CN116384039A - Intelligent power grid energy optimization efficient management method based on model prediction - Google Patents
Intelligent power grid energy optimization efficient management method based on model prediction Download PDFInfo
- Publication number
- CN116384039A CN116384039A CN202211743033.6A CN202211743033A CN116384039A CN 116384039 A CN116384039 A CN 116384039A CN 202211743033 A CN202211743033 A CN 202211743033A CN 116384039 A CN116384039 A CN 116384039A
- Authority
- CN
- China
- Prior art keywords
- energy
- grid
- power
- model
- expressed
- 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.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 52
- 238000007726 management method Methods 0.000 title claims abstract description 51
- 238000010248 power generation Methods 0.000 claims abstract description 50
- 238000004146 energy storage Methods 0.000 claims abstract description 47
- 230000005611 electricity Effects 0.000 claims abstract description 45
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 43
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 41
- 238000013528 artificial neural network Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000013178 mathematical model Methods 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 32
- 230000006870 function Effects 0.000 claims description 29
- 230000005855 radiation Effects 0.000 claims description 24
- 210000004027 cell Anatomy 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 238000005265 energy consumption Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 230000003068 static effect Effects 0.000 claims description 5
- 238000007599 discharging Methods 0.000 claims description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000005520 electrodynamics Effects 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 230000002441 reversible effect Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000012300 Sequence Analysis Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 abstract description 2
- 238000005070 sampling Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000002803 fossil fuel Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 238000005868 electrolysis reaction Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Power Engineering (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a smart grid energy optimization efficient management method based on model prediction, which takes efficient energy management of a micro grid as a research object and comprises the following steps: firstly, establishing a mathematical model of the whole micro-grid, wherein each grid node of the distributed grid comprises a power utilization end, a power supply end, an energy storage end and a micro-grid; secondly, for a distributed grid-connected power generation model of unstable photovoltaic and wind power clean energy, predicting future photovoltaic power generation and wind power generation capacity through training test of an Artificial Neural Network (ANN), so as to reduce unstable factors brought by the clean power supply to a power grid; and finally, the model prediction control technology is skillfully utilized, at each sampling moment, a model prediction optimization problem is established according to the minimum energy cost and the carbon emission element, each element execution strategy is solved, the energy cost paid by a consumer is reduced, the peak pressure of the power demand is reduced, the carbon emission is minimized, and the electricity utilization comfort level of a user is improved.
Description
Technical Field
The invention belongs to the technical field of intelligent power grid energy management, and particularly relates to a model prediction-based intelligent power grid energy optimization efficient management method.
Background
Conventional power systems are inefficient due to the complete reliance on fossil fuels, and the concentrated generation of electricity away from the consumer. In this case, the power generation end often needs to be distributed to the user end through long-distance power transmission and distribution line transmission, which will take a lot of resources for constructing and maintaining all the involved systems and a lot of power transmission loss, resulting in centralized power generation generally causing more environmental pollution than distributed power generation technology. Currently, distributed power generation and consumption modes of emerging smart grids have emerged, which are smart energy management modes of such grids that are distinguished in the power market around the world by their low transmission losses and ability to intelligently provide power control for consumers.
The dependence on fossil fuel is reduced and the problem of high carbon emission is reduced through the new energy distributed micro-grid. In addition, the micro-grid can be connected with the intelligent home in a mode of grid connection of the energy island and the like. In the energy island mode, the domestic micro-grid and the commercial grid are not able to initiate the energy buying and selling mechanism. While in grid-tie mode, the microgrid may buy and sell power from an external grid. Prediction of unstable clean energy sources such as wind power and photovoltaic in micro-grids is an important task, and the selection of a prediction model is generally dependent on available data, the targets of a model network mechanism and the operation of energy planning. A large amount of data is processed through a machine learning model, meanwhile, accurate prediction analysis is provided, the correlation and the characteristics of new energy are extracted and modeled through an artificial neural network, and accurate prediction is made on the future power generation amount of the new energy.
There are currently related methods of mathematics, control theory and heuristic algorithms mainly for solving the energy management problem. Firstly, the mathematical method mainly provides an optimal solution in the aspects of energy use, renewable resource management and other tasks by using a mixed integer linear programming method, and realizes an optimal time table under dynamic electrical limitation, and meanwhile, the use comfort based on users is maintained. Mathematical and deterministic methods have problems with system and computational complexity. Secondly, a control method is adopted by a learner, and integration and control automation of renewable energy sources such as loads of photovoltaic power stations and solid oxide fuel cells in a smart grid are adopted by the learner. The energy management system adopts proportional integral and self-adaptive neural fuzzy reasoning system technology, so that the power grid is effectively balanced in supply and demand. The dynamic energy management system based on model predictive control is also designed by students and is used for connecting a grid-connected micro-grid of a residential district, and the dynamic energy management system collects data from all electric components through an intelligent metering system. However, control-based methods are computationally intensive and problem optimization is too slow. Finally, a related method of heuristic algorithm, the learner mainly uses a hierarchical architecture of cloud computing and edge computing, which provides intelligent-based autonomous strategic decisions for a large amount of information. In homes and grids, large-scale information collection, communication, processing and control is performed by agents that cooperate with energy management. Experimental results show that the agent-based solution has good application prospect in collaborative energy management.
The above-mentioned methods can achieve a certain effect in terms of energy management, however, researchers have not fully considered some key functions such as advanced metering infrastructure, prediction, and two-way communication of smart grid. And targets such as electricity rates, carbon emissions, and grid peak ratios have not been optimized by the learner at the same time. Accordingly, there is a need for an optimization technique that considers user priority, real-time electricity prices, and user comfort constraints to meet load and renewable energy generation uncertainties, to efficiently utilize energy, reduce energy costs, mitigate peak ratios, mitigate carbon emissions, and end user satisfaction to meet both power suppliers and power users.
Disclosure of Invention
In order to overcome the defects and the shortcomings in the prior art, the invention introduces a high-efficiency micro-grid energy management model to systematically schedule load and charge and discharge of the electric automobile. The smart micro-grid is equipped with controllable appliances, photovoltaic panels, wind turbine power generation, electrolysis cells, energy storage systems. The charging and discharging of the electric automobile reduces the peak load, peak average ratio, cost, energy cost and carbon emission operation of household appliances, and the energy storage system adopts real-time pricing electricity price for scheduling. Therefore, balance between power demand and supply is realized, energy cost, peak power grid ratio, carbon emission and user discomfort are reduced, and a new low-carbon environment-friendly mode is realized.
The invention aims to establish a mathematical model of a distributed power grid, wherein each power grid node comprises a power utilization end, a power supply end, an energy storage end and a micro-grid overall. And secondly, determining an unstable clean energy distributed grid-connected power generation model, such as a photovoltaic power generation model and a wind power generation model, and predicting the power generation amount of the clean energy in the future through an Artificial Neural Network (ANN). And finally, establishing a model prediction optimization problem according to the minimum energy cost, carbon emission and other elements, solving and obtaining each element execution strategy, reducing the energy cost paid by consumers, relieving the peak pressure of the power demand, minimizing the carbon emission, and improving the electricity utilization comfort level of users so as to realize a new low-carbon environment-friendly mode.
The method takes high-efficiency energy management of a micro-grid as a research object and comprises the following steps: firstly, establishing a mathematical model of the whole micro-grid, wherein each grid node of the distributed grid comprises a power utilization end, a power supply end, an energy storage end and a micro-grid; secondly, for a distributed grid-connected power generation model of unstable photovoltaic and wind power clean energy, predicting future photovoltaic power generation and wind power generation capacity through training test of an Artificial Neural Network (ANN), so as to reduce unstable factors brought by the clean power supply to a power grid; and finally, the model prediction control technology is skillfully utilized, at each sampling moment, a model prediction optimization problem is established according to the minimum energy cost and the carbon emission element, each element execution strategy is solved, the energy cost paid by a consumer is reduced, the peak pressure of the power demand is reduced, the carbon emission is minimized, and the electricity utilization comfort level of a user is improved.
The technical scheme adopted for solving the technical problems is as follows:
the intelligent power grid energy optimization efficient management method based on model prediction is characterized by comprising the following steps of:
step S1: establishing a mathematical model of the whole micro-grid, wherein each grid node of the distributed power grid comprises a power utilization end, a power supply end, an energy storage end and a power distribution end;
step S2: the method comprises the steps of determining an unstable photovoltaic and wind power distributed grid-connected power generation model, and predicting the power generation capacity of clean energy in the future through an artificial neural network ANN;
step S3: and establishing a model prediction optimization problem according to the minimum energy cost, the peak value and average ratio of the power grid and the carbon emission element, and solving to obtain an execution strategy of each element.
Further, in step S1, a smart micro-grid equipped with a household appliance, a photovoltaic array, an electrolytic cell, wind power, an electric vehicle and an energy storage device is mathematically modeled, and a model prediction optimization problem is established according to minimum energy cost, a grid peak-to-average ratio and carbon emission elements.
Further, in step S2, the solar radiation and wind speed time sequence is used as a model input to remove uncorrelated and redundant features, the selected sample feature input is divided into a training and test data set, then the training and test set is used to predict solar radiation and wind speed within the time range of the following whole day, an error between the predicted value and the actual observed value of the artificial neural network is calculated, and the enhanced differential evolution algorithm EDE is used in the optimization stage to further minimize the error.
Further, in step S3, an optimization problem is established in consideration of the energy cost, the small power grid fluctuation, the objective function of carbon emission, and the constraint of the system, and an optimal strategy is obtained by minimizing the objective function.
Further, the step S1 specifically includes the following steps:
step 1.1: the self-adaptive scheduling method based on the real-time pricing signal is characterized in that an energy management system receives a low-price signal from the real-time pricing, and immediately schedules and controls an electric appliance; the consumer schedules the smart appliances at specified time intervals to avoid high costs due to operation during peak hours; defining a user's start probability function as:
wherein S represents an intelligent electrical device, h represents an hour of the day, d represents a day of the week, W represents a day of the year,representing the time step, σ, of the predictive computation flat Standard deviation of social random factor, P season Indicating the probability of use of seasons, P hour Represents the hourly start-up probability factor, P social Represents the probability of random use of society, P step Representing the scale factor;
step 1.2: establishing a micro-grid model; the micro-grid at least comprises an electric appliance, a photovoltaic panel, wind power, an electrolytic tank, an electric automobile and an energy storage device; net energy m produced by each device in the microgrid at time t t Energy generated within the predicted time period T:
the mathematical model of the power generation amount per hour of wind power generation is expressed as:
wherein P is t wt Representing t hours of wind power generation capacity, C p Representing a wind energy conversion value, A representing a region swept by turbine blades of a wind turbine generator, V t wt Representing the wind speed at the t hour, ρ representing the air density, the power generation of wind energy satisfying the constraint:
wherein V is cut-in And V cut-out Respectively representing the speed of wind entering the blade and the speed of wind exiting the blade;
the mathematical model of the photovoltaic panel generation power is expressed as:
P t pv =η pv ×A pv ×Irr(t)×(1-0.005×(Temp(t)-25)) (4)
wherein P is t pv Represents the photovoltaic power generation amount per hour, A pv And eta pv Expressed as the area and efficiency of the photovoltaic panel to receive the sun, respectively, irr (t) and Temp (t) expressed as the external temperature of the photovoltaic panel and the solar radiation amount, respectively, at the t-th hour;
the electricity generated by the electrodes of the electrolyzer cell is expressed in terms of voltage relationship:
wherein r represents ohmic resistance parameter, s represents overvoltage parameter, C represents electrode contact area, kappa is overvoltage on electrode, I represents electrode current, U rev Reversible battery standard voltage;
the stored energy of the static energy storage system is expressed as:
wherein SE is t Represents the amount of electricity that can be stored at the t hour, eta ESS Is the energy storage efficiency of the battery, ES t ch And ES (ES) t dis Respectively representing the charge and discharge states in the t time period, and gamma represents the interval duration;
the energy stored in the mobile energy storage system is expressed as:
wherein,,indicating the arrival time of the electric vehicle, < > or>Indicating the electrodynamic force departure time, ψ e (t) represents the charge/discharge amount, α, of the electric vehicle at the t-th hour e (t) is the electric vehicle state, α e (t) =1 is the electric vehicle state of charge, α e (t) = -1 is discharge state, α e (t) =0 is an idle state.
Further, the step S2 specifically includes the following steps:
the predictive model consists of three parts: (1) a feature selector; (2) a predictor; (3) an optimizer;
(1) Feature selection stage: the prediction model based on the information interaction technology adopts solar radiation and wind speed time sequence as model input; sorting the input through an information interaction technology, and transmitting the sorted unit features to a redundancy filter to remove irrelevant and redundant features; the selected sample feature inputs are then separated into training and test data sets;
(2) The prediction stage adopts a training and testing set to predict solar radiation and wind speed in the following whole day time range; the artificial neural network consists of three layers, namely an input layer, a hidden layer and an output layer; wherein the artificial neuron ANs of each layer is used as an activation function through a sigmoid function, as shown in the following formula (8):
s is a solar radiation intensity and wind speed input signal, the parameter beta is the steepness of an activation function, and b represents a signal deviation value; the prediction model designed through the method can learn and accurately estimate the electric quantity to be generated in the future through training; in the embodiment, the multiple autoregressive rule has higher convergence than the reference learning rule, and the designed prediction framework adopts a supervised learning method to learn from time sequence analysis;
training a prediction framework through a training set, verifying the prediction framework by a test set to predict future values, and comparing the obtained prediction result with a ground real observation result to obtain accuracy; the mean absolute percentage error MAPE as a verification degree between the predicted output and the actual observed value of the artificial neural network can be expressed as follows:
wherein p is actual (i, j) is expressed as the actual observed value, p forecast (i, j) is expressed as predicted solar radiation intensity and wind speed, n is the number of samples taken, Ω is the number of days observed; providing the predicted values of the artificial neural network predictor to an optimization stage of the prediction model to further minimize the error;
(3) And (3) optimizing: and calculating an error between the predicted value and the actual observed value of the artificial neural network, and further minimizing the error by using an enhanced differential evolution algorithm EDE in an optimization stage.
Further, the step S3 specifically includes the following steps:
the energy management system receives a demand response signal and broadcasts the demand response signal to the user in advance; the user sends the power consumption mode response to the energy management system; the energy management system arranges a power utilization strategy of a consumer and a charging and discharging strategy of an electric automobile so as to reduce energy cost, reduce power grid fluctuation and reduce carbon emission, and therefore, an adopted objective function is modeled as an optimization function so as to minimize the objective; each optimization target is respectively expressed mathematically according to the formula of the whole energy management problem: (1) Cost of energy consumption
The energy consumption cost without considering the real-time electricity price signal of the micro-grid is expressed as:
wherein Γ is t Represents the power consumption of the microgrid per hour, EP t Represents an average electricity price per hour, and T represents a predicted time length; each node of the micro-grid is provided with unstable renewable energy sources, battery energy storage and electric vehicle energy storage, and the required input power of each day is expressed as:
wherein ER t Representing the amount of electricity generated by renewable energy sources, EV t Representing the electric quantity released by the energy storage of the electric vehicle and ESS t Representing the amount of electricity released by the energy storage of the battery; phi T > 0 represents the power introduced, and Φ T =0 indicates that no charge is introduced; the cost per hour and per day of electricity charge of the power consumer after the micro-grid is considered is expressed as:
δ t =(Φ t ×EP t )(12)
wherein delta T Representing daily electricity charge; phi t Represents the electricity consumption per hour, EP t Represents an average electricity price per hour; (2) Grid peak and averageRatio of;
the ratio of peak power consumption to average power consumption is expressed as:
wherein max (Γ 1 ,Γ 2 ,...,Γ 24 ) Represents the maximum hour power consumption in one day, Γ T Power demand per 24 hours;
(3) Carbon emission
The mathematical model of carbon emissions is expressed as:
wherein γ represents the carbon emission amount, mean (EP (t)) represents the average electricity price, λ represents the price per kilowatt-hour, ζ represents the electricity discharge carbon factor;
(4) Target optimization function construction
Minimum energy cost, carbon emissions, peak to average ratio and user comfort, optimization problems are:
wherein,,indicating energy storage level of electric vehicle reaching charging pile, EV e Represents the energy storage energy of the electric automobile, EV max-e Indicating the maximum discharge amount of the battery of the electric vehicle, EV min-e Representing the minimum discharge capacity of the battery of the electric vehicle, P t elec Indicating the electric energy generation capacity of the electrolytic cell, irr max Indicating the maximum solar radiation quantity which can be received by the solar panel and ESS min And ESS (ESS) max Representing the minimum and maximum capacities of the energy storage system, respectively;
and solving to obtain an optimal strategy sequence of each node of the power grid, taking a first strategy element, and feeding the first strategy element back to each node of the power grid for control so as to complete the strategy control operation of the power grid.
The intelligent power grid energy optimization high-efficiency management system based on model prediction is characterized by being based on a computer system and comprising a processor, a memory and a computer program stored on the memory, wherein the method is realized when the processor runs the program instructions.
A computer readable storage medium having stored thereon computer program instructions which, when loaded and executed by a processor, are capable of implementing a method as described above.
Compared with the prior art, the invention and the preferable scheme thereof have the following beneficial effects:
the energy cost paid by consumers can be reduced, the peak pressure of power demand is reduced, carbon emission is minimized, and the problem of electric comfort of users is improved; and establishing mathematical models of all grid nodes of the distributed power grid, including a power utilization end, a power supply end, an energy storage end and a micro-grid overall, and defining unstable clean energy distributed grid-connected power generation models, such as a photovoltaic power generation model and a wind power generation model, and predicting the power generation capacity of the clean energy in the future through an Artificial Neural Network (ANN). And finally, establishing a model prediction optimization problem according to the minimum energy cost, carbon emission and other elements, solving to obtain each element execution strategy, effectively realizing efficient energy management, and realizing accurate prediction on the power generation efficiency of the unstable new energy.
Drawings
The invention is described in further detail below with reference to the attached drawings and detailed description:
the accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a scroll optimization execution of an embodiment of the present invention;
FIG. 2 is a schematic diagram of a system microgrid model in accordance with the background of the invention;
FIG. 3 is a flow chart of an enhanced differential algorithm of an embodiment of the present invention;
FIG. 4 is a schematic diagram of the operation of various intelligent home appliances according to an embodiment of the present invention;
FIG. 5 is a diagram showing the comparison of electric charges for various scheduling modes according to an embodiment of the present invention;
fig. 6 is a graph of error rate versus improved artificial neural network for an embodiment of the present invention.
Detailed Description
In order to make the features and advantages of the present patent more comprehensible, embodiments accompanied with figures are described in detail below:
it should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
The following is a further detailed description of the present embodiment with reference to the accompanying drawings:
as shown in fig. 1; the embodiment provides a smart grid energy optimization efficient management method based on model prediction, which comprises the following steps:
step one: and establishing a mathematical model of the whole micro-grid, wherein each grid node of the distributed power grid comprises an electricity utilization end, a power supply end, an energy storage end and the like.
Step 1.1: modeling of powered devices operating in a smart home, as shown in fig. 2, each device is arranged according to consumer demand. An adaptive scheduling method based on real-time pricing signals. The energy management system receives the low price signal from the real-time pricing and immediately dispatches and controls the electric appliance. The consumer schedules the smart appliance at specified time intervals to avoid the high costs incurred by operating in peak hours. The user's start probability function is defined as:
wherein S represents an intelligent electrical device, h represents an hour of the day, d represents a day of the week, W represents a day of the year,representing the time step, σ, of the predictive computation flat Standard deviation of social random factor, P season Indicating the probability of use of seasons, P hour Represents the hourly start-up probability factor, P social Represents the probability of random use of society, P step Representing the scale factor.
Step 1.2: and establishing a micro-grid model. The micro-grid comprises an electric appliance, a photovoltaic panel, wind power, an electrolytic tank, an electric automobile and an energy storage device. Net energy m produced by each device in the microgrid at time t t Energy generated within the predicted time period T:
step 1.2.1: wind power generation
The power generation amount of wind power generation per hour is mainly determined by wind speed, and a mathematical model is expressed as follows:
wherein P is t wt Representing t hours of wind power generation capacity, C p Representing a wind energy conversion value, A representing a region swept by turbine blades of a wind turbine generator, V t wt Representing the t-th smallWhen wind speed, ρ represents air density, the power generation of wind energy is directly affected by wind speed, i.e. the higher the wind speed, the higher the power generation and vice versa, however the above model satisfies the constraint:
wherein V is cut-in And V cut-out Respectively representing the speed of wind entering the blade and the speed of wind exiting the blade;
step 1.2.2: photovoltaic power generation
The generated power of the photovoltaic panel directly receives the influence of the intensity of solar radiation, and the mathematical model can be expressed as follows:
P t pv =η pv ×A pv ×Irr(t)×(1-0.005×(Temp(t)-25)) (4)
wherein P is t pv Represents the photovoltaic power generation amount per hour, A pv And eta pv Expressed as the area and efficiency of the photovoltaic panel to receive the sun, respectively, irr (t) and Temp (t) expressed as the external temperature of the photovoltaic panel and the solar radiation amount, respectively, at the t-th hour.
Step 1.2.3: electrolytic cell power generation
In this example, an electrochemical reaction process was employed in the cell model. In addition, a maximum temperature of 100℃is also considered. The electrical voltage relationship produced by the electrodes of the electrolyzer cell is expressed as:
wherein r represents ohmic resistance parameter, s represents overvoltage parameter, C represents electrode contact area, kappa is overvoltage on electrode, I represents electrode current, U rev Reversible battery standard voltage;
step 1.3: and establishing an energy storage system model. The energy storage system comprises a static storage system and a mobile storage system, wherein an unstable renewable energy source is arranged in a micro-grid, electric quantity is stored at peak time (as load), and energy is released at low price time (as power supply).
(1) Static energy storage system: the static energy storage system considered in this embodiment is mainly a battery with a storage capacity of 3 kWh. Its stored energy can be expressed as:
SE t =SE t-1 +γ×η ESS ×ES t ch -γ×ES t dis /η ESS (6)
wherein SE is t Represents the amount of electricity that can be stored at the t hour, eta ESS Is the energy storage efficiency of the battery, ES t ch And ES (ES) t dis Respectively, the charge and discharge states in the t period, and γ represents the interval duration.
(2) A mobile energy storage system: the mobile energy storage system considered in this embodiment is an electric vehicle, and the energy stored in the electric vehicle is expressed as:
wherein,,indicating the arrival time of the electric vehicle, < > or>Indicating the electrodynamic force departure time, ψ e (t) represents the charge/discharge amount, α, of the electric vehicle at the t-th hour e (t) is the electric vehicle state, α e (t) =1 is the electric vehicle state of charge, α e (t) = -1 is discharge state, α e (t) =0 is an idle state.
Step two: and (3) defining an unstable clean energy distributed grid-connected power generation model, such as a photovoltaic power generation model and a wind power generation model, and predicting the power generation amount of the clean energy in the future through an Artificial Neural Network (ANN).
Firstly, an artificial neural network framework is optimized by adopting a differential algorithm to predict solar radiation and wind speed, as shown in fig. 3, so as to effectively estimate the generated energy, and the proposed prediction model consists of three parts: (1) a feature selector; (2) a predictor; (3) an optimizer.
(1) Feature selection stage: the prediction model based on the information interaction technology adopts solar radiation and wind speed time sequence as model input. And sequencing the input through an information interaction technology, and transmitting the sequenced unit features to a redundancy filter to remove irrelevant and redundant features. The selected sample feature inputs are then separated into training and test data sets.
(2) The prediction phase is implemented based on an artificial neural network, in particular employing training and test sets to predict solar radiation and wind speed over the following whole day time frame. The artificial neural network is composed of three layers, namely an input layer, a hidden layer and an output layer. Wherein the Artificial Neurons (ANs) of each layer are activated by a sigmoid function as shown in the following formula (8):
where S is the solar radiation intensity, wind speed input signal, the parameter β is the steepness of the activation function, and b represents the signal deviation value. The prediction model designed by the above can learn and accurately estimate the electric quantity to be generated in the future through training. In this embodiment, since the multiple autoregressive rule has higher convergence than the reference learning rule, the designed prediction framework learns from time series analysis by using a supervised learning method.
The prediction framework is trained through the training set, the test set verifies the prediction framework to predict future values, and the obtained prediction result is compared with the ground real observation result to obtain accuracy. The mean absolute percentage error MAPE as a verification degree between the predicted output and the actual observed value of the artificial neural network can be expressed as follows:
wherein p is actual (i, j) is expressed as the actual observed value, p forecast (i, j) is expressed as predictionN represents the number of samples taken, Ω represents the number of days observed, and the predicted values (solar radiation and wind speed) of the artificial neural network predictor are provided to the optimization stage of the predictive model to further minimize the error.
(3) And (3) optimizing: the error between the predicted value and the actual observed value of the artificial neural network is calculated, and the error is further minimized by using an Enhanced Differential Evolution (EDE) algorithm in the optimization stage.
Step three: and (3) establishing a model prediction optimization problem according to the minimum energy cost, carbon emission and small power grid fluctuation elements, solving and obtaining each element execution strategy, reducing the energy cost paid by consumers, relieving the peak pressure of the power demand, minimizing the carbon emission and improving the electricity utilization comfort level of users.
In terms of energy management, the main objectives are energy costs, small grid fluctuations and carbon emission factors, achieved by actively letting consumers/end users participate in distributed power generation and demand response projects. To this end, the energy management system receives a demand response signal and broadcasts it to the users in advance. The user sends its power usage pattern response to the energy management system. The energy management system will arrange consumer electricity usage strategies and electric vehicle charging and discharging strategies to reduce energy costs, mitigate grid fluctuations, reduce carbon emissions, and thus model the proposed objective function as an optimization function to minimize the above objectives. Each optimization objective will be expressed mathematically according to the formula of the whole energy management problem:
(1) Cost of energy consumption
The energy cost refers to a consumer paying the utility provider for electricity consumed during a specific period. The energy costs are formulated from real-time electricity price signals provided by the grid. The energy consumption cost without considering the real-time electricity rate signal of the micro grid is expressed as:
wherein Γ is t Representing the electricity of a microgrid per hourForce consumption, EP t The average power rate per hour is represented, and T represents the predicted time period. Each node of the micro-grid is provided with unstable renewable energy sources, battery energy storage and electric vehicle energy storage, and the required input power of each day can be expressed as:
wherein ER t Representing the amount of electricity generated by renewable energy sources, EV t Representing the electric quantity released by the energy storage of the electric vehicle and ESS t Representing the amount of power released by the stored energy of the battery. Phi T > 0 represents the power introduced, and Φ T =0 indicates that no charge is introduced. The electricity consumer per hour and per day costs after the micro grid is considered can be expressed as:
δ t =(Φ t ×EP t ) (12)
wherein delta T Indicating the daily electricity charge. Phi t Represents the electricity consumption per hour, EP t The average electricity price per hour is represented.
(2) Peak to average ratio of power grid
The ratio of peak power consumption to average power consumption can be expressed as:
wherein max (Γ 1 ,Γ 2 ,...,Γ 24 ) Represents the maximum hour power consumption in one day, Γ T /24 power demand per hour.
(3) Carbon emission
The mathematical model of carbon emissions can be expressed as:
where γ represents the carbon emission amount, mean (EP (t)) represents the average electricity price, λ represents the price per kilowatt-hour,representing the carbon factor of the charge emission.
(4) Target optimization function construction
To achieve our desired goal: minimum energy cost, carbon emissions, peak to average ratio, and user comfort, optimization problems can be designed as:
wherein ρEV is a e Indicating energy storage level of electric vehicle reaching charging pile, EV e Represents the energy storage energy of the electric automobile, EV max-e Indicating the maximum discharge amount of the battery of the electric vehicle, EV min-e Representing the minimum discharge capacity of the battery of the electric vehicle, P t elec Indicating the electric energy generation capacity of the electrolytic cell, irr max Indicating the maximum solar radiation quantity which can be received by the solar panel and ESS min And ESS (ESS) max Representing the minimum and maximum capacities of the energy storage system, respectively.
And solving to obtain an optimal strategy sequence of each node of the power grid, taking a first strategy element, and feeding the first strategy element back to each node of the power grid for control, thereby completing the strategy control operation of the power grid.
Step four: simulation contrast and analysis
In the simulation cases, the intelligent power grid energy optimization high-efficiency management method based on model prediction is compared with the traditional mixed integer linear programming, four performance indexes including energy cost, peak value and average value ratio, carbon emission and waiting time/delay are adopted in the cases, and compared with the existing models, the performance of the proposed model is evaluated. The proposed system model development house intelligent home is designed into three types of loads: an electrical control appliance, a temperature regulating appliance and a lighting home. In addition, a prediction power generation framework of solar irradiation and wind speed is performed to accurately estimate power generation so as to realize effective energy management. The following cases were simulated: (I) energy management without microgrid; (II) 24 hours energy management with microgrid. Scheduling and planning each electric appliance after the intelligent power grid energy optimization high-efficiency management method based on the model prediction is operated, as shown in fig. 4; the electricity fee generated by various scheduling modes is shown in fig. 5; the error rate of predicting unstable clean energy by improving the artificial neural network is shown in fig. 6.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the invention in any way, and any person skilled in the art may make modifications or alterations to the disclosed technical content to the equivalent embodiments. However, any simple modification, equivalent variation and variation of the above embodiments according to the technical substance of the present invention still fall within the protection scope of the technical solution of the present invention.
The patent is not limited to the best mode, any person can obtain other various forms of intelligent power grid energy optimization high-efficiency management method based on model prediction under the teaching of the patent, and all equivalent changes and modifications made according to the application scope of the invention are covered by the patent.
Claims (9)
1. The intelligent power grid energy optimization efficient management method based on model prediction is characterized by comprising the following steps of:
step S1: establishing a mathematical model of the whole micro-grid, wherein each grid node of the distributed power grid comprises a power utilization end, a power supply end, an energy storage end and a power distribution end;
step S2: the method comprises the steps of determining an unstable photovoltaic and wind power distributed grid-connected power generation model, and predicting the power generation capacity of clean energy in the future through an artificial neural network ANN;
step S3: and establishing a model prediction optimization problem according to the minimum energy cost, the peak value and average ratio of the power grid and the carbon emission element, and solving to obtain an execution strategy of each element.
2. The intelligent power grid energy optimization efficient management method based on model prediction according to claim 1, wherein the method is characterized by comprising the following steps of:
in step S1, a smart micro-grid equipped with a household appliance, a photovoltaic array, an electrolytic cell, wind power, an electric vehicle and an energy storage device is mathematically modeled, and a model predictive optimization problem is established according to minimum energy cost, grid peak-to-average ratio and carbon emission factors.
3. The intelligent power grid energy optimization efficient management method based on model prediction according to claim 1, wherein the method is characterized by comprising the following steps of: in step S2, the solar radiation and wind speed time sequence is used as a model input to remove uncorrelated and redundant features, the selected sample feature input is divided into training and test data sets, then the training and test sets are used to predict solar radiation and wind speed within the time range of the following whole day, the error between the predicted value and the actual observed value of the artificial neural network is calculated, and the enhanced differential evolution algorithm EDE is used in the optimization stage to further minimize the error.
4. The intelligent power grid energy optimization efficient management method based on model prediction according to claim 1, wherein the method is characterized by comprising the following steps of: in step S3, the optimization problem is established by considering the objective functions of energy cost, small power grid fluctuation and carbon emission and the constraint of the system, and the optimal strategy is obtained by minimizing the objective functions.
5. The intelligent power grid energy optimization efficient management method based on model prediction according to claim 2, wherein the method is characterized by comprising the following steps of: the step S1 specifically comprises the following steps:
step 1.1: the self-adaptive scheduling method based on the real-time pricing signal is characterized in that an energy management system receives a low-price signal from the real-time pricing, and immediately schedules and controls an electric appliance; the consumer schedules the smart appliances at specified time intervals to avoid high costs due to operation during peak hours; defining a user's start probability function as:
wherein S represents an intelligent electrical device, h represents an hour of the day, d represents a day of the week, W represents a day of the year,representing the time step, σ, of the predictive computation flat Standard deviation of social random factor, P season Indicating the probability of use of seasons, P hour Represents the hourly start-up probability factor, P social Represents the probability of random use of society, P step Representing the scale factor;
step 1.2: establishing a micro-grid model; the micro-grid at least comprises an electric appliance, a photovoltaic panel, wind power, an electrolytic tank, an electric automobile and an energy storage device; net energy m produced by each device in the microgrid at time t t Energy generated within the predicted time period T:
the mathematical model of the power generation amount per hour of wind power generation is expressed as:
P t wt =1/2×C p ×ρ×A×(V t wt ) 3 (3)
wherein P is t wt Representing t hours of wind power generation capacity, C p Representing a wind energy conversion value, A representing a region swept by turbine blades of a wind turbine generator, V t wt Represents the wind speed at the t hour, ρ represents the air density, and the wind energy is full of power generationFoot constraint:
V cut-in ≤V t wt ≤V cut-out
wherein V is cut-in And V cut-out Respectively representing the speed of wind entering the blade and the speed of wind exiting the blade;
the mathematical model of the photovoltaic panel generation power is expressed as:
P t pv =η pv ×A pv ×Irr(t)×(1-0.005×(Temp(t)-25)) (4)
wherein P is t pv Represents the photovoltaic power generation amount per hour, A pv And eta pv Expressed as the area and efficiency of the photovoltaic panel to receive the sun, respectively, irr (t) and Temp (t) expressed as the external temperature of the photovoltaic panel and the solar radiation amount, respectively, at the t-th hour;
the electricity generated by the electrodes of the electrolyzer cell is expressed in terms of voltage relationship:
wherein r represents ohmic resistance parameter, s represents overvoltage parameter, C represents electrode contact area, kappa is overvoltage on electrode, I represents electrode current, U rev Reversible battery standard voltage;
the stored energy of the static energy storage system is expressed as:
wherein SE is t Indicated at the t hourThe amount of electricity, eta, that can be stored ESS Is the energy storage efficiency of the battery,and->Respectively representing the charge and discharge states in the t time period, and gamma represents the interval duration;
the energy stored in the mobile energy storage system is expressed as:
wherein,,indicating the arrival time of the electric vehicle, < > or>Indicating the electrodynamic force departure time, ψ e (t) represents the charge/discharge amount, α, of the electric vehicle at the t-th hour e (t) is the electric vehicle state, α e (t) =1 is the electric vehicle state of charge, α e (t) = -1 is discharge state, α e (t) =0 is an idle state.
6. The intelligent power grid energy optimization efficient management method based on model prediction according to claim 5, wherein the method is characterized by comprising the following steps of: the step S2 specifically comprises the following steps:
the predictive model consists of three parts: (1) a feature selector; (2) a predictor; (3) an optimizer;
(1) Feature selection stage: the prediction model based on the information interaction technology adopts solar radiation and wind speed time sequence as model input; sorting the input through an information interaction technology, and transmitting the sorted unit features to a redundancy filter to remove irrelevant and redundant features; the selected sample feature inputs are then separated into training and test data sets;
(2) The prediction stage adopts a training and testing set to predict solar radiation and wind speed in the following whole day time range; the artificial neural network consists of three layers, namely an input layer, a hidden layer and an output layer; wherein the artificial neuron ANs of each layer is used as an activation function through a sigmoid function, as shown in the following formula (8):
s is a solar radiation intensity and wind speed input signal, the parameter beta is the steepness of an activation function, and b represents a signal deviation value; the prediction model designed through the method can learn and accurately estimate the electric quantity to be generated in the future through training; in the embodiment, the multiple autoregressive rule has higher convergence than the reference learning rule, and the designed prediction framework adopts a supervised learning method to learn from time sequence analysis;
training a prediction framework through a training set, verifying the prediction framework by a test set to predict future values, and comparing the obtained prediction result with a ground real observation result to obtain accuracy; the mean absolute percentage error MAPE as a verification degree between the predicted output and the actual observed value of the artificial neural network can be expressed as follows:
wherein p is actual (i, j) is expressed as the actual observed value, p forecast (i, j) is expressed as predicted solar radiation intensity and wind speed, n is the number of samples taken, Ω is the number of days observed; providing the predicted values of the artificial neural network predictor to an optimization stage of the prediction model to further minimize the error;
(3) And (3) optimizing: and calculating an error between the predicted value and the actual observed value of the artificial neural network, and further minimizing the error by using an enhanced differential evolution algorithm EDE in an optimization stage.
7. The intelligent power grid energy optimization efficient management method based on model prediction as set forth in claim 6, wherein the method comprises the following steps: the step S3 specifically comprises the following steps:
the energy management system receives a demand response signal and broadcasts the demand response signal to the user in advance; the user sends the power consumption mode response to the energy management system; the energy management system arranges a power utilization strategy of a consumer and a charging and discharging strategy of an electric automobile so as to reduce energy cost, reduce power grid fluctuation and reduce carbon emission, and therefore, an adopted objective function is modeled as an optimization function so as to minimize the objective; each optimization target is respectively expressed mathematically according to the formula of the whole energy management problem: (1) Cost of energy consumption
The energy consumption cost without considering the real-time electricity price signal of the micro-grid is expressed as:
wherein Γ is t Represents the power consumption of the microgrid per hour, EP t Represents an average electricity price per hour, and T represents a predicted time length; each node of the micro-grid is provided with unstable renewable energy sources, battery energy storage and electric vehicle energy storage, and the required input power of each day is expressed as:
wherein ER t Representing the amount of electricity generated by renewable energy sources, EV t Representing the electric quantity released by the energy storage of the electric vehicle and ESS t Representing the amount of electricity released by the energy storage of the battery; phi T > 0 represents the power introduced, and Φ T =0 indicates that no charge is introduced; the cost per hour and per day of electricity charge of the power consumer after the micro-grid is considered is expressed as:
δ t =(Φ t ×EP t ) (12)
wherein delta T Representing daily electricity charge; phi t Represents the electricity consumption per hour, EP t Represents an average electricity price per hour;
(2) The peak to average ratio of the power grid;
the ratio of peak power consumption to average power consumption is expressed as:
wherein max (Γ 1 ,Γ 2 ,...,Γ 24 ) Represents the maximum hour power consumption in one day, Γ T Power demand per 24 hours;
(3) Carbon emission
The mathematical model of carbon emissions is expressed as:
where γ represents the carbon emission amount, mean (EP (t)) represents the average electricity price, λ represents the price per kilowatt-hour,representing an electric quantity emission carbon factor;
(4) Target optimization function construction
Minimum energy cost, carbon emissions, peak to average ratio and user comfort, optimization problems are:
Subjected to:ER t =P t pv +P t wt +P t elec
Γ t =ER t +ESS t +EV t +Φ t ,
wherein,,indicating energy storage level of electric vehicle reaching charging pile, EV e Represents the energy storage energy of the electric automobile, EV max-e Indicating the maximum discharge amount of the battery of the electric vehicle, EV min-e Representing the minimum discharge capacity of the battery of the electric vehicle, P t elec Indicating the electric energy generation capacity of the electrolytic cell, irr max Indicating the maximum solar radiation quantity which can be received by the solar panel and ESS min And ESS (ESS) max Representing the minimum and maximum capacities of the energy storage system, respectively;
and solving to obtain an optimal strategy sequence of each node of the power grid, taking a first strategy element, and feeding the first strategy element back to each node of the power grid for control so as to complete the strategy control operation of the power grid.
8. A smart grid energy optimization efficient management system based on model prediction, characterized in that it is based on a computer system, comprising a processor, a memory and a computer program stored on the memory, which when being executed by the processor, implements the method according to any of claims 1-7.
9. A computer readable storage medium, having stored thereon computer program instructions, which when loaded and executed by a processor are capable of implementing the method according to any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211743033.6A CN116384039A (en) | 2022-12-30 | 2022-12-30 | Intelligent power grid energy optimization efficient management method based on model prediction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211743033.6A CN116384039A (en) | 2022-12-30 | 2022-12-30 | Intelligent power grid energy optimization efficient management method based on model prediction |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116384039A true CN116384039A (en) | 2023-07-04 |
Family
ID=86960384
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211743033.6A Pending CN116384039A (en) | 2022-12-30 | 2022-12-30 | Intelligent power grid energy optimization efficient management method based on model prediction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116384039A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117239740A (en) * | 2023-11-14 | 2023-12-15 | 北京国科恒通数字能源技术有限公司 | Optimal configuration and flexibility improvement method and system for virtual power plant system |
CN117371765A (en) * | 2023-12-06 | 2024-01-09 | 厦门亿京能源集团股份有限公司 | Comprehensive optimization operation method and system based on energy-saving carbon-reduction intelligent energy |
-
2022
- 2022-12-30 CN CN202211743033.6A patent/CN116384039A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117239740A (en) * | 2023-11-14 | 2023-12-15 | 北京国科恒通数字能源技术有限公司 | Optimal configuration and flexibility improvement method and system for virtual power plant system |
CN117239740B (en) * | 2023-11-14 | 2024-01-23 | 北京国科恒通数字能源技术有限公司 | Optimal configuration and flexibility improvement method and system for virtual power plant system |
CN117371765A (en) * | 2023-12-06 | 2024-01-09 | 厦门亿京能源集团股份有限公司 | Comprehensive optimization operation method and system based on energy-saving carbon-reduction intelligent energy |
CN117371765B (en) * | 2023-12-06 | 2024-03-12 | 厦门亿京能源集团股份有限公司 | Comprehensive optimization operation method and system based on energy-saving carbon-reduction intelligent energy |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fontenot et al. | Modeling and control of building-integrated microgrids for optimal energy management–a review | |
Carli et al. | Energy scheduling of a smart microgrid with shared photovoltaic panels and storage: The case of the Ballen marina in Samsø | |
Ju et al. | Multi-objective stochastic scheduling optimization model for connecting a virtual power plant to wind-photovoltaic-electric vehicles considering uncertainties and demand response | |
Megahed et al. | Energy management in zero-energy building using neural network predictive control | |
Huang et al. | Mixed deep reinforcement learning considering discrete-continuous hybrid action space for smart home energy management | |
CN116384039A (en) | Intelligent power grid energy optimization efficient management method based on model prediction | |
Mei et al. | Stochastic optimization of multi-energy system operation considering hydrogen-based vehicle applications | |
Lai et al. | Multiagent reinforcement learning for community energy management to mitigate peak rebounds under renewable energy uncertainty | |
CN113437752B (en) | Operation control method of comprehensive energy system containing hybrid energy storage | |
Xu et al. | Energy allocation strategy based on fuzzy control considering optimal decision boundaries of standalone hybrid energy systems | |
Mekontso et al. | Review of optimization techniques for sizing renewable energy systems | |
Beheshtikhoo et al. | Design of type-2 fuzzy logic controller in a smart home energy management system with a combination of renewable energy and an electric vehicle | |
Chellaswamy et al. | A framework for building energy management system with residence mounted photovoltaic | |
Dimopoulou et al. | A Markov decision process for managing a hybrid energy storage system | |
CN112508325A (en) | Multi-time-scale electric energy scheduling method for household micro-grid | |
Bartels et al. | Influence of hydrogen on grid investments for smart microgrids | |
Kofinas et al. | Energy management in solar microgrid via reinforcement learning | |
Leo et al. | Multi agent reinforcement learning based distributed optimization of solar microgrid | |
Chreim et al. | Praha-price based demand response framework for smart homes: Application to smart grids | |
Zhang et al. | Resilient energy management for residential communities under grid outages | |
Yu et al. | Transactive control of a residential community with solar photovoltaic and battery storage systems | |
CN114498769B (en) | High-proportion wind-solar island micro-grid group energy scheduling method and system | |
Zhong et al. | A logic-based geometrical model for the next day operation of PV-battery systems | |
Fang et al. | Energy scheduling and decision learning of combined cooling, heating and power microgrid based on deep deterministic policy gradient | |
Singh et al. | Application of renewable energy system with fuzzy logic |
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 |