CN109242193A - A kind of dynamic need response pricing method based on intensified learning - Google Patents
A kind of dynamic need response pricing method based on intensified learning Download PDFInfo
- Publication number
- CN109242193A CN109242193A CN201811109071.XA CN201811109071A CN109242193A CN 109242193 A CN109242193 A CN 109242193A CN 201811109071 A CN201811109071 A CN 201811109071A CN 109242193 A CN109242193 A CN 109242193A
- Authority
- CN
- China
- Prior art keywords
- load
- model
- user
- intensified learning
- responds
- 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
- 230000004044 response Effects 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000005611 electricity Effects 0.000 claims abstract description 20
- 238000005381 potential energy Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims abstract description 7
- 238000005265 energy consumption Methods 0.000 claims description 3
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 5
- 230000007812 deficiency Effects 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000009467 reduction Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 4
- 238000010248 power generation Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
-
- 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
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The dynamic need that the invention discloses a kind of based on intensified learning responds pricing method, comprising steps of S1, establishing layered education model, including workload demand response model, load provider model and its target function model;S2, the model established to step S1 are based on nitrification enhancement and are solved to obtain optimal zero potential energy.The present invention finds reasonable electricity price in the case where considering that load responding is uncertain, the probabilistic deficiency of load responding is not accounted for for dynamic need response pricing model, it is proposed the workload demand response model in Power Market Structure, load provider Optimized model and target function model, and propose that the dynamic need based on intensified learning responds pricing steps, not only fully consider the uncertainty of load responding, also adapt to the Power Market of dynamic change, improve computational efficiency, real-time optimal pricing strategy is found by optimization, it is unbalanced to play the role of raising electric network reliability reduction energy.
Description
Technical field
The present invention relates to a kind of, and the dynamic need based on intensified learning responds pricing method.
Background technique
With the development of power distribution network mechanics of communication, because Demand Side Response has flexible regulating effect, demand in load side
Side responds into improve electric network reliability and reduce the effective ways of energy loss.Price type demand response makes user according to reality
The electricity price signal of Shi Bianhua changes it and uses power mode, achievees the purpose that Load adjustment curve.Dynamic need responds price-setting process
One decision process, its object is to find a reasonable electricity price with the electric energy service of distribution system.Demand response price mould
Type often uses determining pricing model, such as timesharing pricing model, can not reflect the energy of real-time dynamic marketplace well
Uncertainty.Dynamic price pricing model usually utilizes linear pricing model, without reasonable logic price-setting process, and not
It can reflect the complexity of demand response distribution.
Intensified learning (Reinforcement learning, RL) is a kind of intelligent algorithm.Nitrification enhancement is borrowed
Mirror behaviour psychology, is one kind of machine learning, can be used for decision problem.Intensified learning by individual to uncertain environment not
The disconnected reward for taking action to maximize some decisions.Be conducive to fully consider electricity in pricing model using nitrification enhancement
The uncertainty and flexibility in power market.
Summary of the invention
It is an object of the invention to overcome the shortcomings of conventional dynamic demand response pricing algorithm, propose based on intensified learning
Dynamic need responds pricing algorithm, which sufficiently can consider determining for electricity price for the uncertainty of electricity market and flexibility
In plan.
The technical solution adopted by the present invention is that:
A kind of dynamic need response pricing method based on intensified learning, comprising steps of
S1, layered education model, including workload demand response model, load provider model and its target letter are established
Exponential model;
S2, the model established to step S1 are based on nitrification enhancement and are solved to obtain optimal zero potential energy.
Further, it in step S1, establishes workload demand response model and specifically includes:
S11, the model for establishing basic load and interruptible load model:
In the workload demand response model, load includes interruptible load, the basic load for being not involved in demand response, institute
State the model of basic load are as follows:
In formula,WithIt is illustrated respectively in the energy consumption and actual energy demand of t period user n;t∈{1,2,
3 ... T }, T indicates one day total time number of segment;N ∈ { 1,2,3 ... N }, N indicate that total number of users, subscript b indicate basic load;
The interruptible load model are as follows:
ξt<0
λt,n≥πt
In formula, ξtIt is the load responding coefficient of elasticity of t period, value is less than zero;λt,nIndicate user n in time period t
Zero potential energy;πtIndicate the wholesale electricity price of t period.For energy requirement can be interrupted;
S12, the minimum cost target mould that user is determined according to the model and interruptible load model of the basic load
Type:
Wherein,Indicate total actual load consumption desired value,Indicate user n in time period t
Dissatisfaction:
αn>0,βn>0
In formula, αnAnd βnIndicate load to the response parameter of cutting load amount;DminAnd DmaxRespectively indicate load minimum and most
Big cutting load amount.
Further, in step S1, the purpose for establishing load provider model is earning zero potential energy and wholesale electricity price
Maximum return, concrete model are as follows:
πt,min≤λt,n≤πt,max
Further, in step S1, when the income of the cost and load provider that consider user simultaneously, the target letter
Exponential model are as follows:
In formula, ρ ∈ [0,1] indicates the weight relationship of user's cost and load provider.
Further, the step S2 is specifically included:
Step S21: initiation parameter, comprising: the energy requirement E of loadt,n;Response parameter α of the load to cutting load amountn、
βn;The minimum and maximum cutting load amount D of loadmin、Dmax;Wholesale electricity price πn;The weight coefficient θ of reward;User's cost and load mention
For the weight relationship ρ of quotient;
Step S22: initialization Q (et,n|Et,n,λt,n), each element is zero in Q table, sets time period t=0, the number of iterations i=
0;
Step S23: energy requirement E of the observation user in t=1t,n;
Step S24: zero potential energy λ is selected with greedy strategyt,n;
Step S25: calculating reward is objective function
User is observed in the energy requirement E of time period t+1t+1,n, and update Q value;
Step S26: judging whether to reach maximum time period T, is to go to next step, otherwise, t=t+1,
Return step S24;
Step S27: judging whether Q table converges to maximum value, is, goes to next step, otherwise, i=i+1,
Return step S23;
Step S28: the optimal zero potential energy of T period in output one day.
Further, in step S25, the Q value can be used following formula to update:
Q(et,n|Et,n,λt,n)←Q(et,n|Et,n,λt,n)+θ[r(et,n|Et,n,λt,n)+γmaxQ(et+1,n|Et+1,n,
λt+1,n)-Q(et,n|Et,n,λt,n)]
Wherein, θ is the weight coefficient of reward, and γ indicates discount factor.
Compared with prior art, the beneficial effect that the present invention reaches is:
In calculating process, the uncertainty of load is fully considered, do not account for for dynamic need response pricing model
The probabilistic deficiency of load responding is suitble to the Power Market of real-time change, increases the reasonability of Dynamic Pricing, improves meter
Efficiency is calculated, real-time optimal pricing strategy is found by optimization algorithm, plays and improves the electric network reliability reduction unbalanced work of energy
With.
Detailed description of the invention
Fig. 1 is layered education model schematic.
Fig. 2 is the flow diagram for being solved to obtain optimal zero potential energy based on nitrification enhancement.
Specific embodiment
The present invention is described further with reference to the accompanying drawings and examples.
A kind of dynamic need response pricing method based on intensified learning, comprising steps of
S1, layered education model, including workload demand response model, load provider model and its target letter are established
Exponential model;
S2, the model established to step S1 are based on nitrification enhancement and are solved to obtain optimal zero potential energy.
As shown in Figure 1, the energy is sold to load provider by energy producers with wholesale price, then by load provider to be sold
Valence is sold to consumption user.Exchange information between three is mainly power purchase price and electricity consumption.Wherein, load provider and consumption
The information exchange of retail price and pricing decision mechanism between user are then the dynamics based on intensified learning provided by the present embodiment
Workload demand responds pricing method.
Specifically, in step S1, establishing workload demand response model in step S1 and specifically including:
S11, the model for establishing basic load and interruptible load model:
In the workload demand response model, load includes interruptible load, the basic load for being not involved in demand response, institute
State the model of basic load are as follows:
In formula,WithIt is illustrated respectively in the energy consumption and actual energy demand of t period user n;t∈{1,2,
3 ... T }, T indicates one day total time number of segment;N ∈ { 1,2,3 ... N }, N indicate that total number of users, subscript b indicate basic load;
The interruptible load model are as follows:
ξt<0
λt,n≥πt
In formula, ξtIt is the load responding coefficient of elasticity of t period, value is less than zero;λt,nIndicate user n in time period t
Zero potential energy;πtIndicate the wholesale electricity price of t period.For energy requirement can be interrupted;
S12, the minimum cost target mould that user is determined according to the model and interruptible load model of the basic load
Type:
Wherein,Indicate total actual load consumption desired value,Indicate user n in time period t
Dissatisfaction:
αn>0,βn>0
In formula, αnAnd βnIndicate load to the response parameter of cutting load amount;DminAnd DmaxRespectively indicate load minimum and most
Big cutting load amount.
Specifically, the purpose for establishing load provider model is earning zero potential energy and wholesale electricity price in step S1
Maximum return, concrete model are as follows:
πt,min≤λt,n≤πt,max
Specifically, in step S1, when the income of the cost and load provider that consider user simultaneously, the target letter
Exponential model are as follows:
In formula, ρ ∈ [0,1] indicates the weight relationship of user's cost and load provider.
Specifically, as shown in Fig. 2, the step S2 is specifically included:
Step S21: initiation parameter, comprising: the energy requirement E of loadt,n;Response parameter α of the load to cutting load amountn、
βn;The minimum and maximum cutting load amount D of loadmin、Dmax;Wholesale electricity price πn;The weight coefficient θ of reward;User's cost and load mention
For the weight relationship ρ of quotient;
Step S22: initialization Q (et,n|Et,n,λt,n), each element is zero in Q table, sets time period t=0, the number of iterations i=
0;
Step S23: energy requirement E of the observation user in t=1t,n;
Step S24: zero potential energy λ is selected with greedy strategyt,n;
Step S25: calculating reward is objective function
User is observed in the energy requirement E of time period t+1t+1,n, and Q value is updated, the Q value can be used following formula to update:
Q(et,n|Et,n,λt,n)←Q(et,n|Et,n,λt,n)+θ[r(et,n|Et,n,λt,n)+γmaxQ(et+1,n|Et+1,n,
λt+1,n)-Q(et,n|Et,n,λt,n)] wherein, θ is the weight coefficient of reward, and γ indicates discount factor;
Step S26: judging whether to reach maximum time period T, is to go to next step, otherwise, t=t+1, return step
S24;
Step S27: judging whether Q table converges to maximum value, is, goes to next step, otherwise, i=i+1, return step
S23;
Step S28: the optimal zero potential energy of T period in output one day.
The power demand E that load provider passes through collection consumption usert,n, the initialization such as user's dissatisfaction coefficient ginseng
Number, a kind of pricing method of the dynamic load demand response based on intensified learning proposed through the invention acquire objective function
It maximizes, the optimization retail price of calculating is distributed to consumption user, while feeding back electricity consumption demand to power generation department,
Power generation department then instructs power generation.
The present invention finds reasonable electricity price in the case where considering that load responding is uncertain, and it is fixed to respond for dynamic need
Valence model does not account for the probabilistic deficiency of load responding, proposes workload demand response model, service provider's model and mesh
Offer of tender exponential model, and the step of place responds pricing algorithm based on the dynamic need of intensified learning is mentioned, it can not only fully consider negative
The uncertainty of lotus response, moreover it is possible to adapt to the environment of the electricity market of dynamic change.
The above is only the embodiment of the present invention, is not intended to limit the present invention in any form, although originally
Invention is disclosed above with embodiment, however is not intended to limit the present invention, any person skilled in the art, is not taking off
From within the scope of technical solution of the present invention, when the technology contents using the disclosure above make a little change or are modified to equivalent variations
Equivalent embodiment, but without departing from the technical solutions of the present invention, according to the technical essence of the invention to above embodiments
Made simple modification, equivalent change and modification, all of which are still within the scope of the technical scheme of the invention.
Claims (6)
1. a kind of dynamic need based on intensified learning responds pricing method, which is characterized in that comprising steps of
S1, layered education model, including workload demand response model, load provider model and its objective function mould are established
Type;
S2, the model established to step S1 are based on nitrification enhancement and are solved to obtain optimal zero potential energy.
2. a kind of dynamic need based on intensified learning according to claim 1 responds pricing method, it is characterised in that: step
In rapid S1, establishes workload demand response model and specifically includes:
S11, the model for establishing basic load and interruptible load model:
In the workload demand response model, load includes interruptible load, the basic load for being not involved in demand response, the base
The model of plinth load are as follows:
In formula,WithIt is illustrated respectively in the energy consumption and actual energy demand of t period user n;T ∈ { 1,2,3 ... T },
T indicates one day total time number of segment;N ∈ { 1,2,3 ... N }, N indicate that total number of users, subscript b indicate basic load;
The interruptible load model are as follows:
ξt<0
λt,n≥πt
In formula, ξtIt is the load responding coefficient of elasticity of t period, value is less than zero;λt,nIndicate user n in the retail of time period t
Electricity price;πtIndicate the wholesale electricity price of t period.For energy requirement can be interrupted;
S12, the minimum cost object module that user is determined according to the model and interruptible load model of the basic load:
Wherein,Indicate total actual load consumption desired value,Indicate user n in the discontented of time period t
Meaning degree:
αn>0,βn>0
In formula, αnAnd βnIndicate load to the response parameter of cutting load amount;DminAnd DmaxThe minimum and maximum for respectively indicating load is cut
Load.
3. a kind of dynamic need based on intensified learning according to claim 2 responds pricing method, it is characterised in that: step
In rapid S1, the purpose for establishing load provider model is to earn the maximum return of zero potential energy and wholesale electricity price, concrete model are as follows:
4. a kind of dynamic need based on intensified learning according to claim 3 responds pricing method, it is characterised in that: step
In rapid S1, when the income of the cost and load provider that consider user simultaneously, the target function model are as follows:
In formula, ρ ∈ [0,1] indicates the weight relationship of user's cost and load provider.
5. a kind of dynamic need based on intensified learning according to claim 2 responds pricing method, it is characterised in that: institute
Step S2 is stated to specifically include:
Step S21: initiation parameter, comprising: the energy requirement E of loadt,n;Response parameter α of the load to cutting load amountn、βn;It is negative
The minimum and maximum cutting load amount D of lotusmin、Dmax;Wholesale electricity price πn;The weight coefficient θ of reward;User's cost and load provider
Weight relationship ρ;
Step S22: initialization Q (et,n|Et,n,λt,n), each element is zero in Q table, sets time period t=0, the number of iterations i=0;
Step S23: energy requirement E of the observation user in t=1t,n;
Step S24: zero potential energy λ is selected with greedy strategyt,n;
Step S25: calculating reward is objective functionIt sees
User is examined in the energy requirement E of time period t+1t+1,n, and update Q value;
Step S26: judging whether to reach maximum time period T, is to go to next step, otherwise, t=t+1, return step S24;
Step S27: judging whether Q table converges to maximum value, is, goes to next step, otherwise, i=i+1, return step S23;
Step S28: the optimal zero potential energy of T period in output one day.
6. a kind of dynamic need based on intensified learning according to claim 5 responds pricing method, it is characterised in that: step
In rapid S25, the Q value can be used following formula to update:
Q(et,n|Et,n,λt,n)←Q(et,n|Et,n,λt,n)+θ[r(et,n|Et,n,λt,n)+γmaxQ(et+1,n|Et+1,n,λt+1,n)-Q
(et,n|Et,n,λt,n)] wherein, θ is the weight coefficient of reward, and γ indicates discount factor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811109071.XA CN109242193A (en) | 2018-09-21 | 2018-09-21 | A kind of dynamic need response pricing method based on intensified learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811109071.XA CN109242193A (en) | 2018-09-21 | 2018-09-21 | A kind of dynamic need response pricing method based on intensified learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109242193A true CN109242193A (en) | 2019-01-18 |
Family
ID=65057493
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811109071.XA Pending CN109242193A (en) | 2018-09-21 | 2018-09-21 | A kind of dynamic need response pricing method based on intensified learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109242193A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110084494A (en) * | 2019-04-12 | 2019-08-02 | 国网(苏州)城市能源研究院有限责任公司 | A kind of flexible power load soft readjustment method based on Spot Price |
CN110111135A (en) * | 2019-04-09 | 2019-08-09 | 广东电力交易中心有限责任公司 | A kind of Generation Side member dynamic pricing decision-making technique, device and equipment |
CN110705738A (en) * | 2019-08-13 | 2020-01-17 | 合肥工业大学 | Intelligent electricity utilization stimulation demand response method and system based on artificial intelligence |
CN111369108A (en) * | 2020-02-20 | 2020-07-03 | 华中科技大学鄂州工业技术研究院 | Power grid real-time pricing method and device |
CN111598721A (en) * | 2020-05-08 | 2020-08-28 | 天津大学 | Load real-time scheduling method based on reinforcement learning and LSTM network |
CN112329980A (en) * | 2020-09-24 | 2021-02-05 | 国网辽宁省电力有限公司沈阳供电公司 | Method for improving power grid operation level by machine learning fixed electricity price |
-
2018
- 2018-09-21 CN CN201811109071.XA patent/CN109242193A/en active Pending
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111135A (en) * | 2019-04-09 | 2019-08-09 | 广东电力交易中心有限责任公司 | A kind of Generation Side member dynamic pricing decision-making technique, device and equipment |
CN110111135B (en) * | 2019-04-09 | 2023-04-07 | 广东电力交易中心有限责任公司 | Power generation side member dynamic quotation decision method, device and equipment |
CN110084494A (en) * | 2019-04-12 | 2019-08-02 | 国网(苏州)城市能源研究院有限责任公司 | A kind of flexible power load soft readjustment method based on Spot Price |
CN110705738A (en) * | 2019-08-13 | 2020-01-17 | 合肥工业大学 | Intelligent electricity utilization stimulation demand response method and system based on artificial intelligence |
CN111369108A (en) * | 2020-02-20 | 2020-07-03 | 华中科技大学鄂州工业技术研究院 | Power grid real-time pricing method and device |
CN111598721A (en) * | 2020-05-08 | 2020-08-28 | 天津大学 | Load real-time scheduling method based on reinforcement learning and LSTM network |
CN112329980A (en) * | 2020-09-24 | 2021-02-05 | 国网辽宁省电力有限公司沈阳供电公司 | Method for improving power grid operation level by machine learning fixed electricity price |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109242193A (en) | A kind of dynamic need response pricing method based on intensified learning | |
Yuyin et al. | The effect of governmental policies of carbon taxes and energy-saving subsidies on enterprise decisions in a two-echelon supply chain | |
CN110378058A (en) | A kind of method for building up for the electro thermal coupling microgrid optimal response model comprehensively considering reliability and economy | |
Bu et al. | A game-theoretical decision-making scheme for electricity retailers in the smart grid with demand-side management | |
Sianaki et al. | A knapsack problem approach for achieving efficient energy consumption in smart grid for endusers' life style | |
CN110728410A (en) | Load aggregator economic scheduling method considering demand response flexibility and uncertainty | |
CN110276698A (en) | Distribution type renewable energy trade decision method based on the study of multiple agent bilayer cooperative reinforcing | |
CN106846179B (en) | Resident load double-layer scheduling optimization method based on non-cooperative game | |
CN105006843A (en) | Multi-time-scale flexible load scheduling method for handling wind power uncertainties | |
CN109617133A (en) | A kind of electric power system dispatching method considering flexible load | |
CN108279566A (en) | A kind of more household electricity energy requirements response regulation and control method of Load aggregation quotient | |
CN108537363B (en) | Electricity purchasing amount control method for electricity selling company under distribution and sale separated environment | |
CN109461019A (en) | A kind of dynamic need response pricing method based on Fuzzy Reinforcement Learning | |
CN112036934A (en) | Quotation method for participation of load aggregators in demand response considering thermoelectric coordinated operation | |
TWI767525B (en) | Method and apparatus for renewable energy allocation based on reinforcement learning | |
Meng et al. | A bilevel optimization approach to demand response management for the smart grid | |
CN115276047A (en) | Electric energy scheduling method and device and computer readable storage medium | |
Chasparis et al. | A cooperative demand-response framework for day-ahead optimization in battery pools | |
CN106203674A (en) | A kind of dispatching management information system for energy-storage system | |
CN109726894A (en) | Ensure the new energy active command calculation method of spot exchange and medium-term and long-term electricity | |
CN111985783A (en) | Power load demand response game modeling method | |
CN111080014A (en) | Load curve optimization method based on load aggregator non-cooperative game | |
CN109492905A (en) | A kind of controllable resources control method based on purchase of electricity transfer | |
Liu et al. | Optimal design of a score-based incentive mechanism for promoting demand response participations of residential users | |
CN110135625A (en) | A kind of two stages price competing method for the end-to-end transaction of community's microgrid |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |
|
RJ01 | Rejection of invention patent application after publication |