a clustering method and reporting to an upper layer; the optimization calculation layer collects the overall state information of all the electric vehicle demand responses, establishes a multi-objective dispatching optimization model, solves the multi-objective dispatching optimization model, and reports the optimization calculation result to the dispatching control layer. The electric vehicles respond to the control instructions and issue in a top-down mode, a dispatching control layer formulates a charging and discharging dispatching strategy of each electric Vehicle cluster according to the optimized calculation result and issues the dispatching strategy to a cluster Grid dividing layer, and electric vehicles in the layer execute the dispatching control instructions and participate in Vehicle to Grid (V2G) dispatching according to requirements.
The pyramid model is adopted to describe the electric vehicle cluster scheduling, and the method has the advantages that the large-scale electric vehicle scheduling work can be subdivided into a plurality of clusters which are convenient to operate; for the upper power distribution network dispatching system, the dispatching object is not a single dispersed electric automobile, but a large-capacity storage battery consisting of electric automobiles with similar behaviors, so that the calculation complexity can be effectively reduced, and the optimal dispatching control of the large-scale electric automobiles can be applied to the actual environment.
Step two: electric vehicle user behavior prediction
The current behavior of the electric automobile is directly related to the state of the electric automobile at the historical moment, so that the recurrent neural network with short-time memory is adopted to predict the user behavior of the electric automobile. According to the principle structure of the recurrent neural network, the input vector X= [ X ] 1 ,x 2 ,…,x 7 ]Wherein: x is x 1 Indicating the battery capacity of the electric automobile, x 2 Indicating the initial SOC of the electric automobile, x 3 Representing the expected SOC, x, over a scheduling period (24 h) 4 =t represents the electric car access time, x 5 = (1, 2, …, q) represents a charging place, x 6 ＝[0,1]Representing weather factors (x 6 =1 indicates that hail, heavy rain, typhoon, etc. affect the electric car userWeather of normal behavior; x is x 6 =0 indicates weather that does not affect the normal behavior of the electric vehicle on sunny days, cloudy days, etc.), x 7 Indicating the type of day scheduled, such as weekday, weekend, holiday, etc. The output vector is o= [ O 1 ,o 2 ,o 3 ]Wherein: o (o) 1 O as schedulable location 2 To be schedulable time o 3 Is the schedulable capacity of each electric car. Sequencing the charge and discharge behavior records according to different times to obtain an input sequence X 1 、X 2 … and output sequence O 1 、O 2 …. The RNN is used for predicting load distribution Q of all electric automobile users participating in V2G scheduling at t moment based on historical behaviors t . The hidden layer and the output layer use Logistic functions, and a specific calculation formula is as follows:
wherein O is t Andrepresenting the output true and predicted values, respectively. />The loss function is represented by a function of the loss, I U I 2 +||V|| 2 Representing normalization operations, alpha being the weight. Solving the learning parameters of RNN by using a back propagation algorithm, gradually transmitting error information forward in reverse order, and generating new record [ X, O ]]And when the U and the V are updated, the prediction model is adjusted to obtain more accurate results.
For the electric automobile users newly added with the V2G scheduling, under the condition of lacking historical behavior data, an initial prediction model is established according to the statistical rules shown in the table 1, and the prediction model is continuously adjusted along with accumulation of the historical data so as to improve the prediction accuracy.
Table 1 statistics of behavior habits of three electric vehicles
Step three: electric automobile grid cluster dynamic division
Uploading predicted data of the user behaviors of the electric automobile to a cluster dynamic partitioning layer, and adopting a multi-resolution clustering technology based on grids: statistical information grids (STatistical INformation Grid, STING) cluster electric vehicles with similar behaviors, forming a grid-like large-capacity distributed power supply for distribution network scheduling and control (as in fig. 2). Taking the fluctuation and uncertainty of the user behavior into consideration, setting a rolling time window to update the actual behavior of the electric automobile user, further adjusting a prediction model on the basis, and dynamically adjusting the electric automobile cluster to reduce the influence of the behavior uncertainty on the optimal scheduling.
Step four: multi-objective optimized dispatching for electric automobile
In order to balance the competition relationship between the travel demands of users and the dispatching of the power distribution network side, an optimal dispatching scheme (shown in figure 3) is obtained by adopting a multi-objective optimization model which maximizes user satisfaction and minimizes power distribution network load fluctuation. The user satisfaction degree comprises two aspects of income satisfaction degree and travel satisfaction degree, and the V2G scheduling is capable of reducing the charging cost while guaranteeing travel convenience of the electric automobile user.
Travel satisfaction is defined as:
wherein k is j,t (j=1, 2.,. J) is the access coefficient, k, of the jth electric car in period t j,t =1 indicates that the electric vehicle j has been connected to the power system and can be scheduledOtherwise, the electric automobile is not available for dispatching; t is the number of time periods within the scheduling period;and->The method comprises the steps that the SOC of a j-th electric automobile is scheduled at the beginning and the end; />And for the expected SOC of the jth electric automobile, when the SOC value of the electric automobile reaches the expected value within the specified time, the user satisfaction is met.
The revenue satisfaction is defined as:
in the method, in the process of the invention,and->The discharging and charging power of the jth electric automobile at the t moment are respectively +.>And->The discharge and charge prices, c min Is the lowest charge price for the entire scheduling period. Equation (5) shows that the more the electric vehicle user provides electricity to the grid and the lower the charging price, the higher the revenue satisfaction.
The objective function is converted into a minimum objective function by applying a proportional fuzzy membership inverse function:
the constraint conditions are as follows:
wherein lambda is 1 And lambda (lambda) 2 Respectively f' 1,j And f' 2,j Weight parameter lambda of (2) 1 +λ 2 ＝1。Is the maximum SOC of the electric vehicle j. (7)
Indicating that the SOC of the electric automobile should be greater than or equal to 0, less than or equal toEquation (8) and equation (9) represent schedulable and non-schedulable times of the electric vehicle.
On the power distribution network side, the minimized load fluctuation is taken as a scheduling target to realize peak clipping and valley filling of a load curve. The objective function of load fluctuation is:
in the method, in the process of the invention,for the period t without the base load of the electric vehicle, < >>Is the total charge-discharge load of the electric automobile. P (P) avg The average load is represented by the following calculation formula:
the constraint conditions are as follows:
1) System power balance:
wherein,for the power loss of the power system at time t +.>And transmitting power for the connecting line of the transformer at the moment t.
2) Network node voltage:
wherein,and->The voltage limits of node i, respectively.
3) Branch transmission power:
wherein,for the transmission work of the line at time tRate of->Is the maximum transmission power of the l line.
4) Transformer transmission capacity:
wherein,and->The upper and lower limits of the distribution transformer power, respectively.
And obtaining a Pareto optimal solution of the multi-objective optimization problem by adopting a non-dominant order algorithm (NSGA-II), thereby obtaining an optimal scheduling scheme for satisfying both the electric automobile user and the power distribution network.
In summary, by adopting the dynamic meshing pyramid scheduling method of the large-scale electric vehicle, the user behavior can be automatically predicted by adopting the recurrent neural network in the electric vehicle user information collection stage, so that the complicated workload of the user in participating in V2G scheduling is greatly reduced, and the participation degree of the user is further improved. In addition, when the dispatching is optimized, the traveling requirement of a user and the operation requirement of the distribution network side can be considered, and the actual requirement of dispatching of the large-scale electric automobile can be met.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should be covered by the protection scope of the present invention by making equivalents and modifications to the technical solution and the inventive concept thereof.
Claims (4)
1. The dynamic gridding pyramid scheduling method for the large-scale electric automobile is characterized by comprising the following steps of:
step one: a four-layer pyramid scheduling model is built, electric automobile information adopts a bottom-up transmission mode, and an optimal scheduling strategy adopts a top-down release mode;
step two: predicting the user behavior of the electric automobile, establishing a prediction model by adopting a recurrent neural network with a short-time memory function, and predicting the charge and discharge behaviors of all the electric automobiles in the area in the next scheduling period;
step three: electric automobile grid clusters are dynamically divided, and electric automobiles with similar behaviors are divided into different grid clusters to form a large-capacity distributed energy storage unit for dispatching;
step four: the method comprises the steps of (1) multi-objective optimal scheduling of the electric automobile, establishing an optimal model aiming at maximizing user satisfaction and minimizing load fluctuation of a power distribution system, and obtaining an optimal scheduling scheme;
the electric automobile user behavior prediction model, the input vector includes: the battery capacity, initial state of charge, expected state of charge, access time, charging place, weather factors and dispatch date type of the electric automobile; the output vector includes: the method comprises the steps of (1) establishing a prediction model by taking historical data of an electric automobile as training data, wherein the electric automobile can be scheduled in position, time and capacity;
the user satisfaction index comprises two aspects of income satisfaction and travel satisfaction;
travel satisfaction is defined as:
wherein k is j,t (j=1, 2.,. J) is the access coefficient, k, of the jth electric car in period t j,t =1 indicates that the electric automobile j has been connected to the power system and can be scheduled, whereas indicates that the electric automobile is not available for scheduling; t is the number of time periods within the scheduling period;and->The method comprises the steps that the SOC of a j-th electric automobile is scheduled at the beginning and the end; />For the expected SOC of the jth electric automobile, when the SOC value of the electric automobile reaches an expected value within a specified time, the user satisfaction is satisfied;
the revenue satisfaction is defined as:
in the method, in the process of the invention,and->The discharging and charging power of the jth electric automobile at the t moment are respectively +.>And->The discharge and charge prices, c min For the lowest charging price of the whole dispatching cycle, the more the electric automobile user provides electricity to the power grid, the lower the charging price, and the higher the income satisfaction.
2. The method for dispatching dynamic meshing pyramids of large-scale electric vehicles according to claim 1, wherein the four-layer pyramid dispatching models are respectively as follows from bottom to top: the electric vehicle comprises an electric vehicle local response layer, a cluster grid dividing layer, an optimization calculation layer and a power distribution network dispatching control layer.
3. The method for dispatching dynamic meshing pyramids of large-scale electric vehicles according to claim 1, wherein the electric vehicle meshing clusters are dynamically partitioned, and electric vehicles with similar behaviors are partitioned into different dynamic meshing clusters according to behavior prediction results of electric vehicle users to form the dispatching high-capacity distributed energy storage unit.
4. The method for dispatching dynamic meshing pyramids of large-scale electric vehicles according to claim 1, wherein the electric vehicle multi-objective optimization dispatching model comprises two optimization objectives of user satisfaction and power distribution network load fluctuation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010414980.5A CN113675866B (en) | 2020-05-15 | 2020-05-15 | Dynamic gridding pyramid scheduling method for large-scale electric automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010414980.5A CN113675866B (en) | 2020-05-15 | 2020-05-15 | Dynamic gridding pyramid scheduling method for large-scale electric automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113675866A CN113675866A (en) | 2021-11-19 |
| CN113675866B true CN113675866B (en) | 2023-12-05 |
Family
ID=78537827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010414980.5A Active CN113675866B (en) | 2020-05-15 | 2020-05-15 | Dynamic gridding pyramid scheduling method for large-scale electric automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113675866B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104064829A (en) * | 2013-11-28 | 2014-09-24 | 清华大学 | Electric vehicle real-time charging method based on electric vehicle cluster charging prediction |
| CN106960279A (en) * | 2017-03-16 | 2017-07-18 | 天津大学 | Consider the electric automobile energy efficiency power plant characteristic parameter appraisal procedure of user's participation |
| CN107133415A (en) * | 2017-05-22 | 2017-09-05 | 河海大学 | A kind of electric automobile charge and discharge Electric optimization for considering user's satisfaction and distribution safety |
| CN107769237A (en) * | 2017-11-30 | 2018-03-06 | 南方电网科学研究院有限责任公司 | Multi-energy system coordinated dispatching method and device based on electric automobile access |
| CN108053653A (en) * | 2018-01-11 | 2018-05-18 | 广东蔚海数问大数据科技有限公司 | Vehicle behavior Forecasting Methodology and device based on LSTM |
| GB201810314D0 (en) * | 2018-06-22 | 2018-08-08 | Moixa Energy Holdings Ltd | Systems for machine learning, optimising and managing local multi-asset flexibility of distributed energy storage resources |
| CN109190812A (en) * | 2018-08-21 | 2019-01-11 | 中国电力科学研究院有限公司 | A kind of virtual energy storage active volume prediction technique and system based on electric car |
| CN109447376A (en) * | 2018-12-11 | 2019-03-08 | 国网山东省电力公司滨州供电公司 | Residential block electric car charge and discharge Electric optimization based on user's comprehensive satisfaction |
| CN109672199A (en) * | 2018-11-29 | 2019-04-23 | 杭州电子科技大学 | A kind of electric car peak load shifting capabilities method based on energy balance |
| CN110053508A (en) * | 2019-04-30 | 2019-07-26 | 国网电动汽车服务有限公司 | Energy internet cluster traffic control method and system based on car networking platform |
| CN110110895A (en) * | 2019-04-08 | 2019-08-09 | 国网河北省电力有限公司经济技术研究院 | The method and terminal device of electric car Optimized Operation |
| CN110543543A (en) * | 2019-09-10 | 2019-12-06 | 苏州大学 | user movement behavior prediction method and device based on multi-granularity neural network |
| CN110751314A (en) * | 2019-09-16 | 2020-02-04 | 上海电力大学 | Electric vehicle load prediction method considering user charging behavior characteristic data driving |
| CN110826880A (en) * | 2019-10-24 | 2020-02-21 | 成都信息工程大学 | Active power distribution network optimal scheduling method for large-scale electric vehicle access |
-
2020
- 2020-05-15 CN CN202010414980.5A patent/CN113675866B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104064829A (en) * | 2013-11-28 | 2014-09-24 | 清华大学 | Electric vehicle real-time charging method based on electric vehicle cluster charging prediction |
| CN106960279A (en) * | 2017-03-16 | 2017-07-18 | 天津大学 | Consider the electric automobile energy efficiency power plant characteristic parameter appraisal procedure of user's participation |
| CN107133415A (en) * | 2017-05-22 | 2017-09-05 | 河海大学 | A kind of electric automobile charge and discharge Electric optimization for considering user's satisfaction and distribution safety |
| CN107769237A (en) * | 2017-11-30 | 2018-03-06 | 南方电网科学研究院有限责任公司 | Multi-energy system coordinated dispatching method and device based on electric automobile access |
| CN108053653A (en) * | 2018-01-11 | 2018-05-18 | 广东蔚海数问大数据科技有限公司 | Vehicle behavior Forecasting Methodology and device based on LSTM |
| GB201810314D0 (en) * | 2018-06-22 | 2018-08-08 | Moixa Energy Holdings Ltd | Systems for machine learning, optimising and managing local multi-asset flexibility of distributed energy storage resources |
| CN109190812A (en) * | 2018-08-21 | 2019-01-11 | 中国电力科学研究院有限公司 | A kind of virtual energy storage active volume prediction technique and system based on electric car |
| CN109672199A (en) * | 2018-11-29 | 2019-04-23 | 杭州电子科技大学 | A kind of electric car peak load shifting capabilities method based on energy balance |
| CN109447376A (en) * | 2018-12-11 | 2019-03-08 | 国网山东省电力公司滨州供电公司 | Residential block electric car charge and discharge Electric optimization based on user's comprehensive satisfaction |
| CN110110895A (en) * | 2019-04-08 | 2019-08-09 | 国网河北省电力有限公司经济技术研究院 | The method and terminal device of electric car Optimized Operation |
| CN110053508A (en) * | 2019-04-30 | 2019-07-26 | 国网电动汽车服务有限公司 | Energy internet cluster traffic control method and system based on car networking platform |
| CN110543543A (en) * | 2019-09-10 | 2019-12-06 | 苏州大学 | user movement behavior prediction method and device based on multi-granularity neural network |
| CN110751314A (en) * | 2019-09-16 | 2020-02-04 | 上海电力大学 | Electric vehicle load prediction method considering user charging behavior characteristic data driving |
| CN110826880A (en) * | 2019-10-24 | 2020-02-21 | 成都信息工程大学 | Active power distribution network optimal scheduling method for large-scale electric vehicle access |
Non-Patent Citations (3)
| Title |
|---|
| A Novel Algorithm for Scheduling of Electric Vehicle Using Adaptive Load Forecasting with Vehicle-to-Grid Integration;Akash Gautam等;《2019 8th International Conference on Power Systems (ICPS)》;1-6页 * |
| 考虑多方主体利益的大规模电动汽车分布式实时协同优化;潘振宁等;《中国电机工程学报》;第39卷(第12期);3528-3539页 * |
| 计及路-网-车交互作用的电动汽车充电实时优化调度;王珂等;《电力建设》;第39卷(第12期);63-70页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113675866A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103241130B (en) | Energy management method and system for electric bus charging and swap station | |
| CN109398149A (en) | Intelligent electric automobile charge-discharge system and its progress control method based on distributed energy application | |
| CN107104454A (en) | Meter and the optimal load flow node electricity price computational methods in electric automobile power adjustable control domain | |
| CN112636338B (en) | Load partition regulation and control system and method based on edge calculation | |
| CN111422094A (en) | Charge-discharge coordination optimization control method for distributed charging pile | |
| CN106096773A (en) | A kind of electric automobile serves as the Multiobjective Optimal Operation method of energy storage | |
| CN114219212B (en) | Flexible scheduling method for demand side resources considering ubiquitous electric power Internet of things and edge calculation | |
| CN110676849B (en) | Method for constructing islanding micro-grid group energy scheduling model | |
| CN102708425A (en) | Coordination control system and method for electric vehicle service network based on Multi-Agent system | |
| CN113326994A (en) | Virtual power plant energy collaborative optimization method considering source load storage interaction | |
| CN111798121B (en) | Distributed collaborative optimization method for energy management scheduling of electric automobile | |
| CN113269372A (en) | Cluster electric vehicle schedulable capacity prediction evaluation method considering user will | |
| CN113326467B (en) | Multi-target optimization method, storage medium and optimization system for multi-station fusion comprehensive energy system based on multiple uncertainties | |
| CN110053508B (en) | Energy internet cluster operation scheduling method and system based on internet of vehicles platform | |
| CN116436008A (en) | Power dispatching method and terminal for optical storage charging station | |
| Niu et al. | Hierarchical power control strategy on small-scale electric vehicle fast charging station | |
| CN112217195A (en) | Cloud energy storage charging and discharging strategy forming method based on GRU multi-step prediction technology | |
| CN112001564A (en) | User leaving time prediction method based on long-term and short-term memory network | |
| CN113159578B (en) | Charging optimization scheduling method of large-scale electric vehicle charging station based on reinforcement learning | |
| Tong et al. | An intelligent scheduling control method for smart grid based on deep learning | |
| CN202650066U (en) | Coordination control system for electric-automobile service network based on Multi-Agent system | |
| CN113675866B (en) | Dynamic gridding pyramid scheduling method for large-scale electric automobile | |
| CN112396223A (en) | Electric vehicle charging station energy management method under interactive energy mechanism | |
| CN112633669A (en) | Energy management system and method suitable for large-scale light storage charging electric vehicle charging station | |
| CN109980695A (en) | A kind of distributed energy and user's behavior prediction method of distribution system |
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 |