WO2022152065A1 - 一种充电管理系统的充电与供能优化方法及装置 - Google Patents

一种充电管理系统的充电与供能优化方法及装置 Download PDF

Info

Publication number
WO2022152065A1
WO2022152065A1 PCT/CN2022/070920 CN2022070920W WO2022152065A1 WO 2022152065 A1 WO2022152065 A1 WO 2022152065A1 CN 2022070920 W CN2022070920 W CN 2022070920W WO 2022152065 A1 WO2022152065 A1 WO 2022152065A1
Authority
WO
WIPO (PCT)
Prior art keywords
charging
information
electric vehicle
capacity
demand
Prior art date
Application number
PCT/CN2022/070920
Other languages
English (en)
French (fr)
Inventor
孙玉鸿
潘非
戴珂
康勇
Original Assignee
上海追日电气有限公司
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 上海追日电气有限公司 filed Critical 上海追日电气有限公司
Priority to KR1020237026122A priority Critical patent/KR20230122165A/ko
Priority to DE112022000624.2T priority patent/DE112022000624T5/de
Priority to JP2023541706A priority patent/JP2024503017A/ja
Publication of WO2022152065A1 publication Critical patent/WO2022152065A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • B60L53/60—Monitoring or controlling charging stations
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • B60L53/60—Monitoring or controlling charging stations
    • B60L53/62—Monitoring or controlling charging stations in response to charging parameters, e.g. current, voltage or electrical charge
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • B60L53/60—Monitoring or controlling charging stations
    • B60L53/63—Monitoring or controlling charging stations in response to network capacity
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • B60L53/60—Monitoring or controlling charging stations
    • B60L53/68—Off-site monitoring or control, e.g. remote control
    • 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
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/0013—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries acting upon several batteries simultaneously or sequentially
    • 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
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/007—Regulation of charging or discharging current or voltage
    • 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
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/007—Regulation of charging or discharging current or voltage
    • H02J7/00712—Regulation of charging or discharging current or voltage the cycle being controlled or terminated in response to electric parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Y—INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY
    • B60Y2200/00—Type of vehicle
    • B60Y2200/90—Vehicles comprising electric prime movers
    • B60Y2200/91—Electric vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • 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
    • 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
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02T90/10—Technologies relating to charging of electric vehicles
    • Y02T90/12—Electric charging stations
    • 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
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02T90/10—Technologies relating to charging of electric vehicles
    • Y02T90/14—Plug-in electric vehicles

Definitions

  • the invention relates to the technical field of charging management, in particular to a charging and energy supply optimization method and device for a charging management system.
  • the charging facilities will be idle and the utilization rate is not high during the low-peak period.
  • the charging facilities are fully charged and output, due to the factor of the power demand curve during the charging process, the charging gun and the parking space will be affected. Restrictions, peak hours will also appear the phenomenon that the charging facilities are rich, and the cars are forced to wait.
  • the existing charging facility management system does not have the ability to predict charging supply and demand, and it is only adjusted manually in combination with actual charging usage, which has low efficiency and prominent contradictions in the vehicle charging process, which cannot maximize the charging output of charging facilities and the efficiency of electricity consumption and energy supply. .
  • the purpose of the present invention is to solve the defects of the prior art, to provide a charging and energy supply optimization method and device for a charging management system, using deep learning to establish a continuously optimized management control model, and to optimize the energy supply and charging capability resources of charging facilities , improve the utilization efficiency.
  • a charging and energy supply optimization method for a charging management system comprising:
  • S1 obtain the electric energy supply transformation and distribution information of the charging station, the capability information of the charging facility, the output information of the charging terminal, and the charging demand information of the electric vehicle;
  • S2 Determine the charging capability, power supply capability and actual power supply capability of the charging facility system of the charging station according to the electrical energy supply transformation and distribution information of the charging station, the capability information of the charging facility, the output information of the charging terminal, and the charging demand information of the electric vehicle. charging capacity;
  • the charging management system includes a charging capacity execution management unit and a charging capacity training optimization unit, and the charging capacity training optimization unit forms a pre-trained depth by training, testing and verifying the initial machine learning model.
  • Learning the time series prediction algorithm model in the specific electric vehicle charging application scenario, input the data collected in real time into the deep learning time series prediction algorithm model, and output the results according to the model, combined with the actual charging capacity of the charging facility and the electric vehicle to be charged.
  • the charging power allocation command is generated and sent to the charging capacity execution management unit.
  • the charging capacity execution management unit adjusts the energy supply and charging ratio of the charging facility system in real time according to the actual demand, so that the output of the charging terminal can be optimally satisfied.
  • the charging and energy supply optimization method of the charging management system is to use AI deep learning to establish a continuously optimized management control model to form an optimized charging system energy control supply and demand balance and optimal charging terminal utilization control model output, so as to realize charging The charging and electricity efficiency of the facility system is maximized.
  • the charging and energy supply optimization method provided by the present invention realizes that the charging station can maximize the charging output and power supply efficiency under the best meeting the charging demand of electric vehicles, so that the charging facilities and the corresponding power supply efficiency can be continuously Optimization, using AI deep learning to establish a continuously optimized management control model to maximize the charging and electricity efficiency of the charging facility system.
  • the real-time collected data is input into the deep learning time series prediction algorithm model, and according to the model output results, combined with the actual charging capacity of the charging facility and the charging demand of the electric vehicle to be charged, Generate charging power allocation instructions and adjust the energy supply and charging ratio of the charging facility system in real time according to actual needs, so that the output of the charging terminal can best meet the charging needs of electric vehicles, and maximize the efficiency of charging output and power consumption and energy supply.
  • the model is continuously trained, tested, verified and optimized, so as to continuously optimize the charging facilities and the corresponding power supply efficiency.
  • the real-time charging capacity of the charging equipment is compared with the power supply of the charging station power. Participate in the learning and training to continuously optimize the charging power management module of the system, and predict the charging demand and response capacity of each charging terminal, and the charging capacity of each charging terminal and the power of the charged electric vehicle.
  • the power demand curve of the battery charging process is compared in real time to optimally respond to the charging demand and control the charging capacity in real time.
  • the deep learning time series prediction algorithm model After the deep learning time series prediction algorithm model is formed, it can be combined with the actual charging application scenario to continuously train, verify and optimize the model by inputting real-time values, so as to form an optimized control model output of the energy control supply and demand balance of the charging system.
  • the optimization method of charging and energy supply is continuously optimized, and the changes can be flexibly adjusted according to the actual situation to maximize the charging and power consumption efficiency of the charging facility system.
  • this system can be used to optimize the scheduling, so as to improve the supply and demand adaptability between charging facilities, power supply and distribution and charging terminals, and electric vehicles to be charged, so as to improve the supply and demand of charging facilities, power supply and distribution, charging terminals, and electric vehicles to be charged.
  • the system's resource dynamic optimization implementation provides space.
  • FIG. 1 is a schematic flowchart of a charging and energy supply optimization method for a charging management system of the present invention
  • FIG. 2 is a schematic diagram of the implementation steps of a deep learning model of a charging and energy supply optimization method for a charging management system of the present invention
  • FIG. 3 is a schematic diagram of an energy control output sub-flow diagram of a charging management system of the present invention.
  • FIG. 4 is a schematic structural diagram of a charging and energy supply optimization device of a charging management system of the present invention.
  • FIG. 5 is a graph showing the change in power demand during the charging process of the electric vehicle power battery of the charging terminal being charged according to the present invention.
  • Data management module 2. Data acquisition module; 3. Data storage module; 4. Data training and output module; 5. Human-computer interaction scheduling module; 6. Communication module; 7. Cloud server; 8. Charging Capability management execution unit; 9. Charging capability training optimization unit.
  • the present invention provides a charging and energy supply optimization method for a charging management system, including:
  • Step S1 acquiring information on electric energy supply, transformation and distribution of electric energy in the charging station, capability information of charging facilities, output information of the charging terminal, and information on the charging demand of the electric vehicle.
  • Step S2 Determine the charging capacity, power supply capacity and actual charging capacity of the charging station charging facility system according to the charging station electric energy supply transformation and distribution information, charging facility capability information, charging terminal output information and electric vehicle charging demand information.
  • Step S3 input the charging capacity, power supply capacity and actual charging capacity into the pre-trained deep learning time series prediction algorithm model, and obtain the model output result.
  • Step S4 generating a charging power allocation instruction according to the model output result, the actual charging capacity of the charging facility of the charging station, and the charging demand of the electric vehicle to be charged.
  • step S5 electric energy is distributed to each charging facility according to the charging power distribution instruction, and the electric vehicle is charged through the charging terminal set on the charging facility.
  • the charging management system includes a charging capacity execution management unit 8 and a charging capacity training and optimization unit 9.
  • the charging capacity training and optimization unit 9 forms pre-training by training, testing and verifying the initial machine learning model.
  • the data collected in real time is input into the deep learning time series prediction algorithm model, and the results are output according to the model, combined with the actual charging capacity of the charging facility and the waiting time.
  • a charging power allocation command is generated and sent to the charging capacity execution management unit 8, and the charging capacity execution management unit 8 adjusts the energy supply and charging ratio of the charging facility system in real time according to the actual demand, so that the output of the charging terminal is In the best way to meet the charging needs of electric vehicles, maximize the efficiency of charging output and power consumption; at the same time, in the process of using the deep learning time series prediction algorithm model, combined with the actual charging application scenario, the model is continuously updated. It can be trained, tested, verified and optimized locally, so that the charging facilities and the corresponding power supply efficiency can be continuously optimized.
  • the charging capacity of the charging facility system is the sum of the rated power of all charging facilities, and the power supply capacity of the charging facility system is the rated capacity of the charging station energy supply, transformation and distribution transformer minus the electric power of other equipment in the power grid.
  • the maximum output capacity is set to be ⁇ P
  • the power supply capacity is ⁇ Q
  • the actual charging capacity is ⁇ S
  • the rated power of a single charging facility is P
  • the number of charging facilities is m
  • the charging capacity set on each charging facility is ⁇ S.
  • the number of terminals is n, we can get:
  • the output power of the charging facility P m ⁇ S m1 +S m2 +...+S mn , S m is the actual charging power of the charging terminal, which is directly related to the electric vehicle to be charged, and its value is 0 when the electric vehicle is not connected .
  • the maximum output power of the charging terminal is less than or equal to the maximum power receiving capacity of the electric vehicle, which is controlled by the battery charging management system in the electric vehicle, and is also controlled by the power supply capacity of the system.
  • the charging terminal should be selectively controlled, and the charging completion command should be issued to access the new charging demand, so as to charge the new electric vehicle and monitor the charging status in real time.
  • the charging and energy supply optimization method of the charging management system provided by the present invention is to use AI deep learning to establish a continuously optimized management control model to form an optimized charging system energy control supply and demand balance and optimal charging terminal utilization control model output, so as to realize charging The charging and electricity efficiency of the facility system is maximized.
  • the charging management system of the present invention includes a charging capability execution management unit 8 , a charging capability training optimization unit 9 and a cloud server 7 , and the charging capability execution management unit 8 includes an energy supply substation and distribution station for charging facilities.
  • the control module and several charging facilities are provided with several charging terminals, the charging facilities are all connected with the charging facility distribution control module, the charging facility distribution control module is connected to the energy supply substation, and the charging facility distribution control module is used for receiving The charging power distribution instruction sent by the charging capability training optimization unit, and control the distribution of electric energy to the charging facility according to the charging power distribution instruction; the charging facility is used to convert the electric energy into the working power required by the electric vehicle to be charged, and the electric vehicle to be charged is to be charged through the charging terminal. Perform DC fast charging or AC slow charging.
  • the charging capacity training optimization unit 9 includes a data management module 1, a data acquisition module 2, a data storage module 3, a data training and output module 4, and the data acquisition module 2, the data storage module 3 and the data training and output module 4 all pass through the data management module. 1 is connected to the charging facility distribution control module.
  • the charging capability training and optimization unit 9 also includes a human-computer interaction scheduling module 5 and a communication module 6.
  • the human-computer interaction scheduling module 9 is connected to the data management module 1 and the communication module 6 respectively, and the communication module 6 is connected to the Data training and output module 4 are connected.
  • Cloud server 7 supports system-level comprehensive management, supports remote sharing, collection, processing, interoperability and scheduling of data information through the common protocol of communication interfaces, and serves as a charging capacity training and optimization unit.
  • 8 Extension of data management center and local area network management and sharing expansion and can accept the migration and placement of AI training environment and models, so as to better utilize the advantages of artificial intelligence technology under big data to train and verify the output control model, so as to optimize data sharing and data sharing under the local multi-station charging management system Machine in-depth learning realizes the complementation and optimization of charging capacity resources of each system, and maximizes the charging and power consumption efficiency of the charging facility system in the local area.
  • step S1 before the step of acquiring the electric energy supply and distribution information of the charging station, the capability information of the charging facility, the output information of the charging terminal and the charging demand information of the electric vehicle, the method further includes:
  • Step S01 selecting a machine learning pre-model, setting an initial threshold value and a function matrix related to charging capacity in the machine learning pre-model, and establishing a relationship model for timing prediction relationship between charging and energy supply optimization.
  • Step S02 set the characteristic parameters of the charging terminal, obtain the power demand variation curve of the power battery of the charged electric vehicle during the charging process, and establish the characteristic time sequence prediction relationship of the charging working state.
  • Step S03 acquiring the charging demand information of the electric vehicle, the charging work information of the charging facility, the power supply information and the environmental information, and creating a feature database.
  • Step S04 the data in the feature database is input into the charging and energy supply optimization time sequence prediction relationship model, combined with the charging working state characteristic time sequence prediction relationship, the charging and energy supply optimization time sequence prediction relationship model is trained and optimized to obtain the pre-trained depth. Learn algorithmic models for time series forecasting.
  • timing prediction relationship between charging and energy supply optimization After the timing prediction relationship between charging and energy supply optimization is established, it is also necessary to establish the timing prediction relationship for the characteristics of the charging working state, including: setting the corresponding relationship between the charging capacity and time of each charging terminal as the main variable, which is used to correspond and respond to the charging of electric vehicles. demand, and establish a one-to-one corresponding time series prediction relationship trend between the electric vehicle entering the charging state and the charging terminal.
  • the power demand change curve of the power battery charging process of the charged electric vehicle can be derived from the historical database or the source
  • the battery management system BMS of the charged electric vehicle can be read through the mobile APP, Internet server or charging terminal, and the power demand change curve of the power battery of the charged electric vehicle during the charging process can be obtained. It is used for the supervised learning of the real-time charging energy state of the charging terminal and the charged electric vehicle, and improves the accuracy of the energy adaptation control.
  • the power of the charging terminal is generally selected to meet the maximum rated power required for the charging of the electric vehicle, so as to ensure that when the charged electric vehicle needs to be charged with the maximum capacity, the charging terminal can provide the corresponding electric energy.
  • Figure 5(a) shows the typical different SOC of the power battery at room temperature. The lower charging current curve. With the change of the power battery charging process, the output power of the charger also changes accordingly.
  • Figure 5(b) reflects the curve of the actual output power of the charging terminal changing with the power charging process.
  • the system can be used to optimize scheduling, so as to Improve the supply and demand adaptability between charging facilities, power supply and distribution and charging terminals, and electric vehicles to be charged, thereby providing space for the implementation of dynamic optimization of resources in this system.
  • Module 2 collects data, and after being processed by data management module 1, enters data storage module 3 for storage, provides historical and real-time data for data training and output module 4, and trains and optimizes the initially established charging and energy supply optimization timing prediction relationship model.
  • Relevant collection parameters include working information status parameters of charging facilities, number and model parameters of charged electric vehicles, charging demand parameters of charged electric vehicles, power supply capacity parameters, environmental status parameters, working status scene data, and human-computer interaction control parameters, associative data It is used to calculate the charging demand of electric vehicles, the real-time charging capacity of charging equipment and the power supply of charging station power. Participate in learning and training to continuously optimize the charging power management module of the system, and predict the charging demand and response capacity of each charging terminal. The charging capacity is compared with the power demand curve of the electric vehicle power battery during the charging process in real time, so as to optimally respond to the charging demand and control the charging capacity in real time.
  • step S04 the data in the feature database is input into the charging and energy supply optimization time sequence prediction relationship model, combined with the charging working state characteristic time sequence prediction relationship, the charging and energy supply optimization time sequence prediction relationship model is trained and optimized to obtain
  • the method further includes:
  • Step S05 compare, predict and optimize the target control amount under the pre-trained deep learning time series prediction algorithm model, and perform model training and data output according to the comparison value (first comparison value).
  • Step S06 accumulating certain charging and energy supply values, inputting the collected real-time data into a feature database, and enriching the feature database in combination with the application scene features of the charging station and the electric vehicle to be charged.
  • data such as charging demand information of electric vehicles, charging work information of charging facilities, power supply information, and environmental information are collected in real time to enrich the feature database.
  • Step S07 perform model learning training and numerical analysis according to the enriched feature database, output a comparison value (second comparison value) according to the numerical analysis result, and control the use of the charging terminal in combination with the charging state of the charging terminal and the demand information of the electric vehicle.
  • Step S08 forming an optimized control model output of the energy control supply and demand balance of the charging system.
  • the deep learning time series prediction algorithm model it is necessary to combine the actual charging application scenarios, and continuously input real-time values to train, verify and optimize the model, so as to form an optimized charging system energy control supply and demand balance.
  • the output of the control model makes the charging and energy supply optimization method continuously optimized, and can be adjusted and changed flexibly according to the actual situation to maximize the charging and power consumption efficiency of the charging facility system.
  • the available charging and energy supply time series prediction algorithm framework models include autoregressive models, LSTM models, etc. for deep learning optimization algorithm models, providing more suitable applications Predict the trend of the relationship between scene charging and energy supply demand to adapt to the coordination of supply and demand capabilities between different charging systems and achieve a better supply and demand balance.
  • step S05 the target control quantity is compared, predicted and optimally controlled under the deep learning time series prediction algorithm model, and according to the comparison value (the first comparison value), the steps of model training and data output specifically include:
  • the charging power distribution command is output, and the energy control output sub-process is executed. , to control the use of the charging terminal.
  • the target control amount is the relationship between charging and energy supply.
  • the processed real-time data is input to obtain the output result of the model, and according to the output result of the model, the charging power is output.
  • Assign instructions or continue to train and optimize the model apply the model to the actual charging scenario, and perform training optimization in the actual charging scenario, so as to provide a trend prediction that is more suitable for the relationship between charging and energy supply demand in the application scenario, and achieve the best
  • the output command of the charging capacity training optimization management unit is given to the charging capacity execution power management unit, the energy control output sub-process is executed, and the use of the charging terminal is controlled to meet the The charging demand of new electric vehicles, while improving the utilization rate of charging terminals, avoids idle charging terminals or waste of excess power in the system.
  • step S07 model learning training and numerical analysis are carried out according to the accumulated data set, and a comparison value (second comparison value) is output according to the numerical analysis result, and the charging terminal's charging state and the demand information of the electric vehicle are combined to control the charging terminal.
  • the steps used include:
  • the system will also respond to the actual charging demand, output the comparison value according to the numerical analysis result, and control the charging capacity to execute the power management unit charging terminal.
  • the output comparison value control system needs to respond to or receive the charging demand of the new electric vehicle, that is, the output command of the management unit is optimized by charging capacity training.
  • the charging capability executes the power management unit, executes the energy control output sub-process, controls the use of the charging terminal, meets the charging requirements of the new electric vehicle, and at the same time improves the utilization rate of the charging terminal and avoids the idle charging terminal or the waste of excess power in the system.
  • the steps of the energy control output sub-process include:
  • the charging terminal When the charging terminal is in an idle state, it connects to the new electric vehicle according to the priority, charges the new electric vehicle, monitors the charging status in real time, and feeds back the charging energy usage information to the database.
  • the energy control output sub-process is based on the output results of the numerical analysis of the charging data management center, combined with the charging state of the charging terminal and the charging demand of the electric vehicle to judge and control the use of the charging terminal.
  • the energy optimization scheduling output control process is specifically as follows: while the data training and output module 4 outputs commands, the charging facility allocation control module of the charging capacity execution management unit 8 is also monitoring the charging terminals of the system at all times. Once the charging demand of the new electric vehicle is received through the mobile APP or the Internet server or the human-computer interaction scheduling module 5, etc., the priority is defined according to the demand sequence, and the judgment is made in the system according to identification and scheduling.
  • the charging facility distribution control module arranges the access of new electric vehicles to be charged.
  • the electric vehicle is charged, and the charging status is monitored in real time.
  • the relevant information of the newly connected charging terminal and the electric vehicle is fed back to the data acquisition module and entered into the large database.
  • the charging facility distribution control module judges whether there is a surplus of power supply in the system, and if there is a surplus of power supply in the system, finds out the corresponding connected devices whose real-time charging power of each charging terminal is less than 90% of the maximum charging capacity.
  • the control center can judge whether the charged electric vehicle is in an equalizing state by combining the power demand change curve of the power battery of the charged electric vehicle in Figure 5.
  • the relevant information about entering the electric vehicle is fed back to the data acquisition module and entered into the large database.
  • the charging facility distribution control module judges whether there is a surplus of electric energy in the system, and if there is no surplus in the electric energy supply in the system, finds out the real-time charging power of each charging terminal that is less than 90% of the maximum charging capacity.
  • the control center can judge whether the charged electric vehicle is in an equalizing state by combining the power demand change curve of the power battery of the charged electric vehicle in Figure 5.
  • the charging capacity of the charging terminal through the output energy scheduling of the relevant output points in the network, the charging of the charged electric vehicles with priority needs is met, and the charging status and energy supply adjustment are monitored in real time; The relevant information is fed back to the data acquisition module and entered into the big database.
  • the charging facility allocation control module judges whether there is a surplus in the electrical energy supply in the system.
  • Cross-station resource complementary scheduling that is, recommending new demand for charging electric vehicles to nearby charging stations with idle power resources for priority charging.
  • step S08 after the step of forming the output of the optimized control model for energy control supply and demand balance of the charging system, the method further includes: step S09, after training and saving the output of the control model to form the optimized energy control supply and demand balance of the charging system, in On this basis, machine learning training is carried out every preset time period to optimize the control model of the energy control supply and demand balance of the charging system.
  • the deep learning training environment of this embodiment adopts the open-source PyTorch framework of Facebook for learning and training, and the open-source GUN/Linux operating system based on the Ubuntu operating system.
  • the default PyTorch installation environment is based on its relevant intelligent data and models, including the Anaconda package management tool, Mirror settings, visualization tools, GPU (image processor), etc., are built into the developed charging facility management system based on the deep learning time series prediction based on the present invention, and a training model is established. Users can also configure the Ubuntu operating system through the server, and migrate the database implanted in the learning system for remote interaction.
  • the initial thresholds related to the charging capacity include: the maximum power supply capacity of the electric energy supply substation of the charging system, the total rated charging capacity of the charging facilities, the rated charging capacity of each charging facility, and the number and location information of the charging terminals.
  • the charging demand information of the electric vehicle, the charging work information of the charging facility, the power supply information and the environmental information specifically include: the status parameter of the charging facility work information, the number and model parameters of the charged electric vehicle, the charging demand parameter of the charged electric vehicle, Power supply capacity parameters, environmental state parameters, working state scene data and human-computer interaction control parameters.
  • the collection of status parameters of charging facility working information includes charging power and charging duration, real-time power and accumulated power, from charging facilities and their terminals or the BMS management system of the charged electric vehicle, which is used for real-time management and control to enter the database at the same time.
  • the system optimizes the scheduling model combined with the demand and schedules it in real time;
  • the power supply capacity parameter collects the status information from the power supply substation, including the maximum power supply capacity and historical power supply capacity, and real-time power supply data for AI training, matching, and verification.
  • formulate a system optimization scheduling model that combines charging capacity and charging demand, and conduct overall scheduling control;
  • the collection of environmental state parameters is mainly temperature and humidity, the state information from electric energy supply substations and the collection of key points of equipment in the system.
  • Train, match, verify and optimize the control model support the optimization of system work in different scenarios, and monitor and protect the working status of key points;
  • the data collection of working status scenarios is mainly for system monitoring and identification of the working status of smart devices, including charging facilities , charging interface, electric vehicle and other images and data to support model data training, verification and optimization of control system decision-making control capabilities;
  • human-computer interaction control parameters are collected from human-computer interaction scheduling units, charging APP terminals and remote servers, including real-time status Data and model adjustment and setting demand information are directly used as input to realize local or remote human-machine collaborative parameters to participate in operation, control and scheduling.
  • the present invention also provides a charging and energy supply optimization device for a charging management system, including:
  • the data acquisition module 2 is used to acquire the electric energy supply, transformation and distribution information of the charging station, the capability information of the charging facility, the output information of the charging terminal, and the charging demand information of the electric vehicle.
  • the data management module 1 is used to determine the charging capacity, power supply capacity and actual charging capacity of the charging facility system of the charging station according to the electric energy supply transformation and distribution information of the charging station, the capacity information of the charging facility, the output information of the charging terminal and the charging demand information of the electric vehicle.
  • the data storage module 3 is used to store the information on power supply, transformation and distribution of electric energy in the power station, capability information of charging facilities, output information of the charging terminal and information on the charging demand of electric vehicles.
  • Data training and output module 4 is used to input the charging capacity, power supply capacity and actual charging capacity into the pre-trained deep learning time series prediction algorithm model, and obtain the model output results.
  • the charging capacity and the charging demand of the electric vehicle to be charged are used to generate charging power allocation instructions.
  • the charging capacity management execution unit 8 is used for allocating electric energy to each charging facility according to the charging power distribution instruction, and charging the electric vehicle through the charging terminal set on the charging facility.
  • the charging and energy supply optimization device of the charging management system of the present invention takes the data management center as the core, and includes a data management module 1, a data acquisition module 2, a data storage module 3, a data training and output module 4, etc.
  • the management module 1 supports the storage and processing of various databases in the system, and is responsible for communicating with cloud servers, various charging APPs, and WiFi devices to realize remote interaction of users; data acquisition module 2, data storage module 3 , data training and output module 4, human-computer interaction scheduling module 5, and communication module 6 together constitute the charging management computing center of the present invention, and through centralized management of multiple charging station-level systems, the charging and energy supply of the charging management system Optimization, control multiple charging terminals to achieve dynamic distribution of charging power.

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

一种充电管理系统的充电与供能优化方法及装置，方法包括：获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息，并确定充电站充电设施系统的充电能力、供电能力与实际充电容量，根据预先训练的深度学习时间序列预测算法模型获得模型输出结果，结合充电站充电设施系统的实际充电容量以及待充电电动汽车的充电需求量，生成充电功率分配指令，对各充电设施进行电能分配；由于利用深度学习建立持续优化的管理控制模型，优化充电设施的供能与充电能力资源并提高了利用效率。

Description

一种充电管理系统的充电与供能优化方法及装置
本申请要求于2021年1月12日提交中国专利局、申请号为202110033191.1、发明名称为“一种充电管理系统的充电与供能优化方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及充电管理技术领域，特别涉及一种充电管理系统的充电与供能优化方法及装置。
背景技术
电动汽车充电桩作为一项重要的基础设施，关乎着车辆的用车体验，随着新能源汽车保有量的增加和续航里程的提升，对于充电桩的需求量也在逐渐增多，人们日益看重充电基础设施的建设和发展。现有充电设施数量多，充电容量大，但充电设施一旦建成，充电输出接口和停车位是相对固定的，同时还受到接入的供电能力的影响。由于被充电电动汽车的流动性，充电设施所连接的被充电电动汽车的数量，需要充电的时间以及所需充电容量均不确定，经常会出现高峰时段车找桩困难，车辆需排队充电且等候时间长，低峰时段又会出现充电设施闲置、利用率不高的现象；有时，还会出现即使充电设施满充电输出工作，由于存在充电过程功率需求曲线的因素，受充电枪与停车位的限制，高峰时段也会出现充电设施能力富裕，而被迫车等位的现象。
现有的充电设施管理系统不具备充电供需预测能力，仅靠人工结合实际充电使用而调整，效率低且车辆充电过程中矛盾突出，无法实现充电设施的充电输出与用电供能效率的最大化。
发明内容
本发明的目的旨在解决现有技术的缺陷，提供一种充电管理系统的充电与供能优化方法及装置，利用深度学习建立持续优化的管理控制模型，优化充电设施的供能与充电能力资源，提高利用效率。
本发明的上述技术目的是通过以下技术方案得以实现的：一种充电管理系统的充电与供能优化方法，所述方法包括：
S1，获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息；
S2，根据所述充电站电能供能变配电信息、所述充电设施能力信息、所述充电终端输出信息以及所述电动汽车充电需求信息确定充电站充电设施系统的充电能力、供电能力与实际充电容量；
S3，将所述充电能力、所述供电能力与所述实际充电容量输入至预先训练的深度学习时间序列预测算法模型，并获得模型输出结果；
S4，根据所述模型输出结果和充电站充电设施的实际充电容量以及待充电电动汽车的充电需求量，生成充电功率分配指令；
S5，根据所述充电功率分配指令对各充电设施进行电能分配，并通过充电设施上设置的充电终端对电动汽车进行充电。
通过采用上述技术方案，本发明提供的充电管理系统包括充电能力执行管理单元和充电能力训练优化单元，充电能力训练优化单元通过对初始的机器学习模型进行训练、测试和验证，形成预先训练的深度学习时间序列预测算法模型，在具体的电动汽车充电应用场景中，将实时采集的数据输入至深度学习时间序列预测算法模型中，根据模型输出结果，并结合充电设施的实际充电容量以及待充电电动汽车的充电需求，生成充电功率分配指令并发送至充电能力执行管理单元，由充电能力执行管理单元根据实际需求实时调整充电设施系统的供能与充电比例，使充电终端的输出量在最佳满足电动汽车的充电需求下，实现充电输出与用电供能效率的最大化；同时，在使用深度学习时间序列预测算法模型的过程中，结合实际的充电应用场景，对模型进行不断地训练、测试、验证和优化，从而使充电设施及相应的供电效率持续优化。本发明提供的充电管理系统的充电与供能优化方法是利用AI深度学习建立持续优化的管理控制模型，形成优化的充电系统能量控制供需平衡、最佳充电终端利用的控制模型输出，从而实现充电设施系统的充电与用电效率最大化。
本发明的有益效果是：
1、本发明提供的充电与供能优化方法，实现本充电站在最佳满足电动汽车的充电需求下，实现充电输出与用电供能效率的最大化，使充电设施及相应的供电效率持续优化，利用AI深度学习建立持续优化的管理控制模型，实现充电设施系统的充电与用电效率最大化。
2、在具体的电动汽车充电应用场景中，将实时采集的数据输入至深度学习时间序列预测算法模型中，根据模型输出结果，并结合充电设施的实际充电容量以及待充电电动汽车的充电需求，生成充电功率分配指令并根据实际需求实时调整充电设施系统的供能与充电比例，使充电终端的输出量在最佳满足电动汽车的充电需求下，实现充电输出与用电供能效率的最大化；同时，在使用深度学习时间序列预测算法模型的过程中，结合实际的充电应用场景，对模型进行不断地训练、测试、验证和优化，从而使充电设施及相应的供电效率持续优化。
3、在对模型进行训练前，需要收集大量的历史数据和实时数据，创建特征数据库，通过特征数据库中的数据对模型进行反复地训练、验证和优化，关联数据用于计算电动汽车充电需求量、充电设备的实时充电量于充电站电能的供电量，参与学习训练不断优化系统充电电能管理模块，并预测各充电终端充电需求与响应能力，对各充电终端的充电能力与被充电电动汽车动力电池充电过程功率需求曲线进行实时对比，以最优实时响应充电需求和控制充电能力。
4、深度学习时间序列预测算法模型形成后，可以结合实际的充电应用场景，不断地通过输入实时的数值去训练、验证并优化模型，从而形成优化的充电系统能量控制供需平衡的控制模型输出，使得充电与供能优化方法是在持续优化的，根据实际情况灵活调整改变，实现充电设施系统的充电与用电效率最大化。
5、在充电需求多而充电终端不足的资源矛盾下，可通过本系统进行优化调度，从而提高充电设施、供配电与充电终端、待充电电动汽车之间的供需适配性，从而为本系统的资源动态优化实施提供了空间。
说明书附图
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明一种充电管理系统的充电与供能优化方法的流程示意图；
图2是本发明一种充电管理系统的充电与供能优化方法的深度学习模型实施步骤示意图；
图3是本发明一种充电管理系统的能量控制输出子流程示意图；
图4是本发明一种充电管理系统的充电与供能优化装置的结构示意图；
图5是本发明充电终端被充电电动汽车动力电池充电过程功率需求变化曲线图。
图中，1、数据管理模块；2、数据采集模块；3、数据存储模块；4、数据训练和输出模块；5、人机交互调度模块；6、通讯模块；7、云服务器；8、充电能力管理执行单元；9、充电能力训练优化单元。
具体实施方式
下面将结合具体实施例对本发明的技术方案进行清楚、完整地描述。显然，所描述的实施例仅仅是本发明的一部分实施例，而不是全部的实施例。基于本发明的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
参见图1，本发明提供一种充电管理系统的充电与供能优化方法，包括：
步骤S1，获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息。
步骤S2，根据充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息确定充电站充电设施系统的充电能力、供电能力与实际充电容量。
步骤S3，将充电能力、供电能力与实际充电容量输入至预先训练的 深度学习时间序列预测算法模型，并获得模型输出结果。
步骤S4，根据模型输出结果和充电站充电设施的实际充电容量以及待充电电动汽车的充电需求量，生成充电功率分配指令。
步骤S5，根据充电功率分配指令对各充电设施进行电能分配，并通过充电设施上设置的充电终端对电动汽车进行充电。
需要说明的是，本发明提供的充电管理系统包括充电能力执行管理单元8和充电能力训练优化单元9，充电能力训练优化单元9通过对初始的机器学习模型进行训练、测试和验证，形成预先训练的深度学习时间序列预测算法模型，在具体的电动汽车充电应用场景中，将实时采集的数据输入至深度学习时间序列预测算法模型中，根据模型输出结果，并结合充电设施的实际充电容量以及待充电电动汽车的充电需求，生成充电功率分配指令并发送至充电能力执行管理单元8，由充电能力执行管理单元8根据实际需求实时调整充电设施系统的供能与充电比例，使充电终端的输出量在最佳满足电动汽车的充电需求下，实现充电输出与用电供能效率的最大化；同时，在使用深度学习时间序列预测算法模型的过程中，结合实际的充电应用场景，对模型进行不断地训练、测试、验证和优化，从而使充电设施及相应的供电效率持续优化。
需要说明的是，充电设施系统的充电能力为所有充电设施的额定功率之和，充电设施系统的供电能力为充电站供能变配电变压器额定容量减去电网内其他设备用电功率后所能提供的最大输出容量，设定充电能力为∑P，供电能力为∑Q，实际充电容量为∑S，单个充电设施的额定功率为P，充电设施的数量为m，每个充电设施上设置的充电终端数量为n，可以得到：
∑P＝P1+P2+…+Pm
∑Q≧∑S
其中，充电设施的输出功率P m≧S m1+S m2+…+S mn，S m为充电终端的实际充电功率，与被充电电动汽车直接相关联，没有接入电动汽车时其值为0。充电终端的最大输出功率小于或等于电动汽车的最大受电容量，受电动汽车内电池充电管理系统的控制，同时受本系统供电能力的控制。
充电机实际输出功率Pn＝Sn，充电时实际所需的功率，除受被充电 电动汽车动力容量、环境温度的影响很大外，更受充电电动汽车动力电池自身的荷电动态SOC等影响。根据被充电电动汽车动力电池充电过程的变化产生的功率需求曲线可以得知，当被充电电动汽车动力电池达到一定容量时，进入需要较长时间的低电流匀充阶段，此时如果∑Q富余，即使充电设施不足，一旦接收到新电动汽车的充电需求，应选择性控制充电终端，发出充电完成指令，以接入新的充电需求，从而对新电动汽车进行充电并实时监控充电状态。
本发明提供的充电管理系统的充电与供能优化方法是利用AI深度学习建立持续优化的管理控制模型，形成优化的充电系统能量控制供需平衡、最佳充电终端利用的控制模型输出，从而实现充电设施系统的充电与用电效率最大化。
具体的，结合附图4，本发明的充电管理系统包括充电能力执行管理单元8、充电能力训练优化单元9和云服务器7，充电能力执行管理单元8包括供能变配电站、充电设施分配控制模块以及若干个充电设施，充电设施设置有若干个充电终端，充电设施均与充电设施分配控制模块连接，充电设施分配控制模块连接至供能变配电站，充电设施分配控制模块用于接收充电能力训练优化单元发送的充电功率分配指令，并根据充电功率分配指令控制电能分配至充电设施；充电设施用于将电能转换成待充电电动汽车所需的工作电源，通过充电终端对待充电电动汽车进行直流快速充电或交流慢充。
充电能力训练优化单元9包括数据管理模块1、数据采集模块2、数据存储模块3、数据训练和输出模块4，数据采集模块2、数据存储模块3以及数据训练和输出模块4均通过数据管理模块1与充电设施分配控制模块连接，充电能力训练优化单元9还包括人机交互调度模块5和通讯模块6，人机交互调度模块9分别与数据管理模块1和通讯模块6连接，通讯模块6与数据训练和输出模块4连接。
云服务器7支持系统级的综合管理，通过通讯接口的共同协议支持数据信息的远程共享、收集处理、互用与调度，作为充电能力训练优化单元8数据管理中心的外延与局域网联管理与共享扩展，并可接受AI训练环境及模型的迁移、置入，更好地发挥大数据下人工智能技术的优势进行输 出控制模型的训练与验证，从而优化局域多站充电管理系统下的数据共享与机器深度学习，实现各系统充电能力资源的互补与优化，实现局域内充电设施系统的充电与用电效率最大化。
参见图2，在步骤S1，获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息的步骤之前，方法还包括：
步骤S01，选择机器学习预模型，并设定所述机器学习预模型中与充电容量相关的初始阈值和功能矩阵，建立充电与供能优化时序预测关系模型。
步骤S02，设置充电终端特征参数，并获取被充电电动汽车动力电池充电过程功率需求变化曲线，建立充电工作状态特征时序预测关系。
步骤S03，获取电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息，创建特征数据库。
步骤S04，将特征数据库中的数据输入至充电与供能优化时序预测关系模型中，结合充电工作状态特征时序预测关系，对充电与供能优化时序预测关系模型进行训练优化，获得预先训练的深度学习时间序列预测算法模型。
应理解的是，在使用预先训练的深度学习时间序列预测算法模型之前，需要先建立模型并对模型进行训练验证，首先是选择机器学习预模型，并设定模型中与充电容量相关的初始阈值和功能矩阵，建立充电与供能优化时序预测关系模型，在选择机器学习预模型时，需要结合应用场景进行选择，初始模型选定后，输入具体的充电系统中与充电容量相关的初始阈值，包括充电系统电能供能变配电站最大供电能力、充电设施系统的总额定充电能力、各充电设施额定充电容量及其充电终端的数量、位置信息，用于动态分析与处理充电系统的充电与供能能力，明确应用场景的状态特征。
充电与供能优化时序预测关系建立后，还需要建立充电工作状态特征时序预测关系，具体包括：设置各充电终端的充电容量与时间的对应关系为主变量，用于对应和响应电动汽车的充电需求，并对进入充电状态的电动汽车与充电终端建立一一对应的时间序列预测关系趋势，需要说明的 是，被充电电动汽车动力电池充电过程功率需求变化曲线可以来源于历史数据库，也可以来源于被充电电动汽车的电池管理系统BMS，通过移动APP或互联网服务器或充电终端读取被充电电动汽车的电池管理系统BMS，即可获取到被充电电动汽车动力电池充电过程功率需求变化曲线，用于充电终端于被充电电动汽车实时充电能量状态的监督学习，并提高能量适配控制的准确性。
如图5所示，现有的电动汽车动力电池大多采用锂离子电池，充电过程所需时间很长。充电终端功率一般选配能满足电动汽车充电所需的最大额定功率，这样可保证当被充电电动汽车需要最大容量充电时，充电终端能提供相应的电能。动力电池所需充电容量同时受电池的剩余容量影响，也即动力电池自身的荷电动态SOC(动力电池剩余电量百分比)，剩余容量占电池容量的比值，当SOC＝1时为电池完全充满，当SOC＝0时表示电池放电完全，这种情况对动力电池的损害极大，实际应用中当SOC小于50％时即应充电补电，图5(a)是常温下动力电池的典型不同SOC下充电电流曲线图。随着动力电池充电过程的变化，充电机输出功率也发生相应的变化，图5(b)反应了充电终端实际输出功率随动力充电过程变化的曲线。
通过图5所给出的本实施例电动汽车动力电池充电容量与SOC的关系曲线可看出，当电动汽车动力电池容量达到90％的额定容量时，所需充电功率将快速减小，对应的用充电时间来表征为：本实施例的电动汽车动力电池容量完全充满需要250-300min，但实际只有开始充电的150min左右需要接近满功率快速充电，将达到电动汽车额定容量的90％，其余的时间充电终端实际输出容量逐渐变低。也就是说，一辆电动汽车要完全充满至额定容量，在充电终端富余的情况下，系统可提供支持，在充电需求多而充电终端不足的资源矛盾下，可通过本系统进行优化调度，从而提高充电设施、供配电与充电终端、待充电电动汽车之间的供需适配性，从而为本系统的资源动态优化实施提供了空间。
在对模型进行训练前，还需要收集大量的历史数据和实时数据，创建特征数据库，也就是模型训练的数据集，通过特征数据库中的数据对模型进行反复地训练、验证和优化，通过数据采集模块2采集数据，经过数据 管理模块1处理后进入数据存储模块3进行存储，为数据训练和输出模块4提供历史和实时数据，对初始建立的充电与供能优化时序预测关系模型进行训练优化，相关采集参数包括充电设施工作信息状态参数、被充电电动汽车车辆数量及车型参数、被充电电动汽车充电需求参数、供电能力参数、环境状态参数、工作状态场景数据以及人机交互控制参数，关联数据用于计算电动汽车充电需求量、充电设备的实时充电量于充电站电能的供电量，参与学习训练不断优化系统充电电能管理模块，并预测各充电终端充电需求与响应能力，对各充电终端的充电能力与被充电电动汽车动力电池充电过程功率需求曲线进行实时对比，以最优实时响应充电需求和控制充电能力。
需要说明的是，在创建特征数据库时，包括训练集和测试集，初期设置90％为训练数据和10％为测试数据，随着数据的不断增多，调整95％为训练数据和5％为测试数据，为机器学习优化输出模型作准备。具体如以基于过去两年收集的充电数据，以小时充电数据为基本时间序列单元，分成两组数据：90％为训练数据集和10％为测试数据集，对过往数据做历史性分析后，做出时间序列预测、建模，再用测试数据做检验调整控制误差，可以很好的管理如季节环境变化造成的电动汽车充电负荷波动的影响。
参见图2，步骤S04，将特征数据库中的数据输入至充电与供能优化时序预测关系模型中，结合充电工作状态特征时序预测关系，对充电与供能优化时序预测关系模型进行训练优化，获得预先训练的深度学习时间序列预测算法模型的步骤之后，方法还包括：
步骤S05，在预先训练的深度学习时间序列预测算法模型下对目标控制量进行比较、预测和优化控制，根据比较值(第一比较值)，进行模型训练与数据输出。
步骤S06，累积一定的充电与供能数值，将采集的实时数据输入特征数据库，结合充电站与被充电电动汽车的应用场景特征，充实所述特征数据库。在实际应用中，实时采集电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息等数据，充实特征数据库。
步骤S07，根据充实后的特征数据库进行模型学习训练与数值分析， 根据数值分析结果输出比较值(第二比较值)，结合充电终端的充电状态与电动汽车的需求信息，控制充电终端的使用。
步骤S08，形成优化的充电系统能量控制供需平衡的控制模型输出。
应理解的是，深度学习时间序列预测算法模型形成后，还需要结合实际的充电应用场景，不断地通过输入实时的数值去训练、验证并优化模型，从而形成优化的充电系统能量控制供需平衡的控制模型输出，使得充电与供能优化方法是在持续优化的，根据实际情况灵活调整改变，实现充电设施系统的充电与用电效率最大化。
需要说明的是，在累积一定的充电与供能数值时，可根据不同场景或用户要求设置的算法，进入学习训练与数值分析，根据充电站与被充电电动汽车的应用场景特征，定期结合大量数据的采集，充实历史数据库与实时数据库，丰富机器学习的数据面，可采用的充电与供能时间序列预测算法构架模型包括自回归模型、LSTM模型等进行深度学习优化算法模型，提供更适合应用场景充电与供能需求关系的趋势预测，以适应不同充电系统之间的供需能力协调，达到更佳的供需平衡。
具体的，步骤S05，在深度学习时间序列预测算法模型下对目标控制量进行比较、预测和优化控制，根据比较值(第一比较值)，进行模型训练与数据输出的步骤具体包括：
输入各充电终端实时接入的电动汽车信息、充电能力、供电能力以及实际充电容量至预先训练的深度学习时间序列预测算法模型。
计算总充电容量并与预定阈值进行对比，同时比较各充电终端的实际充电容量与充电终端的额定输出能力以及被充电电动汽车的充电需求的差值，根据比较值进行模型训练与数据输出。具体的，计算总充电容量并与将所述总充电容量与预定阈值进行对比，同时比较各充电终端的实际充电容量与充电终端的额定输出能力的第一差值以及各充电终端的实际充电容量与被充电电动汽车的充电需求的第二差值，将所述第一差值和所述第二差值作为第一比较值，根据第一比较值进行模型训练与数据输出。
当接收到新电动汽车的充电需求时，根据数据输出结果，结合充电站充电设施的实际充电容量、充电终端的充电状态与电动汽车的需求信息， 输出充电功率分配指令，执行能量控制输出子流程，控制充电终端的使用。
当未接收到新电动汽车的充电需求时，返回执行获取电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息，创建特征数据库的步骤。
应理解的是，目标控制量为充电与供能之间的关系，在深度学习时间序列预测算法模型下，输入经过处理的实时数据，得到模型的输出结果，并根据模型输出结果，输出充电功率分配指令或继续对模型进行训练优化，将模型应用到实际的充电场景中，并在实际的充电场景中进行训练优化，从而提供更适合应用场景充电与供能需求关系的趋势预测，达到最佳的供需平衡，当需要响应或接收到新电动汽车的充电需求时，通过充电能力训练优化管理单元的输出指令给充电能力执行电能管理单元，执行能量控制输出子流程，控制充电终端的使用，满足新电动汽车的充电需求，同时提高充电终端的利用率，避免充电终端闲置或系统内富余的电能浪费。
具体的，步骤S07，根据累积的数据集进行模型学习训练与数值分析，根据数值分析结果输出比较值(第二比较值)，结合充电终端的充电状态与电动汽车的需求信息，控制充电终端的使用的步骤具体包括：
当接收到新电动汽车的充电需求时，根据输出比较值(第二比较值)，结合充电站充电设施的实际充电容量、充电终端的充电状态与电动汽车的需求信息，输出充电功率分配指令，执行能量控制输出子流程，控制充电终端的使用。
当未接收到新电动汽车的充电需求时，返回执行获取电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息，创建特征数据库的步骤。
应理解的是，在根据累积的数据集进行模型学习训练与数值分析的过程中，系统也会结合实际的充电需求作出响应，根据数值分析结果输出比较值，控制充电能力执行电能管理单元充电终端的使用，根据输出指令，结合电动汽车的需求信息判断充电终端的使用，如此时的输出比较值控制系统需要响应或接收新电动汽车的充电需求，即通过充电能力训练优化管理单元的输出指令给充电能力执行电能管理单元，执行能量控制输出子流程，控制充电终端的使用，满足新电动汽车的充电需求，同时提高充电终 端的利用率，避免充电终端闲置或系统内富余的电能浪费。
参见图3，能量控制输出子流程的步骤包括：
接收充电功率分配指令。
接收新电动汽车的充电需求，并按照需求时序定义优先级。
检测充电终端的工作状态。
当充电终端处于空闲状态时，按照优先级接入新电动汽车，对新电动汽车进行充电并实时监控充电状态，同时将充电能量使用信息反馈至数据库。
当充电终端处于非空闲状态时，比较系统内电能供能是否富余。
当系统内电能供能有富余时，结合被充电电动汽车动力电池充电过程功率需求变化曲线，找到处于均充状态的被充电电动汽车以及相对应的充电终端，控制充电终端和被充电电动汽车停止充电，按照优先级接入新的电动汽车，对新电动汽车进行充电并实时监控充电状态，同时将充电能量使用信息反馈至数据库。
当系统内电能供能没有富余时，结合被充电电动汽车动力电池充电过程功率需求变化曲线，找到处于均充状态的被充电电动汽车以及相对应的充电终端，控制充电终端和被充电电动汽车停止充电，接入新的电动汽车并开始充电，同时调整其他充电终端的充电容量，按照优先级满足新电动汽车的充电需求并实时监控充电状态与能量补给调整，并将充电能量使用信息反馈至数据库。
需要说明的是，能量控制输出子流程是根据充电数据管理中心数值分析的输出结果，结合充电终端的充电状态与电动汽车的充电需求判断并控制充电终端的使用。数据训练和输出模块输出指令后，能量优化调度输出控制过程具体为：数据训练和输出模块4在输出指令的同时，充电能力执行管理单元8的充电设施分配控制模块也在时刻监控系统各充电终端的能量使用情况，一旦通过移动APP或互联网服务器或人机交互调度模块5等接收到新电动汽车的充电需求时，按需求时序定义优先级，并在系统内进行判断按识别与调度。
当充电终端有空闲时，充电设施分配控制模块即安排新待充电电动汽车接入，系统结合电能供能变配电站可用的总功率、实际使用功率以及供 给分配最大充电容量对接入的新电动汽车进行充电，并实时监控充电状态，同时将新接入的充电终端与电动汽车的相关信息反馈至数据采集模块，进入大数据库。
当充电终端没有空闲时，充电设施分配控制模块判断系统内电能供能是否有富余，如果系统内电能供能有富余，找出各充电终端实时充电功率小于最大充电容量90％的对应接入的电动汽车，控制中心可结合图5中的被充电电动汽车动力电池充电过程功率需求变化曲线，判断其被充电电动汽车是否处于均充状态，如果已处于均充状态，可以优先停止充电，从而提高充电终端的利用率，控制该充电终端及其对应的电动汽车停止充电，同时接入新的被充电电动汽车，按照优先级以额定容量快充并实时监控充电状态；同时将充电终端与新接入电动汽车的相关信息反馈至数据采集模块，进入大数据库。
当充电终端没有空闲时，充电设施分配控制模块判断系统内电能供能是否有富余，如果系统内电能供能没有富余，找出各充电终端实时充电功率小于最大充电容量90％的对应接入的电动汽车，控制中心可结合图5中的被充电电动汽车动力电池充电过程功率需求变化曲线，判断其被充电电动汽车是否处于均充状态，如果已处于均充状态，可以优先停止充电，从而提高充电终端的利用率，控制该充电终端及其对应的电动汽车停止充电，接入新的被充电电动汽车并开始充电，同时通过充电设施分配控制模块调整其它被充电电动汽车充电容量正处于大幅下降的充电终端的充电容量，通过网内相关输出点的输出能量调度，满足有优先级需求的被充电电动汽车充电并实时监控充电状态与能量补给调整；同时各相关充电终端与接入电动汽车的相关信息反馈至数据采集模块，进入大数据库。
优选地，当充电终端没有空闲时，充电设施分配控制模块判断系统内电能供能是否有富余，如果系统内电能供能没有富余，在多网充电堆/设施充电能力管理系统互联下，可实现跨站资源互补调度，即推荐新需求充电电动汽车到临近有闲置电能资源的充电站进行优先充电。
参见图2，步骤S08，形成优化的充电系统能量控制供需平衡的控制模型输出的步骤之后，方法还包括：步骤S09，训练形成优化的充电系统能量控制供需平衡的控制模型输出并保存后，在此基础上每隔预设时间周 期进行一次机器学习训练，优化充电系统能量控制供需平衡的控制模型。
应理解的是，在训练形成的充电系统能量控制供需平衡的控制模型基础上，每隔预设时间周期进行一次机器学习训练，将多个充电终端做一次充电优先级的调整，让多个充电终端对应的充电位做功率分配调整，以适应不同季节，不同新能源车用户的变化而优化整体充电效率，融合不同型号车辆及移动充电储能设施的充电需求。
本实施例的深度学习训练环境采用学习训练Facebook开源的PyTorch框架，基于Ubuntu操作系统的开源GUN/Linux操作系统，默认PyTorch安装环境，以其相关智能数据与模型为基础，包括Anaconda包管理工具、镜像设置、可视化工具、GPU(图像处理器)等，通过置入开发的基于本发明基于深度学习时间序列预测的充电设施管理系统并建立训练模型。用户也可通过服务器配置Ubuntu操作系统，迁移植入本学习系统的数据库进行远程交互。
具体的，与充电容量相关的初始阈值包括：充电系统电能供能变配电站最大供电能力、充电设施的总额定充电能力、各充电设施额定充电容量及其充电终端的数量和位置信息。
应理解的是，通过设定模型中充电容量相关的初始阈值，结合应用场景选择学习模型并输入具体充电系统的初始阈值，建立充电系统能量优化运行预训练模型，用于动态分析与处理充电系统的充电与供能能力，明确应用场景的状态特征。
具体的，电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息具体包括：充电设施工作信息状态参数、被充电电动汽车车辆数量及车型参数、被充电电动汽车充电需求参数、供电能力参数、环境状态参数、工作状态场景数据以及人机交互控制参数。
需要说明的是，充电设施工作信息状态参数采集包括充电电量及充电时长、实时电量与累计电量，来自充电设施及其终端或被充电电动汽车BMS管理系统，用来实时管理与控制同时进入数据库，支持机器学习与训练验证；被充电车数车型参数采集来自充电终端或电动汽车的车牌识别信号，信息进入数据库，用于AI控制模型训练、匹配、验证，制定充电能力与充电需求相结合的系统优化调度模型并实时调度；充电需求参数采 集来自电动汽车充电请求及实时充电状态，包括正在充电的终端匹配和待充电电动汽车的需求信息，用于AI训练、匹配、验证，制定充电能力与充电需求相结合的系统优化调度模型并实时调度；供电能力参数采集来自电能供能变配电站的状态信息，包括最大供电能力与历史供电容量、实时供能数据，用于AI训练、匹配、验证，制定充电能力与充电需求相结合的系统优化调度模型并总体调度控制；环境状态参数采集主要是温湿度，来自电能供能变配电站的状态信息及系统内设备关键点的采集，用于训练、匹配、验证和优化控制模型，支持不同场景下的系统工作优化，并对关键点工作状态进行监控与保护；工作状态场景数据采集主要是系统监控、智能设备的工作状态识别，包括充电设施、充电接口、电动汽车等图像与数据，用于支持模型数据训练、验证和优化控制系统决策控制能力；人机交互控制参数采集来自人机交互调度单元、充电APP终端与远程服务器，包括实时状态数据及模型的调整、设置的需求信息，直接作为输入实现就地或远程的人机协同参数参与运算、控制与调度。
参见图4，此外，本发明还提供一种充电管理系统的充电与供能优化装置，包括：
数据采集模块2，用于获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息。
数据管理模块1，用于根据充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息确定充电站充电设施系统的充电能力、供电能力与实际充电容量。
数据存储模块3，用于存储电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息。
数据训练和输出模块4，用于将充电能力、供电能力与实际充电容量输入至预先训练的深度学习时间序列预测算法模型，并获得模型输出结果，根据模型输出结果和充电站充电设施系统的实际充电容量以及待充电电动汽车的充电需求量，生成充电功率分配指令。
充电能力管理执行单元8，用于根据充电功率分配指令对各充电设施进行电能分配，并通过充电设施上设置的充电终端对电动汽车进行充电。
需要说明的是，本发明的充电管理系统的充电与供能优化装置以数据 管理中心为核心，包括数据管理模块1、数据采集模块2、数据存储模块3、数据训练和输出模块4等，数据管理模块1作为数据管理中心的处理器，支持系统各数据库储存与处理，并负责与云服务器、各种充电APP、WiFi设备通讯连接，实现用户的远程交互；数据采集模块2、数据存储模块3、数据训练和输出模块4、人机交互调度模块5、通讯模块6一起组成本发明的充电管理运算中心，通过对多个充电站级系统进行集中式管理，实现充电管理系统的充电与供能优化，控制多个充电终端实现充电功率的动态分配。

Claims (10)

  1. 一种充电管理系统的充电与供能优化方法，其特征在于，所述方法包括：
    S1，获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息；
    S2，根据所述充电站电能供能变配电信息、所述充电设施能力信息、所述充电终端输出信息以及所述电动汽车充电需求信息确定充电站充电设施系统的充电能力、供电能力与实际充电容量；
    S3，将所述充电能力、所述供电能力与所述实际充电容量输入至预先训练的深度学习时间序列预测算法模型，并获得模型输出结果；
    S4，根据所述模型输出结果和充电站充电设施的实际充电容量以及待充电电动汽车的充电需求量，生成充电功率分配指令；
    S5，根据所述充电功率分配指令对各充电设施进行电能分配，并通过充电设施上设置的充电终端对电动汽车进行充电。
  2. 根据权利要求1所述的充电管理系统的充电与供能优化方法，其特征在于，所述S1，获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息的步骤之前，所述方法还包括：
    S01，选择机器学习预模型，并设定所述机器学习预模型中与充电容量相关的初始阈值和功能矩阵，建立充电与供能优化时序预测关系模型；
    S02，设置充电终端特征参数，并获取被充电电动汽车动力电池充电过程功率需求变化曲线，建立充电工作状态特征时序预测关系；
    S03，获取电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息，创建特征数据库；
    S04，将所述特征数据库中的数据输入至所述充电与供能优化时序预测关系模型中，结合所述充电工作状态特征时序预测关系，对所述充电与供能优化时序预测关系模型进行训练优化，获得预先训练的深度学习时间序列预测算法模型。
  3. 根据权利要求2所述的充电管理系统的充电与供能优化方法，其特征在于，所述S04，将所述特征数据库中的数据输入至所述充电与供能优化时序预测关系模型中，结合所述充电工作状态特征时序预测关系，对所 述充电与供能优化时序预测关系模型进行训练优化，获得预先训练的深度学习时间序列预测算法模型的步骤之后，所述方法还包括：
    S05，在所述预先训练的深度学习时间序列预测算法模型下对目标控制量进行比较、预测和优化控制，根据比较值，进行模型训练与数据输出；
    S06，累积一定的充电与供能数值，将采集的实时数据输入特征数据库，结合充电站与被充电电动汽车的应用场景特征，充实所述特征数据库；
    S07，根据充实后的特征数据库进行模型学习训练与数值分析，根据数值分析结果输出比较值，结合充电终端的充电状态与电动汽车的需求信息，控制充电终端的使用；
    S08，形成优化的充电系统能量控制供需平衡的控制模型输出。
  4. 根据权利要求3所述的充电管理系统的充电与供能优化方法，其特征在于，所述S05，在所述深度学习时间序列预测算法模型下对目标控制量进行比较、预测和优化控制，根据比较值，进行模型训练与数据输出的步骤具体包括：
    输入各充电终端实时接入的电动汽车信息、充电能力、供电能力以及实际充电容量至所述预先训练的深度学习时间序列预测算法模型；
    计算总充电容量并与预定阈值进行对比，同时比较各充电终端的实际充电容量与充电终端的额定输出能力以及被充电电动汽车的充电需求的差值，根据比较值进行模型训练与数据输出；
    当接收到新电动汽车的充电需求时，根据数据输出结果，结合充电站充电设施的实际充电容量、充电终端的充电状态与电动汽车的需求信息，输出充电功率分配指令，执行能量控制输出子流程，控制充电终端的使用；
    当未接收到新电动汽车的充电需求时，返回执行所述获取电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息，创建特征数据库的步骤。
  5. 根据权利要求3所述的充电管理系统的充电与供能优化方法，其特征在于，所述S07，根据累积的数据集进行模型学习训练与数值分析，根据数值分析结果输出比较值，结合充电终端的充电状态与电动汽车的需求信息，控制充电终端的使用的步骤具体包括：
    当接收到新电动汽车的充电需求时，根据输出比较值，结合充电站充 电设施的实际充电容量、充电终端的充电状态与电动汽车的需求信息，输出充电功率分配指令，执行能量控制输出子流程，控制充电终端的使用；
  6. 根据权利要求4或5所述的充电管理系统的充电与供能优化方法，其特征在于，所述能量控制输出子流程的步骤包括：
    接收充电功率分配指令；
    接收新电动汽车的充电需求，并按照需求时序定义优先级；
    检测充电终端的工作状态；
    当充电终端处于空闲状态时，按照优先级接入新电动汽车，对新电动汽车进行充电并实时监控充电状态，同时将充电能量使用信息反馈至数据库；
    当充电终端处于非空闲状态时，比较系统内电能供能是否富余；
    当系统内电能供能有富余时，结合被充电电动汽车动力电池充电过程功率需求变化曲线，找到处于均充状态的被充电电动汽车以及相对应的充电终端，控制充电终端和被充电电动汽车停止充电，按照优先级接入新的电动汽车，对新电动汽车进行充电并实时监控充电状态，同时将充电能量使用信息反馈至数据库；
    当系统内电能供能没有富余时，结合被充电电动汽车动力电池充电过程功率需求变化曲线，找到处于均充状态的被充电电动汽车以及相对应的充电终端，控制充电终端和被充电电动汽车停止充电，接入新的电动汽车并开始充电，同时调整其他充电终端的充电容量，按照优先级满足新电动汽车的充电需求并实时监控充电状态与能量补给调整，并将充电能量使用信息反馈至数据库。
  7. 根据权利要求3所述的充电管理系统的充电与供能优化方法，其特征在于，所述S08，形成优化的充电系统能量控制供需平衡的控制模型输出的步骤之后，所述方法还包括：
    S09，训练形成优化的充电系统能量控制供需平衡的控制模型输出并保存后，在此基础上每隔预设时间周期进行一次机器学习训练，优化充电系统能量控制供需平衡的控制模型。
  8. 根据权利要求2所述的充电管理系统的充电与供能优化方法，其特征在，所述与充电容量相关的初始阈值包括：充电系统电能供能变配电站 最大供电能力、充电设施的总额定充电能力、各充电设施额定充电容量及其充电终端的数量和位置信息。
  9. 根据权利要求2所述的充电管理系统的充电与供能优化方法，其特征在，所述电动汽车的充电需求信息、充电设施的充电工作信息、供电信息以及环境信息具体包括：充电设施工作信息状态参数、被充电电动汽车车辆数量及车型参数、被充电电动汽车充电需求参数、供电能力参数、环境状态参数、工作状态场景数据以及人机交互控制参数。
  10. 一种充电管理系统的充电与供能优化装置，其特征在于，所述装置包括：
    数据采集模块，用于获取充电站电能供能变配电信息、充电设施能力信息、充电终端输出信息以及电动汽车充电需求信息；
    数据管理模块，用于根据所述充电站电能供能变配电信息、所述充电设施能力信息、所述充电终端输出信息以及所述电动汽车充电需求信息确定充电站充电设施系统的充电能力、供电能力与实际充电容量；
    数据存储模块，用于存储所述电站电能供能变配电信息、所述充电设施能力信息、所述充电终端输出信息以及所述电动汽车充电需求信息；
    数据训练和输出模块，用于将所述充电能力、所述供电能力与所述实际充电容量输入至预先训练的深度学习时间序列预测算法模型，并获得模型输出结果，根据所述模型输出结果和充电站充电设施系统的实际充电容量以及待充电电动汽车的充电需求量，生成充电功率分配指令；
    充电能力管理执行单元，用于根据所述充电功率分配指令对各充电设施进行电能分配，并通过充电设施上设置的充电终端对电动汽车进行充电。
PCT/CN2022/070920 2021-01-12 2022-01-10 一种充电管理系统的充电与供能优化方法及装置 WO2022152065A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
KR1020237026122A KR20230122165A (ko) 2021-01-12 2022-01-10 충전 관리 시스템의 충전과 에너지공급 최적화 방법및 장치
DE112022000624.2T DE112022000624T5 (de) 2021-01-12 2022-01-10 Verfahren und vorrichtung zur optimierung des ladevorgangs und der stromversorgung für ein lademanagementsystem
JP2023541706A JP2024503017A (ja) 2021-01-12 2022-01-10 充電管理システムにおける充電及びエネルギー供給の最適化方法並び装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110033191.1A CN112874369B (zh) 2021-01-12 2021-01-12 一种充电管理系统的充电与供能优化方法及装置
CN202110033191.1 2021-01-12

Publications (1)

Publication Number Publication Date
WO2022152065A1 true WO2022152065A1 (zh) 2022-07-21

Family

ID=76044599

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/070920 WO2022152065A1 (zh) 2021-01-12 2022-01-10 一种充电管理系统的充电与供能优化方法及装置

Country Status (5)

Country Link
JP (1) JP2024503017A (zh)
KR (1) KR20230122165A (zh)
CN (1) CN112874369B (zh)
DE (1) DE112022000624T5 (zh)
WO (1) WO2022152065A1 (zh)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116039437A (zh) * 2023-01-09 2023-05-02 广东天枢新能源科技有限公司 一种大功率液冷充电桩的能量调度系统
CN116353399A (zh) * 2023-05-09 2023-06-30 湖北国网华中科技开发有限责任公司 充电桩的动态运行方法、装置、设备及可读存储介质
CN116562602A (zh) * 2023-07-12 2023-08-08 国网安徽省电力有限公司经济技术研究院 电动汽车参与需求响应优化运行方法
CN116552299A (zh) * 2023-07-11 2023-08-08 深圳市南霸科技有限公司 一种可移动式电动汽车应急充电系统及方法
CN116663842A (zh) * 2023-06-15 2023-08-29 黑龙江卓锦科技有限公司 一种基于人工智能的数字化管理系统及方法
CN116691419A (zh) * 2023-08-03 2023-09-05 浙江大学 弱链接通信下深度强化学习的电动汽车自主充电控制方法
CN116788102A (zh) * 2023-06-20 2023-09-22 阿维塔科技(重庆)有限公司 充电控制方法、装置、车辆及存储介质
CN116834567A (zh) * 2023-09-04 2023-10-03 北京新源恒远科技发展有限公司 适用于双枪充电桩的充电方法、系统、终端及存储介质
CN116882715A (zh) * 2023-09-07 2023-10-13 杭州格创新能源有限公司 基于云服务器的桩车联动有序安全用电方法及系统
CN116937581A (zh) * 2023-09-19 2023-10-24 广州德姆达光电科技有限公司 一种充电站的智能调度方法
CN117060456A (zh) * 2023-08-21 2023-11-14 深圳中保动力新能源科技有限公司 一种基于人工智能的储能系统控制方法及装置
CN117310313A (zh) * 2023-09-18 2023-12-29 广东永光新能源设计咨询有限公司 储能装置的故障检测方法、系统、设备及介质
CN117406007A (zh) * 2023-12-14 2024-01-16 山东佰运科技发展有限公司 一种充电桩充电数据检测方法及系统
CN117584790A (zh) * 2023-11-23 2024-02-23 北京海蓝云联技术有限公司 一种无增容充电桩控制系统
CN116788102B (zh) * 2023-06-20 2024-05-14 阿维塔科技(重庆)有限公司 充电控制方法、装置、车辆及存储介质

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112733426B (zh) * 2020-12-16 2022-10-04 国创移动能源创新中心(江苏)有限公司 电动汽车的脉冲充电频率优化方法、装置
CN112874369B (zh) * 2021-01-12 2022-08-05 上海追日电气有限公司 一种充电管理系统的充电与供能优化方法及装置
JP2022189386A (ja) * 2021-06-11 2022-12-22 トヨタ自動車株式会社 情報処理装置、情報処理方法及びプログラム
CN113379139A (zh) * 2021-06-22 2021-09-10 阳光电源股份有限公司 一种充电站管理方法及其应用装置
CN113568307B (zh) * 2021-07-02 2022-04-01 福建时代星云科技有限公司 一种储充站的控制策略优化方法及终端
WO2023049998A1 (en) * 2021-10-01 2023-04-06 Cowan & Associates Management Ltd. Electric vehicle fleet charging and energy management system
CN114801834B (zh) * 2022-04-18 2022-12-20 广东健怡投资有限公司 新能源汽车剩余充电时长预估方法、装置、设备及介质
CN115081929B (zh) * 2022-07-18 2023-04-07 东南大学溧阳研究院 一种基于云边协同的电动汽车实时响应能力评估方法
CN115291111B (zh) * 2022-08-03 2023-09-29 苏州清研精准汽车科技有限公司 电池静置时间预测模型的训练方法以及静置时间预测方法
CN116307487B (zh) * 2023-02-01 2024-03-19 浙江曼克斯缝纫机股份有限公司 基于电网新能源节能利用的新能源车充电管理系统及方法
CN115946563B (zh) * 2023-03-13 2023-05-16 山东理工大学 充电堆功率动态分配策略优化方法、系统、终端及介质
CN116386215B (zh) * 2023-03-16 2024-04-19 淮阴工学院 一种基于人流量用于移动电箱的智能充电方法
CN117277519B (zh) * 2023-11-21 2024-02-02 深圳鹏城新能科技有限公司 一种储能逆变器电池过充保护方法、系统及介质

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102055217A (zh) * 2010-10-27 2011-05-11 国家电网公司 电动汽车有序充电控制方法及系统
US20130307466A1 (en) * 2011-01-15 2013-11-21 Daimler Ag System and Method for Charging Car Batteries
US20160352111A1 (en) * 2014-02-26 2016-12-01 Hitachi, Ltd. Control system for electric storage system
CN107623355A (zh) * 2017-10-12 2018-01-23 科世达（上海）管理有限公司 一种充电站功率的配置系统、管理器及方法
CN107769237A (zh) * 2017-11-30 2018-03-06 南方电网科学研究院有限责任公司 基于电动汽车接入的多能源系统协同调度方法及装置
CN108494034A (zh) * 2018-03-21 2018-09-04 电子科技大学 一种配电网电动汽车充电负荷分配计算方法
CN109034648A (zh) * 2018-08-13 2018-12-18 华南理工大学广州学院 一种电动汽车集群需求响应潜力评估方法
CN109523087A (zh) * 2018-11-28 2019-03-26 国网山东省电力公司德州供电公司 基于深度学习的电动汽车快充站储能监测系统及其方法
CN109591643A (zh) * 2018-10-31 2019-04-09 特变电工南京智能电气有限公司 一种基于优先级的功率动态分配系统及其方法
CN109927583A (zh) * 2019-04-09 2019-06-25 广州市奔流电力科技有限公司 充电桩控制方法、装置、电动汽车充电系统和存储介质
CN110936843A (zh) * 2019-12-23 2020-03-31 南方科技大学 智能充电桩互联网系统及管理方法
CN112874369A (zh) * 2021-01-12 2021-06-01 上海追日电气有限公司 一种充电管理系统的充电与供能优化方法及装置

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105930955A (zh) * 2016-04-07 2016-09-07 浙江万马新能源有限公司 基于深度学习的充电网络运行态势分析方法及装置
CN109094381A (zh) * 2017-06-20 2018-12-28 南京理工大学 一种电动汽车充电站有序充电方法
WO2019140279A1 (en) * 2018-01-12 2019-07-18 Johnson Controls Technology Company Building energy optimization system with battery powered vehicle cost optimization
US10759298B2 (en) * 2018-08-29 2020-09-01 GM Global Technology Operations LLC Electric-drive motor vehicles, systems, and control logic for predictive charge planning and powertrain control
CN109398133B (zh) * 2018-10-29 2021-09-03 河南英开电气股份有限公司 一种电动汽车充电集群及其功率自动分配系统
CN110154817A (zh) * 2019-05-16 2019-08-23 上海上汽安悦充电科技有限公司 一种集约式交流充电桩集群架构
CN110888908B (zh) * 2019-11-01 2022-06-28 广州大学 一种可持续深度学习的充电站/桩推荐系统及推荐方法
KR102137751B1 (ko) * 2020-01-16 2020-07-27 주식회사 텔다 머신러닝 알고리즘 기반의 에너지 에이전트를 활용한 전력거래시스템 및 방법
CN111429038B (zh) * 2020-04-25 2022-08-12 华南理工大学 一种基于强化学习的主动配电网实时随机优化调度方法
CN112036602A (zh) * 2020-07-24 2020-12-04 国网安徽省电力有限公司经济技术研究院 一种集成人机智能的5g电动汽车充电预测方法和系统

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102055217A (zh) * 2010-10-27 2011-05-11 国家电网公司 电动汽车有序充电控制方法及系统
US20130307466A1 (en) * 2011-01-15 2013-11-21 Daimler Ag System and Method for Charging Car Batteries
US20160352111A1 (en) * 2014-02-26 2016-12-01 Hitachi, Ltd. Control system for electric storage system
CN107623355A (zh) * 2017-10-12 2018-01-23 科世达（上海）管理有限公司 一种充电站功率的配置系统、管理器及方法
CN107769237A (zh) * 2017-11-30 2018-03-06 南方电网科学研究院有限责任公司 基于电动汽车接入的多能源系统协同调度方法及装置
CN108494034A (zh) * 2018-03-21 2018-09-04 电子科技大学 一种配电网电动汽车充电负荷分配计算方法
CN109034648A (zh) * 2018-08-13 2018-12-18 华南理工大学广州学院 一种电动汽车集群需求响应潜力评估方法
CN109591643A (zh) * 2018-10-31 2019-04-09 特变电工南京智能电气有限公司 一种基于优先级的功率动态分配系统及其方法
CN109523087A (zh) * 2018-11-28 2019-03-26 国网山东省电力公司德州供电公司 基于深度学习的电动汽车快充站储能监测系统及其方法
CN109927583A (zh) * 2019-04-09 2019-06-25 广州市奔流电力科技有限公司 充电桩控制方法、装置、电动汽车充电系统和存储介质
CN110936843A (zh) * 2019-12-23 2020-03-31 南方科技大学 智能充电桩互联网系统及管理方法
CN112874369A (zh) * 2021-01-12 2021-06-01 上海追日电气有限公司 一种充电管理系统的充电与供能优化方法及装置

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116039437B (zh) * 2023-01-09 2023-08-15 广东天枢新能源科技有限公司 一种大功率液冷充电桩的能量调度系统
CN116039437A (zh) * 2023-01-09 2023-05-02 广东天枢新能源科技有限公司 一种大功率液冷充电桩的能量调度系统
CN116353399A (zh) * 2023-05-09 2023-06-30 湖北国网华中科技开发有限责任公司 充电桩的动态运行方法、装置、设备及可读存储介质
CN116353399B (zh) * 2023-05-09 2023-11-03 湖北国网华中科技开发有限责任公司 充电桩的动态运行方法、装置、设备及可读存储介质
CN116663842A (zh) * 2023-06-15 2023-08-29 黑龙江卓锦科技有限公司 一种基于人工智能的数字化管理系统及方法
CN116788102A (zh) * 2023-06-20 2023-09-22 阿维塔科技(重庆)有限公司 充电控制方法、装置、车辆及存储介质
CN116788102B (zh) * 2023-06-20 2024-05-14 阿维塔科技(重庆)有限公司 充电控制方法、装置、车辆及存储介质
CN116552299A (zh) * 2023-07-11 2023-08-08 深圳市南霸科技有限公司 一种可移动式电动汽车应急充电系统及方法
CN116552299B (zh) * 2023-07-11 2023-09-15 深圳市南霸科技有限公司 一种可移动式电动汽车应急充电系统及方法
CN116562602B (zh) * 2023-07-12 2023-10-24 国网安徽省电力有限公司经济技术研究院 电动汽车参与需求响应优化运行方法
CN116562602A (zh) * 2023-07-12 2023-08-08 国网安徽省电力有限公司经济技术研究院 电动汽车参与需求响应优化运行方法
CN116691419A (zh) * 2023-08-03 2023-09-05 浙江大学 弱链接通信下深度强化学习的电动汽车自主充电控制方法
CN116691419B (zh) * 2023-08-03 2023-11-14 浙江大学 弱链接通信下深度强化学习的电动汽车自主充电控制方法
CN117060456A (zh) * 2023-08-21 2023-11-14 深圳中保动力新能源科技有限公司 一种基于人工智能的储能系统控制方法及装置
CN117060456B (zh) * 2023-08-21 2024-04-30 深圳中保动力新能源科技有限公司 一种基于人工智能的储能系统控制方法及装置
CN116834567B (zh) * 2023-09-04 2023-11-17 北京新源恒远科技发展有限公司 适用于双枪充电桩的充电方法、系统、终端及存储介质
CN116834567A (zh) * 2023-09-04 2023-10-03 北京新源恒远科技发展有限公司 适用于双枪充电桩的充电方法、系统、终端及存储介质
CN116882715A (zh) * 2023-09-07 2023-10-13 杭州格创新能源有限公司 基于云服务器的桩车联动有序安全用电方法及系统
CN116882715B (zh) * 2023-09-07 2023-11-28 杭州格创新能源有限公司 基于云服务器的桩车联动有序安全用电方法及系统
CN117310313B (zh) * 2023-09-18 2024-04-16 广东永光新能源设计咨询有限公司 储能装置的故障检测方法、系统、设备及介质
CN117310313A (zh) * 2023-09-18 2023-12-29 广东永光新能源设计咨询有限公司 储能装置的故障检测方法、系统、设备及介质
CN116937581B (zh) * 2023-09-19 2023-12-26 广州德姆达光电科技有限公司 一种充电站的智能调度方法
CN116937581A (zh) * 2023-09-19 2023-10-24 广州德姆达光电科技有限公司 一种充电站的智能调度方法
CN117584790A (zh) * 2023-11-23 2024-02-23 北京海蓝云联技术有限公司 一种无增容充电桩控制系统
CN117406007B (zh) * 2023-12-14 2024-02-13 山东佰运科技发展有限公司 一种充电桩充电数据检测方法及系统
CN117406007A (zh) * 2023-12-14 2024-01-16 山东佰运科技发展有限公司 一种充电桩充电数据检测方法及系统

Also Published As

Publication number Publication date
DE112022000624T5 (de) 2024-01-25
CN112874369A (zh) 2021-06-01
JP2024503017A (ja) 2024-01-24
KR20230122165A (ko) 2023-08-22
CN112874369B (zh) 2022-08-05

Similar Documents

Publication Publication Date Title
WO2022152065A1 (zh) 一种充电管理系统的充电与供能优化方法及装置
Bibak et al. A comprehensive analysis of Vehicle to Grid (V2G) systems and scholarly literature on the application of such systems
Zheng et al. A novel real-time scheduling strategy with near-linear complexity for integrating large-scale electric vehicles into smart grid
CN110649641B (zh) 基于源网荷储协同服务的电动汽车快充站储能系统及其方法
CN103559567B (zh) 电网对电动汽车充电站的管理系统的管理方法
WO2015081740A1 (zh) 电动汽车充放电控制系统及方法
CN106515492B (zh) 一种基于cps的电动汽车充电方法
CN103337890B (zh) 一种电动出租车充电站有序充电系统及方法
CN111497671B (zh) 基于车牌自动识别与引导的电动汽车有序充电方法与系统
Liang et al. A calculation model of charge and discharge capacity of electric vehicle cluster based on trip chain
CN112819203B (zh) 一种基于深度学习的充电管理系统及方法
CN109560577B (zh) 一种交直流混合分布式可再生能源系统的控制方法及系统
CN112994097A (zh) 一种基于智能配变终端系统的高比例分布式光伏协同控制方法
CN114056161A (zh) 一种充电桩有序充电系统及控制方法
CN113437754A (zh) 一种基于台区智能融合终端的电动汽车有序充电方法及系统
CN114429274A (zh) 基于多种资源聚合的虚拟电厂调节能力评估方法及系统
CN114498768A (zh) 一种区域智能变电站源荷储优化运行策略生成方法及装置
Al-Rubaye et al. Power interchange analysis for reliable vehicle-to-grid connectivity
CN113872228A (zh) 一种应用于电网调峰调频的电动汽车调度方法和装置
CN116923168B (zh) 基于变电站联网的充电桩电能调度系统及其调度方法
CN117057547A (zh) 智慧能源服务平台多形态负荷资源调度模型构建方法、装置、存储介质
CN111497668A (zh) 车辆充电管理方法、装置、计算机设备和存储介质
Striani et al. Wind Based Charging via Autonomously Controlled EV Chargers under Grid Constraints
Wang et al. Dynamic electric vehicles charging load allocation strategy for residential area
Yusuf et al. Analyses and Applications of Plug-in Electric Vehicle Charging Stations' User Behavior in a Large University Campus Community

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22738946

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023541706

Country of ref document: JP

ENP Entry into the national phase

Ref document number: 20237026122

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 112022000624

Country of ref document: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22738946

Country of ref document: EP

Kind code of ref document: A1