CN106600078A - Micro-grid energy management scheme based on new energy power generation forecasting - Google Patents
Micro-grid energy management scheme based on new energy power generation forecasting Download PDFInfo
- Publication number
- CN106600078A CN106600078A CN201710035808.7A CN201710035808A CN106600078A CN 106600078 A CN106600078 A CN 106600078A CN 201710035808 A CN201710035808 A CN 201710035808A CN 106600078 A CN106600078 A CN 106600078A
- Authority
- CN
- China
- Prior art keywords
- microgrid
- energy storage
- wind
- user
- electricity
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
Abstract
The invention discloses a distributed energy management algorithm based on short-term wind power forecasting results applied to micro-grid energy management. Firstly, a short-term wind power forecasting algorithm in combination with an automatic coding technology, a back propagation algorithm and a genetic algorithm is proposed, and compared with a traditional wind power forecasting algorithm, the accuracy of wind power forecasting can be effectively increased by using the short-term wind power forecasting algorithm; and secondly, based on the short-term wind power forecasting, the energy management problem is modeled as a three-stage Stackelberg game, the dynamic relationship among grid companies, energy storage companies, micro-grids and users is described, and an optimal management solution can be obtained by analyzing a game model through a reverse recursive method.
Description
Technical field
The invention belongs to microgrid energy management domain, and in particular to it is a kind of apply in energy management based on short-term wind-electricity
The distributed energy management solutions algorithm for predicting the outcome, can consider electrical network, and energy storage company, microgrid are mutual between user
Relation and wind-powered electricity generation realize each participant's maximizing the benefits in the case of predicting the outcome, so as to efficiently solve microgrid energy management
Problem.
Background technology
To solve the contradiction of Operation of Electric Systems and distributed power source generator compartment, distributed power source is given full play to power train
Complex art that system is brought with user, economy, environmental benefit, meet Operation of Electric Systems to motility, controllability and reliability
And requirements at the higher level of the intelligent grid to distributed power generation, microgrid arises at the historic moment, and is quickly become world's electrical engineering research
One of the newest advanced subject in field.Microgrid can effectively integrate various distributed generation technologies, give full play to generation of electricity by new energy
The economic benefit brought with intelligent grid and environmental benefit；Simultaneously can also meet user to the reliability of electricity consumption and safety with
And the diversified requirement of power demands.Due to the unstability of wind itself, wind-power electricity generation has undulatory property and intermittence, and this will make
Obtain scheduling of the microgrid to wind-powered electricity generation and cause serious difficulty.
In microgrid energy management, many work pay attention to the benefit for lifting whole system and ignore each participant it
In contact and interaction, further, since wind-power electricity generation has undulatory property and an intermittence, great majority work is not accounted for
The impact to microgrid energy management is predicted to regenerative resource, the process of the power exchange between participant in the market is also ignored.
Therefore, the energy management system of micro-grid in the urgent need to research and development based on renewable energy power generation prediction.
The content of the invention
The present invention is a kind of distributed energy pipe predicted the outcome based on short-term wind-electricity applied in microgrid energy management
Adjustment method, first proposed the short-term forecast wind-powered electricity generation work(that one kind combines automatic coding, back-propagation algorithm and genetic algorithm
Rate algorithm, compared to traditional wind-powered electricity generation prediction algorithm, this algorithm can effectively improve the accuracy of wind-powered electricity generation prediction.Secondly, based on short
Energy conservation problem is modeled as a triphasic Stackelberg game by phase wind power prediction, describes electrical network public
Department, energy storage company, the dynamic relationship between microgrid and user, and betting model is analyzed using backward induction method method, draw optimum
Rwan management solution RWAN.Its specific implementation process is as follows：1) Fig. 1 is the system model of microgrid energy management, and electricity is included in model
Net company, energy storage company, user
Generate electricity with multiple renewable energy sources.Due to by regenerative resource undulatory property, intermittent impact and microgrid
The restriction of itself capacity, microgrid only tend not to meet the demand of user by self generating, therefore, microgrid can be from electricity
Net company and energy storage company power purchase.In model, each participant's benefit function modeling is as follows：
A () is can be configured such that in view of cost of electricity-generating, pollutant emission cost and line loss, the benefit function of electrical network：Ug
(pg)=pgLm,g-Cg(εgLm,g)-Ig(εgLm,g), C in formulag(εgLm,g) and Ig(εgLm,g) cost of electricity-generating and pollutant are represented respectively
Discharge costs, are all the quadratic functions with regard to generated energy, εgIt is line loss coefficient.In the same manner, it is contemplated that the discharge and recharge of energy storage device is damaged
Consumption and line loss, the benefit function of energy storage company can be configured such that：Us(ps)=psLm,s-Cs(εsLm,s), whereinRepresent total energy storage cost, c in formulasIt is unit energy storage cost, εsIt is line loss coefficient, ηcAnd ηdRespectively
Represent the efficiency for charge-discharge of energy storage device.
B () is in view of microgrid to electrical network and the satisfaction of energy storage company, purchases strategies, wind-powered electricity generation cost of electricity-generating, pollutant row
Cost and forecast error punishment cost are put, the benefit function of microgrid can be configured such that：
In formula WithRepresent respectively
Microgrid is to electrical network and the extent function of energy storage company, Xm,g, dm,g, Xm,s, dm,sIt is satisfaction parameter,Represent k
The total purchase of electricity of user, Cm(Lr+ Δ) and Im(Lr+ Δ) wind-powered electricity generation cost of electricity-generating and pollutant emission cost, wherein L are represented respectivelyr
Represent the true generated energy of wind-powered electricity generation, Δ is wind-powered electricity generation forecast error, F | Δs | represent punishment cost when wind-powered electricity generation prediction produces error, F is
Penalty coefficient.
C () satisfaction and purchases strategies in view of user to microgrid, the benefit function of k-th user can be configured such that：Uk
(Lk,m)=Rk(Lk,m)-pmLk,m.WhereinK-th user of representative is to microgrid
Extent function, Xk,mAnd dk,mIt is satisfaction parameter.
2) our energy conservation problems are modeled as a triphasic Stackelberg betting model, its block diagram such as Fig. 2 institutes
Show, describe grid company, energy storage company, the dynamic relationship between microgrid and user.
(a) first stage：Electrical network and energy storage company, as the leader of game, take the lead in issuing electricity price pgAnd ps.Therefore, electricity
The optimization problem of net company can be expressed as：The optimization problem of energy storage company can be expressed as:
(b) second stage：Microgrid, as the center of EMS, according to electricity price p of first stagegAnd ps, it is determined that
To electrical network and purchase of electricity L of energy storage companym,gAnd Lm,s, while determining microgrid electricity price pm.Therefore, the optimization problem of microgrid can be stated
For：C2:0≤εgLm,g≤Lg,max, C3:0≤εsLm,s≤Ls,max, C4:0≤pm
≤pm,max,In constraints, Lg,maxRepresent electrical network maximum raw
Yield, Ls,maxRepresent energy storage company maximum storage, pm,maxRepresent the ceiling price that user can bear.
(c) phase III：K-th user, as the follower of game, determines k-th user's according to the electricity price of microgrid
Purchase of electricity Lk,m.Therefore, the optimization problem of user can be expressed as：C1:Lk,m≥Lk,b, in constraints
Lk,bRepresent the primary demand of k-th user.
3) for three layers of betting model, we have proposed distributed energy management algorithm and carry out solving-optimizing problem, its tool
Body process is as follows：
(a) phase III user's game theory analysis：The Lagrangian of the optimization problem of k-th user is：Lagk(Lk,m,
μk)=Uk(Lk,m)+μk(Lk,m-Lk,b).Due to optimization problem be standard can nick function, Karush-Kuhn- can be adopted
Tucker (KKT) conditions come seek optimum solution.By calculating, obtaining optimal solution is
Lk,m2=Lk,b.Wherein Lk,m1It is optimum power purchase strategy, Lk,m2It is the optimum power purchase strategy for obtaining boundary condition.
(b) second stage microgrid game theory analysis：Assume in the first phase, there are the individual users of k ' to select the first strategy, k "
Individual user select second it is tactful, therefore the total purchases strategies of user are
The Lagrangian of microgrid is：
By calculating, L is obtainedm,gBest solution is：
Wherein Lm,g1Represent microgrid only to energy storage company power purchase, Lm,g3Represent that microgrid reaches its generating capacity to the purchase of electricity of grid company
Maximum, Lm,g2Represent optimum power purchase strategy.In the same manner, by calculating, L is obtainedm,sBest solution is： Wherein Lm,s1Represent microgrid only to grid company power purchase, Lm,s3Represent microgrid
The maximum of its memory capacity, L are reached to the purchase of electricity of energy storage companym,s2Represent optimum power purchase strategy.By calculating, can obtain
To pmOptimal solution be：Its
Middle pm1, pm3Microgrid electricity price minima and maximum, p are represent respectivelym2Represent optimum pricing strategy.From pm2Expression formula in
As can be seen that microgrid electricity price pmIt is electrical network electricity price pgWith energy storage company electricity price psFunction, be represented by：pm=Am,1pg+Am,2ps+
Am,3.In formula
(c) phase III electrical network and energy storage company game theory analysis：By Lm,gExpression formula we can see that Lm,gIt is electrical network
Company's electricity price pgFunction, be represented by：Lm,g(pg)=Ag,1pg+Ag,2.In formula Therefore, grid company benefit function is represented by pgSecondary letter
Number：Wherein By calculating, the pricing strategy that can obtain optimum is：In the same manner, the optimal pricing strategy for storing company can also use similar method to solve.
4) consider impact of the wind forecast error to prioritization scheme, propose that one kind combines automatic coding, back propagation is calculated
The short-term forecast wind power algorithm of method and genetic algorithm, substantially increases the accuracy of wind-powered electricity generation prediction.Algorithm core is to build
The forecast model of the historical data that is based on training.Wind-powered electricity generation prediction process can be divided into two processes：Including preprocessing process and micro-
Tune process.In preprocessing process, including visual layers, hidden layer and output layer；In trim process, can be in pretreatment network
Finally add multiple Rotating fields and use back-propagation algorithm to calculate the initial weight of overall network.Additionally, in order to improve prediction
Precision, we optimize the neuron number of the learning rate of each encoder and per layer using genetic algorithm.Concrete mistake
Journey is as follows：
(a) preprocessing process and trim process：As shown in Fig. 3 (a), encoder includes an input layer x, a hidden layer
h1, an output layerWe adopt coding function fθ1With decoding functions gθ1To process to input data, by reversely biography
Broadcast algorithm and obtain parameter value Wherein J is the number of plies of autocoder, wjWithIt is
The weight matrix of encoder, bjAnd djIt is the deviation of encoder.
As shown in Fig. 3 (b), in hidden layer h1One added behind new hidden layer h2, now h1And h2Together constitute one
Individual new autocoder.Similar, by adding new hidden layer in overall network rear end, multiple automatic encodings can be obtained
Device, it is contemplated that complexity of the calculation, is contemplated herein three autocoders.Fig. 3 (a) and (b) constitute wind-powered electricity generation data and locate in advance
The process of reason, comprising two hidden layer h1, h2, by direction propagation algorithm, obtain the initial weight of whole network.
In Fig. 3 (c), we finally with the addition of an output layer whole network, and initialize last and imply
Parameter w between layer and output layer4And b4.Using the process of the weight and deviation of back-propagation algorithm deinitialization whole network
Referred to as trim process.By the process and fine setting of three phases, the network of multilamellar can converge to a minima.
(b) model optimization：The learning rate of whole network and the neuron number of each hidden layer are for accurately prediction
As a result it is most important, therefore we are optimized to these parameters using genetic algorithm.Original wind-powered electricity generation data are assumed to lose
Colony P (d, t) inside propagation algorithm, in formula, d is colony's number, and t is Swarm Evolution number of times.Whole colony is initialized first for P
(0,0), each individual fitness is secondly calculated, (0) d, then will to obtain fitness highest individuality P by Selecting operation
Crossover algorithm and mutation algorithm act on colony, obtain colony P of future generation (d, 1).Similar process is repeatedly evolved, and will finally enter
It is individual as optimal solution output with maximum adaptation degree obtained by during change.Additionally, we are also with genetic algorithm come to passing
The parameter of the support vector machine (SVM) and back propagation (BP) model of system is optimized, and compares the precision of this model.Evaluate
The quality of forecast model performance needs the evaluation index of a quantization.Field, conventional evaluation index are predicted in wind-power electricity generation
It is mean absolute percentage error (MAPE).The definition of mean absolute percentage error is：
In formulaRepresent in n moment real wind power value, xnRepresent that wind-powered electricity generation in the same time predicts the outcome, n is the time point of prediction.
Description of the drawings
Fig. 1 is energy management system of micro-grid structural representation.
Fig. 2 is the block diagram of three layers of Stackelberg betting models.
Fig. 3 is the pretreatment of wind-powered electricity generation prediction algorithm and trim process.
Fig. 4 be microgrid to electrical network and energy storage company purchase of electricity with user's primary demand variation diagram.
Fig. 5 is the benefit value of microgrid with wind-powered electricity generation forecast error variation diagram.
Fig. 6 is wind-powered electricity generation prediction mean absolute percentage error (MAPE) with prediction step number variation diagram.
Specific embodiment
Embodiments of the present invention are always divided into two steps, and respectively model sets up process and algorithm realizes process.The present invention
Two models are established, one is the energy management system of micro-grid model predicted based on short-term wind-electricity, and one is with reference to volume automatically
The short-term forecast wind-powered electricity generation model of code technology, back-propagation algorithm and genetic algorithm, and realized with different algorithms respectively.
1) Fig. 1 is the energy management system of micro-grid model predicted based on short-term wind-electricity, as regenerative resource has fluctuation
Property and intermittent feature, it is contemplated that to the impact that manages to microgrid energy of access of distribution type renewable energy, while micro-
Net is limited by itself capacity, is needed to electrical network and energy storage company power purchase under conditions of power-balance is met.We are also contemplated for
To impact of the wind-powered electricity generation forecast error to management scheme, need using more accurate wind-powered electricity generation prediction algorithm to optimize energy management
Scheme.
2) in order to solve the above problems, energy conservation problem is modeled as into a triphasic Stackelberg first and is won
Model is played chess, Fig. 2 is the block diagram of three layers of Stackelberg betting models, can clearly describe grid company, energy storage company is micro-
Net, the process of dynamic relationship and energy Flow between user, by analyzing betting model using backward induction method method, draw optimum
Management scheme.Subsequently propose one kind combine automatic coding, back-propagation algorithm and genetic algorithm short-term it is pre-
Survey wind power algorithm and reduce impact of the wind-powered electricity generation forecast error to management scheme.Fig. 3 is by carrying the pre- of wind-powered electricity generation prediction algorithm
Process and trim process.
For the present invention, a large amount of emulation are We conducted.Fig. 4 is that microgrid is to electricity in the case that wind-powered electricity generation forecast error is zero
The power purchase strategy of net and energy storage company is with user's primary demand variation diagram.Indicate with the increase of user's primary demand, microgrid
To grid company and purchase of electricity L of energy storage companym,g, Lm,sAlso it is being continuously increased, simultaneously because microgrid is to storing regenerative resource
Energy storage company there is higher preference degree, therefore Lm,s>Lm,g.When Fig. 5 is the presence of wind-powered electricity generation forecast error, in the different bases of user
Under this demand, the benefit of microgrid is with wind-powered electricity generation forecast error variation diagram.This it appears that microgrid benefit is with forecast error
Increase and reduce, therefore we need accurately to be predicted wind-powered electricity generation.Fig. 6 is that wind-powered electricity generation is averagely exhausted under different forecast models
To percentage error MAPE with the change of prediction step number.With the increase of prediction step number, MAPE, but can be with also constantly increasing
Find out that, compared to other two kinds of models, wind-powered electricity generation forecast model proposed by the present invention has higher degree of accuracy.
Although disclosing being embodied as and accompanying drawing for the present invention for the purpose of illustration, its object is to help understand the present invention's
Content is simultaneously implemented according to this, but it will be appreciated by those skilled in the art that：Without departing from claim of the invention and appended
In spirit and scope, various replacements, to change and modifications all be possible.Therefore, the present invention should not be limited to most preferred embodiment and
Accompanying drawing disclosure of that, the scope of protection of present invention are defined by the scope that claims are defined.
Claims (3)
1. a kind of distributed energy management algorithm predicted the outcome based on short-term wind-electricity applied in energy conservation, its feature are existed
In：
1）Propose that one kind combines the short-term forecast wind power algorithm of automatic coding, back-propagation algorithm and genetic algorithm；
2）Predicted based on short-term wind-electricity power, energy conservation problem is modeled as into a triphasic Stackelberg game, is retouched
Grid company, energy storage company, the dynamic relationship between microgrid and user are stated, and betting model have been analyzed using backward induction method method,
Draw the rwan management solution RWAN of optimum.
2. such as claim 1 step 1）Described one kind combines the short of automatic coding, back-propagation algorithm and genetic algorithm
Phase predicts wind power algorithm, and its core is to set up the forecast model trained based on historical data；Wind-powered electricity generation prediction process can be with
It is divided into two processes：Including preprocessing process and trim process；In preprocessing process, including visual layers, hidden layer and output
Layer；In trim process, can calculate overall in the multiple Rotating fields of finally addition of pretreatment network and using back-propagation algorithm
The initial weight of network；Additionally, the precision in order to improve prediction, we optimize of each encoder using genetic algorithm
Practise the neuron number of speed and per layer.
3. such as claim 1 step 2）The described three stage Stackelberg betting models predicted based on short-term wind-electricity, which is special
Levy and be, describe grid company, energy storage company, the dynamic relationship between microgrid and user, and analyzed using backward induction method method
Betting model, draws the rwan management solution RWAN of optimum；Wherein three stages Stackelberg game description includes that three below is walked
Suddenly：
1）First stage：Electrical network and energy storage company, as the leader of game, take the lead in issuing electricity priceWith；
2）Second stage；Microgrid, as the center of EMS, according to the electricity price of first stageWith, it is determined that to electrical network
With the purchase of electricity of energy storage companyWith, while determining microgrid electricity price；
3）Phase III：K-th user, as the follower of game, determines the purchase of electricity of k-th user according to the electricity price of microgrid；
Betting model, including three below step are analyzed using backward induction method method：
Phase III user's game theory analysis：In view of satisfaction and purchases strategies of the user to microgrid, the benefit letter of k-th user
Number can be configured such that：
Wherein：
Extent function of k-th user of representative to microgrid,WithIt is satisfaction parameter；Thus, the optimization of user is asked
Topic can be expressed as：
,, in constraintsRepresent the primary demand of k-th user；
2）Second stage microgrid game theory analysis：In view of microgrid to electrical network and the satisfaction of energy storage company, purchases strategies, wind-powered electricity generation are sent out
Electric cost, pollutant emission cost and forecast error punishment cost, the benefit function of microgrid can be configured such that：
-+---+F, in formulaWithSatisfaction letter of the microgrid to electrical network and energy storage company is represented respectively
Number,The k total purchase of electricity of user is represented,WithRepresent respectively wind-powered electricity generation cost of electricity-generating and
Pollutant emission cost, whereinThe true generated energy of wind-powered electricity generation is represented,It is wind-powered electricity generation forecast error, FRepresent wind-powered electricity generation prediction to produce
Punishment cost during error, F are penalty coefficient；Thus, the optimization problem of microgrid can be expressed as：
,
,
,
,
=max{}；
In constraints,Electrical network maximum output is represented,Energy storage company maximum storage is represented,Represent
The ceiling price that user can bear；
3）First stage electrical network and energy storage company game theory analysis：In view of cost of electricity-generating, pollutant emission cost and line loss,
The benefit function of electrical network can be configured such that：=, in formulaWithCost of electricity-generating and pollutant emission cost are represented respectively,It is line loss coefficient；Thus, the optimization of grid company is asked
Topic can be expressed as：；In the same manner, it is contemplated that the charge and discharge electrical loss of energy storage device and line loss, energy storage company
Benefit function can be configured such that：=, wherein=Represent total energy storage into
This, in formulaIt is unit energy storage cost,It is line loss coefficient,WithThe efficiency for charge-discharge of energy storage device is represented respectively；Thus,
The optimization problem of energy storage company can be expressed as:。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710035808.7A CN106600078A (en) | 2017-01-17 | 2017-01-17 | Micro-grid energy management scheme based on new energy power generation forecasting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710035808.7A CN106600078A (en) | 2017-01-17 | 2017-01-17 | Micro-grid energy management scheme based on new energy power generation forecasting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106600078A true CN106600078A (en) | 2017-04-26 |
Family
ID=58585856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710035808.7A Pending CN106600078A (en) | 2017-01-17 | 2017-01-17 | Micro-grid energy management scheme based on new energy power generation forecasting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106600078A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657946A (en) * | 2018-09-19 | 2019-04-19 | 清华大学 | The mathematical model and planing method of Regional Energy internet planning based on game theory |
| CN110571872A (en) * | 2019-09-09 | 2019-12-13 | 江苏方天电力技术有限公司 | Pumped storage power station phase modulation compensation method based on Stackelberg game model |
| CN113550872A (en) * | 2021-09-22 | 2021-10-26 | 深圳市特发信息数据科技有限公司 | Energy consumption monitoring system of wind power data center |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130024243A1 (en) * | 2011-07-20 | 2013-01-24 | Nec Laboratories America, Inc. | Systems and methods for optimizing microgrid capacity and storage investment under environmental regulations |
| CN103729698A (en) * | 2014-01-16 | 2014-04-16 | 国家电网公司 | Requirement responding scheduling method for wind power uncertainty |
| CN103839109A (en) * | 2013-10-19 | 2014-06-04 | 李涛 | Microgrid power source planning method based on game and Nash equilibrium |
| CN105071389A (en) * | 2015-08-19 | 2015-11-18 | 华北电力大学（保定） | Hybrid AC/DC microgrid optimization operation method and device considering source-grid-load interaction |
| CN105591406A (en) * | 2015-12-31 | 2016-05-18 | 华南理工大学 | Optimization algorithm of micro-grid energy management system based on non-cooperation game |
-
2017
- 2017-01-17 CN CN201710035808.7A patent/CN106600078A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130024243A1 (en) * | 2011-07-20 | 2013-01-24 | Nec Laboratories America, Inc. | Systems and methods for optimizing microgrid capacity and storage investment under environmental regulations |
| CN103839109A (en) * | 2013-10-19 | 2014-06-04 | 李涛 | Microgrid power source planning method based on game and Nash equilibrium |
| CN103729698A (en) * | 2014-01-16 | 2014-04-16 | 国家电网公司 | Requirement responding scheduling method for wind power uncertainty |
| CN105071389A (en) * | 2015-08-19 | 2015-11-18 | 华北电力大学（保定） | Hybrid AC/DC microgrid optimization operation method and device considering source-grid-load interaction |
| CN105591406A (en) * | 2015-12-31 | 2016-05-18 | 华南理工大学 | Optimization algorithm of micro-grid energy management system based on non-cooperation game |
Non-Patent Citations (1)
| Title |
|---|
| ZHENYU ZHOU等: ""Game-Theoretical Energy Management for Energy Internet With Big Data-Based Renewable Power Forecasting"", 《IEEE ACCESS》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657946A (en) * | 2018-09-19 | 2019-04-19 | 清华大学 | The mathematical model and planing method of Regional Energy internet planning based on game theory |
| CN109657946B (en) * | 2018-09-19 | 2024-01-02 | 清华大学 | Mathematical model and planning method for regional energy Internet planning based on game theory |
| CN110571872A (en) * | 2019-09-09 | 2019-12-13 | 江苏方天电力技术有限公司 | Pumped storage power station phase modulation compensation method based on Stackelberg game model |
| CN113550872A (en) * | 2021-09-22 | 2021-10-26 | 深圳市特发信息数据科技有限公司 | Energy consumption monitoring system of wind power data center |
| CN113550872B (en) * | 2021-09-22 | 2021-12-07 | 深圳市特发信息数据科技有限公司 | Energy consumption monitoring system of wind power data center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107301470B (en) | Double-layer optimization method for power distribution network extension planning and optical storage location and volume fixing | |
| Sandgani et al. | Coordinated optimal dispatch of energy storage in a network of grid-connected microgrids | |
| CN110276698B (en) | Distributed renewable energy transaction decision method based on multi-agent double-layer collaborative reinforcement learning | |
| CN105071389B (en) | The alternating current-direct current mixing micro-capacitance sensor optimizing operation method and device of meter and source net load interaction | |
| Zhao et al. | Distributed model predictive control strategy for islands multimicrogrids based on noncooperative game | |
| Tushar et al. | Distributed real-time electricity allocation mechanism for large residential microgrid | |
| Wang et al. | Privacy-preserving energy scheduling in microgrid systems | |
| CN106447122A (en) | Area type energy Internet and integrated optimization planning method thereof | |
| Li et al. | Hybrid time-scale energy optimal scheduling strategy for integrated energy system with bilateral interaction with supply and demand | |
| De Santis et al. | Genetic optimization of a fuzzy control system for energy flow management in micro-grids | |
| CN111030188A (en) | Hierarchical control strategy containing distributed and energy storage | |
| Yin et al. | Energy pricing and sharing strategy based on hybrid stochastic robust game approach for a virtual energy station with energy cells | |
| CN107706932A (en) | A kind of energy method for optimizing scheduling based on dynamic self-adapting fuzzy logic controller | |
| CN106600078A (en) | Micro-grid energy management scheme based on new energy power generation forecasting | |
| Huang et al. | Smart energy management system based on reconfigurable AI chip and electrical vehicles | |
| CN108667077A (en) | A kind of wind storage association system Optimization Scheduling | |
| Peng et al. | Sequential coalition formation for wind-thermal combined bidding | |
| Abedinia et al. | Synergizing efficient optimal energy hub design for multiple smart energy system players and electric vehicles | |
| Zhou et al. | Energy management for energy internet: a combination of game theory and big data-based renewable power forecasting | |
| CN115983598A (en) | Micro-grid privacy protection and energy scheduling method based on distributed deep reinforcement learning | |
| CN105514986A (en) | DER user bidding grid-connection method based on virtual power plant technology | |
| Qiu et al. | Local integrated energy system operational optimization considering multi‐type uncertainties: A reinforcement learning approach based on improved TD3 algorithm | |
| CN112116131B (en) | Multi-level optimization method for comprehensive energy system considering carbon emission | |
| Qi et al. | Deep Reinforcement Learning Based Charging Scheduling for Household Electric Vehicles in Active Distribution Network | |
| CN114462854A (en) | Hierarchical scheduling method and system containing new energy and electric vehicle grid connection |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170426 |
|
| WD01 | Invention patent application deemed withdrawn after publication |