CN117254529A - Power distribution network real-time scheduling method and system considering carbon emission and uncertainty - Google Patents
Power distribution network real-time scheduling method and system considering carbon emission and uncertainty Download PDFInfo
- Publication number
- CN117254529A CN117254529A CN202311206448.4A CN202311206448A CN117254529A CN 117254529 A CN117254529 A CN 117254529A CN 202311206448 A CN202311206448 A CN 202311206448A CN 117254529 A CN117254529 A CN 117254529A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- power distribution
- scheduling
- real
- power
- 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.)
- Withdrawn
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 118
- 238000000034 method Methods 0.000 title claims abstract description 58
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 55
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 53
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000005457 optimization Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 27
- 230000007246 mechanism Effects 0.000 claims abstract description 20
- 230000002787 reinforcement Effects 0.000 claims abstract description 15
- 230000009471 action Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims abstract description 11
- 230000004044 response Effects 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000005611 electricity Effects 0.000 claims description 14
- 238000005286 illumination Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 10
- 230000007613 environmental effect Effects 0.000 claims description 9
- 239000002699 waste material Substances 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 230000010485 coping Effects 0.000 abstract description 2
- 238000010248 power generation Methods 0.000 description 6
- 230000002776 aggregation Effects 0.000 description 4
- 238000004220 aggregation Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method 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
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
-
- 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
- B60L53/50—Charging stations characterised by energy-storage or power-generation means
- B60L53/51—Photovoltaic means
-
- 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
- B60L53/50—Charging stations characterised by energy-storage or power-generation means
- B60L53/52—Wind-driven generators
-
- 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
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
- H02J3/144—Demand-response operation of the power transmission or distribution network
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
- H02J3/322—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means the battery being on-board an electric or hybrid vehicle, e.g. vehicle to grid arrangements [V2G], power aggregation, use of the battery for network load balancing, coordinated or cooperative battery charging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- 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
-
- 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
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
-
- 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
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/40—The network being an on-board power network, i.e. within a vehicle
- H02J2310/48—The network being an on-board power network, i.e. within a vehicle for electric vehicles [EV] or hybrid vehicles [HEV]
-
- 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
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
- H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
- H02J2310/58—The condition being electrical
- H02J2310/60—Limiting power consumption in the network or in one section of the network, e.g. load shedding or peak shaving
-
- 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
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
- H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
- H02J2310/62—The condition being non-electrical, e.g. temperature
- H02J2310/64—The condition being economic, e.g. tariff based load management
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Economics (AREA)
- Transportation (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a real-time scheduling method and a real-time scheduling system for a power distribution network, which take carbon emission and uncertainty into account, and provides a mathematical planning model for optimizing scheduling of the power distribution network, which takes new energy output uncertainty into account; a power distribution network real-time optimization scheduling model based on a Markov decision process is constructed in a mode of state, action, rewards and the like, and a model foundation is provided for optimization training of a subsequent deep reinforcement learning algorithm; aiming at the characteristics of high real-time performance and high complexity of a power distribution network scheduling task, a mixed differential evolution-depth deterministic strategy gradient function algorithm mixed with various improved mechanisms is provided, and a power distribution network real-time scheduling strategy is formulated through optimization training; the power distribution network uncertainty resource module system consisting of the photovoltaic output module, the wind power output module and the electric vehicle charging station system module is constructed. The invention improves the coping capability of the power distribution network to the uncertainty of new energy output, can effectively reduce the wind and light discarding phenomenon of the power distribution network and improves the new energy consumption rate.
Description
Technical Field
The invention belongs to the technical field of power distribution network operation scheduling, and particularly relates to a power distribution network real-time scheduling method and system considering carbon emission and uncertainty.
Background
Compared with the traditional power generation mode, the new energy power generation has the advantages of energy conservation, environmental protection, regeneration and the like, and is an important path for reducing the carbon emission level. However, the new energy power generation has quite large instability, the output of the photovoltaic is greatly influenced by external factors such as illumination intensity, temperature and the like, the efficiency of wind power depends on real-time wind speed, and the wind power generation has obvious intermittence and instability. Therefore, under the background that new energy sources such as wind and light are accessed in a large scale and the permeability of the electric automobile is gradually improved, the research and flexible deployment of the power distribution network scheduling strategy are carried out, the coping capacity of the power grid to uncertainty factors can be improved, and the achievement of a power-assisted double-carbon target can be achieved.
The existing power distribution network optimization scheduling technology mainly depends on a traditional mathematical programming model, essentially belongs to an offline method with long operation time consumption, and is difficult to realize flexible deployment of a power distribution network scheduling strategy and quick response of an electric vehicle charging station. The Chinese patent of the invention with publication number of CN116683441A discloses a dispatching optimization method of an electric automobile aggregator facing carbon emission constraint, which comprises the following steps: s1, constructing an electric automobile aggregation model according to energy storage characteristics and delay characteristics of electric automobile resources; s2, constructing a power distribution network carbon flow model, and calculating the carbon potential and the carbon emission of the electric automobile aggregation model based on the power distribution network carbon flow model; s3, constructing a collaborative optimization double-layer model of the electric vehicle aggregation business and the power distribution network according to the electric vehicle aggregation model and the power distribution network carbon flow model; and S4, solving the electric automobile aggregator and power distribution network collaborative optimization double-layer model through a reinforcement learning method based on an augmented Lagrangian equation. The patent can ensure that the electric automobile polymerizer can minimize the charging cost under the constraint of meeting the charging requirement and the total carbon emission; on the premise of meeting the carbon emission constraint, the charging planning with the minimum operation cost is realized, meanwhile, the optimal scheduling of the power distribution network is realized, and the resource utilization efficiency of the energy system is improved.
The invention adopts reinforcement learning technology to realize real-time quick response of the dispatching strategy and reduce carbon emission of the electric automobile cluster. However, the scheme only considers the electric automobile resources at the electricity utilization side, lacks consideration of wind-light and other distributed new energy sources, and is difficult to solve the problem of uncertainty of the new energy sources in practical application. In addition, the scheme is based on an augmented Lagrangian equation, two groups of neural networks are adopted to approach the penalty value function, and the problems of low training efficiency and reduced convergence performance exist.
Disclosure of Invention
The invention mainly aims to solve the problem that flexible deployment of a power distribution network scheduling strategy and quick response of an electric vehicle charging station are difficult to realize in the prior art, and provides a power distribution network multi-resource real-time optimal scheduling method and system based on a hybrid DE-DDPG algorithm, which are used for formulating the power distribution network multi-resource optimal scheduling strategy and developing a power distribution network real-time scheduling method and system considering new energy uncertainty.
In order to achieve the above object, the technical scheme of the present invention is as follows:
the invention relates to a real-time scheduling method and a real-time scheduling system for a power distribution network, which take carbon emission and uncertainty into account, wherein the method comprises the following steps of:
s1: establishing a power distribution network optimal scheduling mathematical programming model considering carbon emission reduction;
s2: constructing a real-time optimal scheduling model of the power distribution network based on a Markov decision process;
s3: and a deep reinforcement learning mixed DE-DDPG algorithm is provided for training and solving, and a real-time scheduling scheme is formulated.
As an preferable technical solution, in the step S1, a modeling process of the power distribution network optimization scheduling mathematical programming model considering carbon emission reduction is represented as follows:
s1.1 distribution network scheduling optimization target
And (3) establishing an optimization target of an optimization scheduling model of the power distribution network by taking the reduction of the carbon emission level and the comprehensive operation cost of the system as targets.
1) Minimum carbon emission of system
Wherein: t is the total step length; n is the total node of the system;the dynamic carbon emission factor of the power distribution network is the unit kg/kWh; p (P) i,t Injecting power for the node; Δt is the time interval.
2) Minimum system comprehensive operation cost
Wherein:and->The method comprises the steps of respectively purchasing electricity cost of an upper power grid, discarding new energy and punishing electricity and charging station demand response cost; pi t The time-sharing electricity price is; pi curt Penalty coefficients for discarding electricity; />And->Discarding electric power for PV and WT respectively; omega shape PV And omega WT Respectively PV and WT node sets; pi CS Responding to the cost coefficient for charging station demand; />And->The original load and the demand response load of the charging station are respectively; i epsilon omega CS Is a collection of charging stations.
S1.2 distribution network scheduling constraint conditions
4) Tidal current constraint
Wherein: p (P) i,t And Q is equal to i,t Injecting active power and reactive power into the nodes respectively; g ij And B is connected with ij Branch conductance and susceptance, respectively; θ ij Representing the phase angle difference of the branch ij.
5) Voltage current constraint
Wherein: i ij,t The current amplitude is the branch current amplitude;and->The upper and lower limits of the current, respectively.
6) Charging station demand response constraints
As an preferable technical solution, the modeling process of the real-time optimal scheduling model of the power distribution network based on the markov decision process in the step S2 is represented as follows:
s2.1 State
Environmental state s t The intelligent power distribution network real-time information sensing system is characterized in that the intelligent body senses the power distribution network real-time information and comprises a power distribution network real-time state, new energy output and charging station energy upper and lower limits:
wherein:and->Photovoltaic and wind power output respectively; />And->The upper and lower limits of the charging station demand response capability are respectively provided.
S2.2 action
According to the environmental state s t The real-time scheduling scheme formulated by the intelligent agent for the power distribution network scheduling center is decision action a t . In the present invention, the actions include new energy waste and charging station dispatch capacity:
wherein:capacity is scheduled for charging stations.
S2.3 rewards
In the execution of action a t The real-time feedback of the environment to the intelligent agent is then rewarded r t . In the present invention, rewards are rewarded by carbon emission reductionIntegrated operation cost r with distribution network t cost The composition is as follows:
wherein:the rewarding coefficient is reduced for carbon emission, and the unit is per kg; />To optimize node load before scheduling.
The process of the deep reinforcement learning mixed DE-DDPG solving algorithm in the step S3 is expressed as follows as a preferable technical scheme:
aiming at the characteristics of high real-time performance and high complexity of a power distribution network scheduling task, the invention provides a deep reinforcement learning hybrid DE-DDPG algorithm mixed with various improved mechanisms, and real-time scheduling of the power distribution network is realized through the optimized training of a DRL intelligent agent.
S3.1 learning rate decay mechanism
The setting of the learning rate directly influences the stability and convergence performance of the algorithm, the too large value can cause over learning, influence the stability of the algorithm, and the too small value can reduce the convergence speed of the algorithm. Therefore, the invention provides a learning rate attenuation model to adapt to learning ability of an intelligent agent in different training periods.
Wherein: alpha n Learning rate for each round; alpha 0 Is the initial learning rate; phi is the attenuation coefficient; n (N) d For the number of decay rounds.
S3.2 DE experience inheritance mechanism
Although the solution speed of the DE algorithm is slower, the solution quality of the DE algorithm is far higher than that of DDPG intelligent agent in the early training stage. Therefore, before the DRL agent formally trains, the DE algorithm is adopted to solve the power distribution network optimization scheduling problem under the random scene, and the obtained solving sample (s j ,a j ,r j ,s j+1 ) And storing the learning result into an experience pool of the DDPG algorithm for learning. Therefore, the DDPG intelligent agent in the initial training stage inherits the solving experience of the DE algorithm through the learning sample, and the convergence performance of the algorithm is greatly improved.
S3.3 mixed DE-DDPG algorithm training process
In the training process, an experience inheritance mechanism is adopted to initialize Critic and Actor networks. Secondly, the agent observes the distribution network environment s t And make scheduling decision a t At the time of obtaining the prize r t And then, carrying out network updating on the intelligent agent. And finally, attenuating the learning rate based on a learning rate attenuation mechanism after the whole-day scheduling is completed, and repeating the steps until the training is completed.
The invention discloses a multi-resource coordination optimization system of an electric vehicle energy station based on a hybrid neural network, which is characterized by comprising the following components:
s1: the photovoltaic output module is used for outputting the output of the photovoltaic system;
s2: the wind power output module is used for outputting the output of the wind power system;
s3: and the electric automobile charging station module is used for carrying out cluster scheduling on electric automobiles.
As an preferable technical scheme, the real-time scheduling system of the power distribution network, which takes into account carbon emission and uncertainty, the modeling process of the photovoltaic output module in the step S1 is represented as follows:
s1.1 photovoltaic output calculation module
The output power of the photovoltaic is mainly affected by the illumination intensity G, and the probability density function can be described by Beta distribution:
wherein: g max Is the maximum illumination intensity; the shape parameters of the Beta distribution for alpha and Beta can be obtained by the following formula:
wherein: sigma (sigma) 2 And mu 2 Standard deviation and mean of historical illumination intensity.
Further, photovoltaic output power P PV Can be expressed as:
wherein: p (P) STC The photovoltaic rated power is the photovoltaic rated power in the standard environment; g STC For standard illumination intensity (1 kW/m) 2 ) The method comprises the steps of carrying out a first treatment on the surface of the Phi represents the power-temperature coefficient; t (T) c And T is r The actual temperature and the standard temperature (25 ℃) of the solar panel are respectively.
As a preferable technical solution, the real-time scheduling system for a power distribution network, which takes into account carbon emission and uncertainty, is characterized in that the modeling process of the wind power generation module in step S2 is as follows:
s2.1 wind power output calculation module
The active output of wind power is mainly affected by wind speed, and the wind speed probability density function can be described by Weibull distribution as shown in a formula (18):
wherein: v is wind speed; k and c are the shape parameter and the scale parameter, respectively, and can be obtained by the following formula:
wherein: Γ represents a Gamma function; sigma (sigma) 1 And mu 1 The distribution is the standard deviation and the mean value of the historical wind speed data.
Further, wind power output power P WT Can be expressed as:
wherein: v in And v out The cut-in wind speed and the cut-out wind speed are respectively represented; p (P) r And v r Rated power and rated wind speed, respectively.
As a preferable technical solution, the real-time dispatching system for the power distribution network, which takes into account carbon emission and uncertainty, is characterized in that the modeling process of the electric vehicle charging station module in the step S3 is as follows:
s3.1 initial State of Charge Module for Battery
The electric vehicle on a large scale has good adjustable characteristics, and the initial battery charge state of the electric vehicle reaching the charging station is subject to logarithmic normal distribution.
Wherein: SOC (State of Charge) 0 Initial SOC when the electric vehicle arrives at the charging station; mu and sigma are the logarithmic mean and standard deviation, respectively, taken as 3.2 and 0.48, respectively.
S3.2 energy boundary calculation module of single electric automobile
Energy adjustable upper and lower limits of single electric automobileThe following is shown:
wherein:upper and lower energy limits for charging the jth EV at the ith charging station,/->Represents the upper limit of->Represents a lower limit; />And->Representing start and end charging times, respectively; />The charging time is the charging time; e, e j,max Is the maximum electric quantity of the vehicle.
S3.3 charging station energy boundary calculation module
Charging station demand response upper and lower limits composed of electric automobile clustersThe following is shown:
wherein: j epsilon omega i Representing all EV sets charged at charging station i.
Compared with the prior art, the invention has the following beneficial effects:
1) In order to assist the double-carbon target, the power distribution network optimization scheduling model is provided with the optimization target of reducing the carbon emission level and the comprehensive operation cost of the system, and the economical efficiency and the low carbon performance of the power distribution network operation can be effectively improved. In addition, the optimization model is converted into a Markov decision process, so that the anti-disturbance capability of the power distribution network to the real-time fluctuation of wind and light output and the random charging of the electric automobile user group is improved.
2) The intelligent agent based on deep reinforcement learning can sense the comprehensive state of the power distribution network-distributed energy source-charging station in real time, provides an information basis for an algorithm to make an optimal decision scheme, and improves the comprehensive sensing and learning capacity of a power distribution network dispatching center on the environmental state.
3) The deep reinforcement learning DDPG algorithm is improved, a learning rate attenuation mechanism and an experience inheritance mechanism are introduced, a mixed DE-DDPG algorithm is provided, and convergence performance of the algorithm in the early stage of training and stability of the algorithm in the later stage are improved. The power distribution network real-time scheduling method and system based on the mixed DE-DDPG can effectively reduce the wind and light discarding phenomenon of the power distribution network and improve the new energy consumption rate.
Drawings
FIG. 1 is a training flow chart of the hybrid DE-DDPG algorithm of the present invention;
FIG. 2 is a topology of an IEEE 33 node system in accordance with a modification of the present invention;
FIG. 3 is a training prize graph of the hybrid DE-DDPG algorithm of the present invention;
FIG. 4 is a graph showing the comparison of the amount of light and power of the wind and the light before and after the optimization of the invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the embodiments of the present invention are not limited thereto.
The invention relates to a real-time scheduling method and a real-time scheduling system for a power distribution network, which take carbon emission and uncertainty into account, wherein the method comprises the following steps of:
s1: establishing a power distribution network optimal scheduling mathematical programming model considering carbon emission reduction;
s2: constructing a real-time optimal scheduling model of the power distribution network based on a Markov decision process;
s3: and a deep reinforcement learning mixed DE-DDPG algorithm is provided for training and solving, and a real-time scheduling scheme is formulated.
As an preferable technical solution, in the step S1, a modeling process of the power distribution network optimization scheduling mathematical programming model considering carbon emission reduction is represented as follows:
s1.1 distribution network scheduling optimization target
And (3) establishing an optimization target of an optimization scheduling model of the power distribution network by taking the reduction of the carbon emission level and the comprehensive operation cost of the system as targets.
1) Minimum carbon emission of system
Wherein: t is the total step length; n is the total node of the system;the dynamic carbon emission factor of the power distribution network is the unit kg/kWh; p (P) i,t Injecting power for the node; Δt is the time interval.
2) Minimum system comprehensive operation cost
Wherein:and->The method comprises the steps of respectively purchasing electricity cost of an upper power grid, discarding new energy and punishing electricity and charging station demand response cost; pi t The time-sharing electricity price is; pi curt Penalty coefficients for discarding electricity; />And->Discarding electric power for PV and WT respectively; omega shape PV And omega WT Respectively PV and WT node sets; pi CS Responding to the cost coefficient for charging station demand; />And->The original load and the demand response load of the charging station are respectively; i epsilon omega CS Is a collection of charging stations.
S1.2 distribution network scheduling constraint conditions
7) Tidal current constraint
Wherein: p (P) i,t And Q is equal to i,t Injecting active power and reactive power into the nodes respectively; g ij And B is connected with ij Branch conductance and susceptance, respectively; θ ij Representing the phase angle difference of the branch ij.
8) Voltage current constraint
Wherein: i ij,t The current amplitude is the branch current amplitude;and->The upper and lower limits of the current, respectively.
9) Charging station demand response constraints
As an preferable technical solution, the modeling process of the real-time optimal scheduling model of the power distribution network based on the markov decision process in the step S2 is represented as follows:
s2.1 State
Environmental state s t The intelligent power distribution network real-time information sensing system is characterized in that the intelligent body senses the power distribution network real-time information and comprises a power distribution network real-time state, new energy output and charging station energy upper and lower limits:
wherein:and->Photovoltaic and wind power output respectively; />And->The upper and lower limits of the charging station demand response capability are respectively provided.
S2.2 action
According to the environmental state s t The real-time scheduling scheme formulated by the intelligent agent for the power distribution network scheduling center is decision action a t . In the present invention, the actions include new energy waste and charging station dispatch capacity:
wherein:capacity is scheduled for charging stations.
S2.3 rewards
In the execution of action a t The real-time feedback of the environment to the intelligent agent is then rewarded r t . In the present invention, rewards are rewarded by carbon emission reductionIntegrated operation cost with distribution network>The composition is as follows:
wherein:the rewarding coefficient is reduced for carbon emission, and the unit is per kg; />To optimize node load before scheduling.
The process of the deep reinforcement learning mixed DE-DDPG solving algorithm in the step S3 is expressed as follows as a preferable technical scheme:
aiming at the characteristics of high real-time performance and high complexity of a power distribution network scheduling task, the invention provides a deep reinforcement learning hybrid DE-DDPG algorithm mixed with various improved mechanisms, and real-time scheduling of the power distribution network is realized through the optimized training of a DRL intelligent agent.
S3.1 learning rate decay mechanism
The setting of the learning rate directly influences the stability and convergence performance of the algorithm, the too large value can cause over learning, influence the stability of the algorithm, and the too small value can reduce the convergence speed of the algorithm. Therefore, the invention provides a learning rate attenuation model to adapt to learning ability of an intelligent agent in different training periods.
Wherein: alpha n Learning rate for each round; alpha 0 Is the initial learning rate; phi is the attenuation coefficient; n (N) d For the number of decay rounds.
S3.2 DE experience inheritance mechanism
Although the solution speed of the DE algorithm is slower, the solution quality of the DE algorithm is far higher than that of DDPG intelligent agent in the early training stage. Therefore, before the DRL agent formally trains, the DE algorithm is adopted to solve the power distribution network optimization scheduling problem under the random scene, and the obtained solving sample (s j ,a j ,r j ,s j+1 ) And storing the learning result into an experience pool of the DDPG algorithm for learning. Therefore, the DDPG intelligent agent in the initial training stage inherits the solving experience of the DE algorithm through the learning sample, and the convergence performance of the algorithm is greatly improved.
S3.3 mixed DE-DDPG algorithm training process
In the training process, an experience inheritance mechanism is adopted to initialize Critic and Actor networks. Secondly, the intelligent body observes the distribution networkEnvironment s t And make scheduling decision a t At the time of obtaining the prize r t And then, carrying out network updating on the intelligent agent. And finally, attenuating the learning rate based on a learning rate attenuation mechanism after the whole-day scheduling is completed, and repeating the steps until the training is completed.
The invention discloses a multi-resource coordination optimization system of an electric vehicle energy station based on a hybrid neural network, which is characterized by comprising the following components:
s1: the photovoltaic output module is used for outputting the output of the photovoltaic system;
s2: the wind power output module is used for outputting the output of the wind power system;
s3: and the electric automobile charging station module is used for carrying out cluster scheduling on electric automobiles.
As an preferable technical scheme, the real-time scheduling system of the power distribution network, which takes into account carbon emission and uncertainty, the modeling process of the photovoltaic output module in the step S1 is represented as follows:
s1.1 photovoltaic output calculation module
The output power of the photovoltaic is mainly affected by the illumination intensity G, and the probability density function can be described by Beta distribution:
wherein: g max Is the maximum illumination intensity; the shape parameters of the Beta distribution for alpha and Beta can be obtained by the following formula:
wherein: sigma (sigma) 2 And mu 2 Standard deviation and mean of historical illumination intensity.
Further, photovoltaic output power P PV Can be expressed as:
wherein: p (P) STC The photovoltaic rated power is the photovoltaic rated power in the standard environment; g STC For standard illumination intensity (1 kW/m) 2 ) The method comprises the steps of carrying out a first treatment on the surface of the Phi represents the power-temperature coefficient; t (T) c And T is r The actual temperature and the standard temperature (25 ℃) of the solar panel are respectively.
As a preferable technical solution, the real-time scheduling system for a power distribution network, which takes into account carbon emission and uncertainty, is characterized in that the modeling process of the wind power generation module in step S2 is as follows:
s2.1 wind power output calculation module
The active output of wind power is mainly affected by wind speed, and the wind speed probability density function can be described by Weibull distribution as shown in a formula (18):
wherein: v is wind speed; k and c are the shape parameter and the scale parameter, respectively, and can be obtained by the following formula:
wherein: Γ represents a Gamma function; sigma (sigma) 1 And mu 1 The distribution is the standard deviation and the mean value of the historical wind speed data.
Further, wind power output power P WT Can be expressed as:
wherein: v in And v out The cut-in wind speed and the cut-out wind speed are respectively represented; p (P) r And v r Rated power and rated wind speed, respectively.
As a preferable technical solution, the real-time dispatching system for the power distribution network, which takes into account carbon emission and uncertainty, is characterized in that the modeling process of the electric vehicle charging station module in the step S3 is as follows:
s3.1 initial State of Charge Module for Battery
The electric vehicle on a large scale has good adjustable characteristics, and the initial battery charge state of the electric vehicle reaching the charging station is subject to logarithmic normal distribution.
Wherein: SOC (State of Charge) 0 Initial SOC when the electric vehicle arrives at the charging station; mu and sigma are the logarithmic mean and standard deviation, respectively, taken as 3.2 and 0.48, respectively.
S3.2 energy boundary calculation module of single electric automobile
Energy adjustable upper and lower limits of single electric automobileThe following is shown:
wherein:upper and lower energy limits for charging the jth EV at the ith charging station,/->Represents the upper limit of->Represents a lower limit; />And->Representing start and end charging times, respectively; />The charging time is the charging time; e, e j,max Is the maximum electric quantity of the vehicle.
S3.3 charging station energy boundary calculation module
Charging station demand response upper and lower limits composed of electric automobile clustersThe following is shown:
wherein: j epsilon omega i Representing all EV sets charged at charging station i.
Application examples:
as shown in fig. 1, in the training process, the Critic and Actor networks are initialized by an experience inheritance mechanism. Secondly, the agent observes the distribution network environment s t And make scheduling decision a t At the time of obtaining the prize r t And then, carrying out network updating on the intelligent agent. And finally, attenuating the learning rate based on a learning rate attenuation mechanism after the whole-day scheduling is completed, and repeating the steps until the training is completed.
To verify the effectiveness of the proposed strategy, a simulation test was performed using a modified IEEE 33 node distribution network system, the system topology shown in FIG. 2, wherein the PV power rating is 350kW, the WT power rating is 300kW, and the CS capacity is 10×30kW. Taking out the abandoned electricity punishment coefficient to be 0.55, enabling the charging station demand response cost coefficient to be 0.85, and enabling the carbon emission reduction rewarding coefficient to be 1;
the discount rate of the mixed DE-DDPG algorithm is set to be 0.98, the soft update coefficient is set to be 0.002, the empirical pool capacity is set to be 5000, the initial learning rate is set to be 0.02, the attenuation coefficient is set to be 0.6, the attenuation round is set to be 220, the DE population scale is set to be 80, and the maximum iteration number is set to be 200. Figure 3 shows the training prize curve of the hybrid DE-DDPG algorithm. It can be seen that, thanks to the proposed inherited mechanism of experience, the agent rewards rise rapidly after a short fluctuation, gradually stabilize after 300 rounds, with an average reward of-232.28. This demonstrates that the agent is now able to make an excellent decision scheme based on the environmental information.
And carrying out online real-time scheduling on the power distribution network by using the offline trained mixed DE-DDPG algorithm, so that the pre-and post-optimization wind and light discarding electric quantity pairs such as shown in figure 4 can be obtained. The graph shows that the system has obvious wind and light discarding phenomenon before the optimal scheduling, and the total daily electric discarding quantity reaches 409.15kWh. The method senses the state of the power distribution network in real time through the DRL agent and makes a decision, so that the phenomena of air abandonment at night and light abandonment at noon are obviously reduced, the total daily electric abandoning quantity is only 154.85, and compared with the method which is reduced by 62.15% before optimization, the effectiveness of the method in improving clean energy consumption and reducing carbon emission is verified.
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (10)
1. The real-time scheduling method of the power distribution network considering carbon emission and uncertainty is characterized by comprising the following steps of:
s1: establishing a power distribution network optimal scheduling mathematical programming model considering carbon emission reduction;
s2: constructing a real-time optimal scheduling model of the power distribution network based on a Markov decision process;
s3: the deep reinforcement learning mixed DE-DDPG algorithm is put forward for training and solving, and a real-time scheduling scheme is formulated;
the deep reinforcement learning mixed DE-DDPG solving algorithm in the step S3 comprises the following steps:
s3.1 learning rate decay mechanism
The setting of the learning rate directly influences the stability and convergence performance of the algorithm, the too large value of the learning rate can cause over-learning to influence the stability of the algorithm, and the too small value can reduce the convergence speed of the algorithm;
wherein: alpha n Learning rate for each round; alpha 0 Is the initial learning rate; phi is the attenuation coefficient; n (N) d For the number of decay rounds.
2. The real-time scheduling method for power distribution network according to claim 1, wherein the mathematical planning model for power distribution network optimization scheduling considering carbon emission reduction in step S1 comprises:
s1.1 distribution network scheduling optimization target
The method comprises the steps of taking the reduction of the carbon emission level and the comprehensive operation cost of a system as targets, and establishing an optimization target of an optimization scheduling model of the power distribution network;
1) Minimum carbon emission of system
Wherein: t is the total step length; n is the total node of the system;the dynamic carbon emission factor of the power distribution network is the unit kg/kWh; p (P) i,t Injecting power for the node; Δt is the time interval;
2) Minimum system comprehensive operation cost
Wherein:and->The method comprises the steps of respectively purchasing electricity cost of an upper power grid, discarding new energy and punishing electricity and charging station demand response cost; pi t The time-sharing electricity price is; pi curt Penalty coefficients for discarding electricity; />And->Discarding electric power for PV and WT respectively; omega shape PV And omega WT Respectively PV and WT node sets; pi CS Responding to the cost coefficient for charging station demand; />And->The original load and the demand response load of the charging station are respectively; i epsilon omega CS Is a collection of charging stations.
3. The real-time scheduling method for power distribution network considering carbon emission and uncertainty as claimed in claim 2, wherein the constraint condition of scheduling of power distribution network is S1.2
1) Tidal current constraint
Wherein: p (P) i,t And Q is equal to i,t Injecting active power and reactive power into the nodes respectively; g ij And B is connected with ij Branch conductance and susceptance, respectively; θ ij Representing the phase angle difference of the branch ij;
2) Voltage current constraint
Wherein: i ij,t The current amplitude is the branch current amplitude;and->The upper and lower limits of the current are respectively;
3) Charging station demand response constraints
4. The real-time scheduling method for power distribution network according to claim 1, wherein the real-time optimal scheduling model for power distribution network based on markov decision process in step S2 comprises:
s2.1 State
Environmental state s t The intelligent power distribution network real-time information sensing system is characterized in that the intelligent body senses the power distribution network real-time information and comprises a power distribution network real-time state, new energy output and charging station energy upper and lower limits:
wherein:and->Photovoltaic and wind power output respectively; />And->The upper limit and the lower limit of the charging station demand response capability are respectively set;
s2.2 action
According to the environmental state s t The real-time scheduling scheme formulated by the intelligent agent for the power distribution network scheduling center is decision action a t The method comprises the steps of carrying out a first treatment on the surface of the The actions include new energy waste amount and charging station scheduling capacity:
wherein:scheduling capacity for the charging station;
s2.3 rewards
In the execution of action a t The real-time feedback of the environment to the intelligent agent is then rewarded r t Rewards reduced rewards from carbon emissionsIntegrated operation cost r with distribution network t cost The composition is as follows:
wherein:the rewarding coefficient is reduced for carbon emission, and the unit is per kg; />To optimize node load before scheduling.
5. The real-time scheduling method for power distribution network according to claim 1, wherein the deep reinforcement learning hybrid DE-DDPG solving algorithm in step S3 further comprises:
s3.2 DE experience inheritance mechanism
Before the formal training of the DRL agent, the DE algorithm is adopted to solve the power distribution network optimization scheduling problem under the random scene, and the obtained solving sample (s j ,a j ,r j ,s j+1 ) The learning model is stored in an experience pool of the DDPG algorithm for learning, and the DDPG agent in the initial stage of training inherits the solving experience of the DE algorithm through a learning sample.
6. The real-time scheduling method for power distribution network according to claim 5, wherein the deep reinforcement learning hybrid DE-DDPG solving algorithm in step S3 further comprises:
s3.3 mixed DE-DDPG algorithm training process
In the training process, firstly, initializing Critic and Actor networks by adopting an experience inheritance mechanism;
secondly, the agent observes the distribution network environment s t And make scheduling decision a t At the time of obtaining the prize r t Then, network updating is carried out on the intelligent agent;
and finally, attenuating the learning rate based on a learning rate attenuation mechanism after the whole-day scheduling is completed, and repeating the steps until the training is completed.
7. A real-time scheduling system for a power distribution network that accounts for carbon emissions and uncertainties, comprising:
the photovoltaic output module is used for outputting the output of the photovoltaic system; the output power of the photovoltaic is affected by the illumination intensity G, and the probability density function is described by Beta distribution:wherein: g max Is the maximum illumination intensity; the shape parameters of the Beta distribution are alpha and Beta, and are obtained by the following formula (16):
wherein: sigma (sigma) 2 And mu 2 Standard deviation and mean value of historical illumination intensity; photovoltaic output power P PV Expressed as:
wherein: p (P) STC The photovoltaic rated power is the photovoltaic rated power in the standard environment; g STC For standard illumination intensity, 1kW/m 2 The method comprises the steps of carrying out a first treatment on the surface of the Phi represents the power-temperature coefficient; t (T) c And T is r The actual temperature and the standard temperature of the solar panel are 25 ℃ respectively;
the wind power output module is used for outputting the output of the wind power system;
and the electric automobile charging station module is used for carrying out cluster scheduling on electric automobiles.
8. The real-time scheduling system for power distribution networks, accounting for carbon emissions and uncertainty as claimed in claim 7, wherein the wind power output module calculates:
the active output of wind power is affected by wind speed, and a Weibull distribution is adopted to describe a wind speed probability density function as shown in a formula (18):
wherein: v is wind speed; k and c are a shape parameter and a scale parameter, respectively, and are obtained by the following formula (19):
wherein: Γ represents a Gamma function; sigma (sigma) 1 And mu 1 The distribution is the standard deviation and the average value of the historical wind speed data;
wind power output power P WT Expressed as:
wherein: v in And v out The cut-in wind speed and the cut-out wind speed are respectively represented; p (P) r And v r Rated power and rated wind speed, respectively.
9. The real-time distribution network scheduling system accounting for carbon emissions and uncertainty as set forth in claim 7, wherein the electric vehicle charging station module comprises: the system comprises a battery initial charge state module, a single electric vehicle energy boundary calculation module and a charging station energy boundary calculation module.
10. A real-time scheduling system for power distribution networks, accounting for carbon emissions and uncertainty as defined in claim 9,
battery initial state of charge module calculation
The large-scale electric automobile has good adjustable characteristics, and the initial battery charge state of the electric automobile reaching the charging station is subjected to lognormal distribution;
wherein: SOC (State of Charge) 0 Initial SOC when the electric vehicle arrives at the charging station; mu and sigma are the logarithmic mean and standard deviation, respectively;
calculation of energy boundary calculation module of single electric automobile
Energy adjustment upper and lower limits of single electric automobileThe following is shown:
wherein:upper and lower energy limits for charging the jth EV at the ith charging station,/->Represents the upper limit of->Represents a lower limit; />And->Representing start and end charging times, respectively; />For the duration of charging；e j,max The maximum electric quantity of the vehicle;
charging station energy boundary calculation module calculates
Charging station demand response upper and lower limits composed of electric automobile clustersThe following is shown:
wherein: j epsilon omega i Representing all EV sets charged at charging station i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311206448.4A CN117254529A (en) | 2023-09-19 | 2023-09-19 | Power distribution network real-time scheduling method and system considering carbon emission and uncertainty |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311206448.4A CN117254529A (en) | 2023-09-19 | 2023-09-19 | Power distribution network real-time scheduling method and system considering carbon emission and uncertainty |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117254529A true CN117254529A (en) | 2023-12-19 |
Family
ID=89136212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311206448.4A Withdrawn CN117254529A (en) | 2023-09-19 | 2023-09-19 | Power distribution network real-time scheduling method and system considering carbon emission and uncertainty |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117254529A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118144619A (en) * | 2024-05-09 | 2024-06-07 | 山东浪潮智慧能源科技有限公司 | Low-carbon emission charging method and device for electric automobile and storage medium |
-
2023
- 2023-09-19 CN CN202311206448.4A patent/CN117254529A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118144619A (en) * | 2024-05-09 | 2024-06-07 | 山东浪潮智慧能源科技有限公司 | Low-carbon emission charging method and device for electric automobile and storage medium |
| CN118144619B (en) * | 2024-05-09 | 2024-07-23 | 山东浪潮智慧能源科技有限公司 | Low-carbon emission charging method and device for electric automobile and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hou et al. | Multi-objective economic dispatch of a microgrid considering electric vehicle and transferable load | |
| CN109347149A (en) | Micro-capacitance sensor energy storage dispatching method and device based on depth Q value network intensified learning | |
| CN109286187B (en) | Multi-subject benefit balance oriented micro-grid day-ahead economic scheduling method | |
| CN111900725B (en) | Collaborative interaction method and system for electric vehicle charging station and photovoltaic power station | |
| CN111626527A (en) | Intelligent power grid deep learning scheduling method considering fast/slow charging/discharging form of schedulable electric vehicle | |
| CN115021295B (en) | Wind farm hybrid energy storage capacity optimal configuration method and system for primary frequency modulation | |
| CN107919675B (en) | Charging station load scheduling model comprehensively considering benefits of vehicle owners and operators | |
| CN116667325B (en) | Micro-grid-connected operation optimization scheduling method based on improved cuckoo algorithm | |
| CN107730048A (en) | A kind of random robust Optimization Scheduling of wind-powered electricity generation electric automobile association system | |
| CN109050284A (en) | A kind of electric car charge and discharge electricity price optimization method considering V2G | |
| CN116436019B (en) | Multi-resource coordination optimization method, device and storage medium | |
| CN115833244A (en) | Wind-light-hydrogen-storage system economic dispatching method | |
| CN117455183B (en) | Comprehensive energy system optimal scheduling method based on deep reinforcement learning | |
| CN117254529A (en) | Power distribution network real-time scheduling method and system considering carbon emission and uncertainty | |
| CN117291390A (en) | Scheduling decision model establishment method based on SumPree-TD 3 algorithm | |
| CN110854910B (en) | Thermal power generating unit climbing pressure relieving method under high-proportion photovoltaic grid connection | |
| CN114285093B (en) | Source network charge storage interactive scheduling method and system | |
| CN112072643A (en) | Light-storage system online scheduling method based on depth certainty gradient strategy | |
| CN114722728A (en) | Wind-solar-energy-storage hybrid energy storage capacity optimal configuration method and system | |
| CN114336597A (en) | Light storage inverter energy scheduling based on self-adaptive penalty function particle swarm algorithm | |
| CN114421502A (en) | Cooperative optimization method for micro-grid community | |
| CN115940284B (en) | Operation control strategy of new energy hydrogen production system considering time-of-use electricity price | |
| CN117172109A (en) | Capacity optimization method of off-grid photovoltaic hydrogen production system | |
| CN116960939A (en) | Multi-target particle swarm algorithm-based wind, solar and diesel storage system optimal scheduling method, equipment and storage medium | |
| CN116865271A (en) | Digital twin-drive-based micro-grid multi-agent coordination optimization control strategy |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231219 |
|
| WW01 | Invention patent application withdrawn after publication |