CN108921601A - A kind of power spot market auxiliary method of commerce neural network based - Google Patents
A kind of power spot market auxiliary method of commerce neural network based Download PDFInfo
- Publication number
- CN108921601A CN108921601A CN201810638002.1A CN201810638002A CN108921601A CN 108921601 A CN108921601 A CN 108921601A CN 201810638002 A CN201810638002 A CN 201810638002A CN 108921601 A CN108921601 A CN 108921601A
- Authority
- CN
- China
- Prior art keywords
- scheme
- clear
- neural network
- declare
- declaring
- 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
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- 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
Abstract
The invention discloses a kind of power spot markets neural network based to assist method of commerce, and method includes the following steps:1. declaring using history and clear data training neural network model out, the amount of the declaring valence and the relationship between clear amount valence out of single period are simulated;Respectively cooperate power plant 2. the same day is declared in calculating and declare electricity in each period;3. generating multiple entirety comprising all cooperation power plants for the single period declares scheme;4. the different schemes of declaring of single period are sequentially input neural network model, the corresponding clear valence out of scheme is each declared using Neural Network model predictive with clear amount, calculating is gone out and each declares the prediction income of scheme;And calculation risk coefficient;5. in conjunction with prediction income and risk factor, final choice go out each period it is optimal declare scheme;6. by each period it is optimal declare the report amount respectively cooperating power plant in scheme and should selecting --- the information of quotation pair is sent to each power plant, instructs each power plant to complete power spot market and declares process.
Description
Technical field
The present invention relates to power spot market fields, more particularly to a kind of power spot market neural network based
Assist method of commerce.
Background technique
Spot market usually refers exclusively to the Real-time markets that the instant physics of commodity is completed a business transaction, it is contemplated that the instantaneous confession that electricity commodity is completed a business transaction
It need to need to keep the feature of balance, the time range of power spot market generally comprises on the day before system real-time prompt day to real-time
Between operation.Power spot market voluntarily participates in declaring generally by the way of market pricing, by market member, and to being formed
Trading program carry out physical delivery and clearing.Spot market construction generally comprises ahead market, in a few days market and Real-time markets
Three parts.There is larger differences on specific building mode for the power spot market of countries in the world, from Object of Transaction, transaction
System, clear mode, price mechanism etc. have different designs out.
2017, the provinces such as China Gansu, Qinghai, Ningxia and Xinjiang Uygur Autonomous Regions started pilot operation affluence newly
The energy transprovincially area spot market.But new energy electric power electricity spot exchange transprovincially more than needed is still in starting stage, market ginseng
Deep understanding is not yet established to spot exchange rule with main body.It is found after we are to transaction history data analysis:Market is whole
For body quote situations there are biggish fluctuation, the case where inertia quotation and irrational quotation, is relatively conventional.Based on the above status, and
In view of power spot market still has the prospect of dilatation, a kind of power spot market auxiliary method of commerce is developed, is electricity power enterprise
The market price bidding that fills your offer decision support service just very it is necessary to.
Artificial neural network (Artificial Neural Network, ANN), abbreviation neural network (Neural
Network, NN), it is the mathematical model or calculating of a kind of structure and function of mimic biology neural network in machine learning field
Model interconnects non-linear, the adaptive information processing system that form by a large amount of processing units, for function carry out estimation or
It is approximate.By the development of many decades, the research work of neural network deepens continuously, there has been proposed various neural network models,
Mainly have according to learning strategy classification:The neural network model of the types such as supervised, unsupervised formula, hybrid and association type;According to net
The classification of network framework mainly has:The neural network model of the types such as feedforward neural network and recurrent neural network.
Neural network model is introduced power spot market aid decision field by the present invention, it is intended that provides electricity for electricity power enterprise
The decision support service that power spot market is bidded improves the income that electricity power enterprise participates in electric power spot exchange, improves electricity power enterprise
The enthusiasm for participating in power spot market competition, is conducive to the construction and development of China's power spot market.
Summary of the invention
The purpose of the present invention is:The decision support service that power spot market is bidded is provided for electricity power enterprise, improves power generation
The income of enterprise's participation electric power spot exchange.The technical solution adopted by the present invention is that:Provide a kind of electricity neural network based
Power spot market assists method of commerce.
A kind of power spot market neural network based auxiliary method of commerce includes the following steps:
Step 1 goes out clear data to power spot market history declaration data and history and pre-processes, and arranges and generates mark
The data file of quasiconfiguaration;It is declared using the history of reference format and clear data trains neural network model out, when simulating single
The amount of the declaring valence of section and the out relationship between clear amount valence;
Step 2 declares the same day in power spot market, by each cooperation power plant predicting in each period on the same day
The Foundation Planning electricity that power subtracts each period obtains each cooperation power plant and declares electricity in each period;
Step 3 declares electricity based on each cooperation power plant, it is optional to enumerate each cooperation power plant within the single period
The report amount selected --- quotation pair, and be combined into multiple entirety comprising all cooperation power plants and declare scheme;Each declare
It include multiple groups report amount-quotation pair in scheme;
Each of the single period scheme of declaring is sequentially input neural network model, utilizes neural network model by step 4
It simulates clearly, the corresponding clear valence out of scheme and clear amount out are each declared in prediction;After deducting cost of electricity-generating, calculates and each declare scheme
Prediction income;Risk assessment is carried out to the different schemes of declaring of single period, calculates the risk factor for each declaring scheme;
Step 5 filters out the single period most by preset appraisal procedure in conjunction with prediction income and risk evaluation result
Excellent declares scheme;
Step 6, by obtained each period it is optimal declare the report amount that each cooperation power plant should select in scheme ---
The information of quotation pair is sent to each power plant, instructs each power plant to complete power spot market and declares process.
Preferably, a kind of power spot market neural network based assists method of commerce, it is characterised in that:
The history declaration data includes:Declare the declared value for declaring electricity and each station of time, each station;The history is clear out
Data include:Out the clear time, each station go out clear electricity and each station cleaing price.The pretreatment includes:Data cleansing,
The treatment processes such as data integration, data transformation and hough transformation.
Preferably, the neural network model is:BP neural network, convolutional neural networks (Convolutional
Neural Network, CNN) or Recognition with Recurrent Neural Network (Recurrent Neural Network, RNN).
Preferably, the prediction income is specifically calculated using the following equation:
Each declaring scheme includes multiple groups report amount --- quotation pair, if declaring scheme SchemeiOffered by m group --- report
Amount is to (Pij,Qij) composition, it is expressed as:Schemei={ (Pi1,Qi1),(Pi2,Qi2),…,(Pij,Qij),…,(Pim,Qim),
Middle quotation is PijReport amount be Qij;Declare scheme SchemeiCorresponding predict settles accounts fruit ResultiBy n group clear valence out ---
Clear amount is to (P outik,Qik) composition, it can be expressed as:Resulti={ (Pi1,Qi1),(Pi2,Qi2),…,(Pik,Qik),…,
(Pin,Qin), wherein clear valence is P outikThe clear amount that goes out be Qik;
Declare scheme SchemeiPrediction income PRiIt is calculated using the following equation:
Wherein, clear electricity price P is predictedikUnder the clear amount that predicts be Qik,It is clear total to declare predicting for scheme i
Amount, Cost (Q) are known cost of electricity-generating function, and Subsidy (Q) is that function is subsidized in known power generation.
Preferably, the risk factor is specifically calculated using the following equation:
Declare scheme SchemeiRisk factor RiskiFor:
Riski=wROH·ROH+wROC·ROC+wROA·ROA
Wherein, QihTo declare scheme SchemeiEach report amount --- centering is highest declares magnitude, Q for quotationaboveFor Shen
Report scheme SchemeiIn quotation be higher than in one month and average out the report amount summation of clear valence,To declare scheme SchemeiIn
The amount of declaring summation,To declare scheme SchemeiIt is corresponding to predict clear amount summation, wROH,wROC,wROAIt is preset
Weighted value;
Preferably, the appraisal procedure is:According to the prediction income and risk factor for each declaring scheme to each Shen
The marking of report scheme, and the scheme of final choice highest scoring declares scheme as the optimal of the period;
Declare the score Grade of scheme iiIt is calculated using the following equation:
Gradei=wPR·PRi-wRisk·Riski
Wherein, PRiFor the prediction income for declaring scheme i, RiskiFor the risk factor for declaring scheme i, wPRFor preset receipts
Beneficial weight, wRiskFor preset Risk rated ratio.
Power spot market neural network based proposed by the present invention assists method of commerce, can provide for electricity power enterprise
The decision support service that power spot market is bidded improves the income that electricity power enterprise participates in electric power spot exchange, improves power generation enterprise
Industry participates in the enthusiasm of power spot market competition, is conducive to the construction and development of China's power spot market.
Detailed description of the invention
Fig. 1 is the flow chart of power spot market neural network based auxiliary method of commerce in the present invention.
Fig. 2 be in the single period of certain province each power plant voluntarily declare declare scheme and out clear result schematic diagram.
Fig. 3 be single period for being filtered out in the embodiment of the present invention it is optimal declare scheme and out clear result schematic diagram.
Specific embodiment
Specific embodiments of the present invention are as follows:
Using the rich new energy of the more province's pilots in currently China, transprovincially area spot market illustrates tool of the invention as background
Body embodiment.Transprovincially new energy spot market in area's carries out to concentrate and bid, and is classified out clear mechanism of exchange;And using consideration channel peace
The clear system of bidding out of staff cultivation.In the single period, each sending end province is reported with the both parties of finishing touch conclusion of the business electricity
The average value of valence as system protection card, the sending end province the period whole conclusion of the business electricity according to system protection card
Clearing.
A kind of power spot market neural network based auxiliary method of commerce includes the following steps:
Step 1, history declaration data and history to the rich new energy spot market in some province, which go out clear data, to carry out
Pretreatment arranges the data file for generating reference format;It is declared using the history of reference format and clear data training convolutional is refreshing out
Through network model, the amount of declaring valence in the single period and the out relationship between clear amount valence are simulated.
Step 2 declares the same day in power spot market, and each cooperation power plant inside the province is pre- in each period on the same day
It measures power and subtracts the Foundation Planning electricity of each period and obtain each cooperation power plant and declare electricity in each period;
Step 3 declares electricity based on each cooperation power plant inside the province within the single period, enumerates each cooperation power generation
The selectable report amount of factory --- quotation pair, and it is combined into multiple entirety sides of declaring comprising all cooperation power plants inside the province
Case;Each declaring includes multiple groups report amount-quotation pair in scheme;
Each of the single period scheme of declaring is sequentially input neural network model, utilizes neural network model by step 4
It simulates clearly, the corresponding clear valence out of scheme and clear amount out are each declared in prediction;After deducting cost of electricity-generating, calculates and each declare scheme
Prediction income;Risk assessment is carried out to the different schemes of declaring of single period, calculates the risk factor for each declaring scheme;
Step 5 filters out the single period most by preset appraisal procedure in conjunction with prediction income and risk evaluation result
Excellent declares scheme;
Step 6, by obtained each period it is optimal declare the report amount that each cooperation power plant should select in scheme ---
The information of quotation pair is sent to each power plant, instructs each power plant to complete power spot market and declares process.
What each power plant was voluntarily declared in the single period of certain province declares scheme and goes out to settle accounts fruit as shown in Fig. 2;
The single period filtered out in the present embodiment is optimal to declare scheme and goes out that settle accounts fruit as shown in Fig. 3.Compare two kinds of sides of declaring
Case and go out clear as a result, the Shen that will voluntarily be declared than each power plant through the prediction income for declaring scheme that the present embodiment filters out
The actual gain of report scheme is higher by about 15%, and economic benefit is more considerable.
Power spot market neural network based proposed by the present invention assists method of commerce, can provide for electricity power enterprise
The decision support service that power spot market is bidded improves the income that electricity power enterprise participates in electric power spot exchange, improves power generation enterprise
Industry participates in the enthusiasm of power spot market competition, is conducive to the construction and development of China's power spot market.
Embodiment described above is a kind of embodiment of the invention, not makees limit in any form to the present invention
System, there are also other variants and remodeling on the premise of not exceeding the technical scheme recorded in the claims.
Claims (6)
1. a kind of power spot market neural network based assists method of commerce, it is characterised in that include the following steps:
Step 1 goes out clear data to power spot market history declaration data and history and pre-processes, and arranges and generates reticle
The data file of formula;It is declared using the history of reference format and clear data trains neural network model out, simulate the single period
Relationship between the amount of declaring valence and out clear amount valence;
Step 2 declares the same day in power spot market, and the prediction power output by each cooperation power plant in each period on the same day subtracts
It goes the Foundation Planning electricity of each period to obtain each cooperation power plant and declares electricity in each period;
Step 3 declares electricity based on each cooperation power plant, it is selectable to enumerate each cooperation power plant within the single period
Report amount --- quotation pair, and be combined into multiple entirety comprising all cooperation power plants and declare scheme;Each declare scheme
In include multiple groups report amount-quotation pair;
Each of the single period scheme of declaring is sequentially input neural network model, is simulated using neural network model by step 4
Clear out, prediction each declares the corresponding clear valence out of scheme and goes out clear amount;After deducting cost of electricity-generating, calculates and each declare the pre- of scheme
Survey income;Risk assessment is carried out to the different schemes of declaring of single period, calculates the risk factor for each declaring scheme;
It is optimal to filter out the single period by preset appraisal procedure in conjunction with prediction income and risk evaluation result for step 5
Declare scheme;
Step 6, by obtained each period it is optimal declare the report amount that each cooperation power plant should select in scheme --- quotation
Pair information be sent to each power plant, instruct each power plant to complete power spot market and declare process.
2. a kind of power spot market neural network based according to claim 1 assists method of commerce, feature exists
In:The history declaration data includes:Declare the declared value for declaring electricity and each station of period, each station;The history
Clear data include out:Out the clear period, each station go out clear electricity and each station cleaing price.
3. a kind of power spot market neural network based according to claim 1 assists method of commerce, feature exists
In:The neural network model is:BP neural network, convolutional neural networks or Recognition with Recurrent Neural Network.
4. a kind of power spot market neural network based according to claim 1 assists method of commerce, feature exists
In:The prediction income is specifically calculated using the following equation:
Each declaring scheme includes multiple groups report amount --- quotation pair, if declaring scheme SchemeiOffered by m group --- report amount pair
(Pij,Qij) composition, it is expressed as:Schemei={ (Pi1,Qi1),(Pi2,Qi2),…,(Pij,Qij),…,(Pim,Qim), wherein reporting
Valence is PijReport amount be Qij;Declare scheme SchemeiCorresponding predict settles accounts fruit ResultiBy n group clear valence out --- go out clear
Amount is to (Pik,Qik) composition, it can be expressed as:Resulti={ (Pi1,Qi1),(Pi2,Qi2),…,(Pik,Qik),…,(Pin,
Qin), wherein clear valence is P outikThe clear amount that goes out be Qik;
Declare scheme SchemeiPrediction income PRiIt is calculated using the following equation:
Wherein, clear electricity price P is predictedikUnder the clear amount that predicts be Qik,Clear total amount, Cost are predicted for declare scheme i
It (Q) is known cost of electricity-generating function, Subsidy (Q) is that function is subsidized in known power generation.
5. a kind of power spot market neural network based according to claim 1 assists method of commerce, feature exists
In:The risk factor is specifically calculated using the following equation:
Declare scheme SchemeiRisk factor RiskiFor:
Riski=wROH·ROH+wROC·ROC+wROA·ROA
Wherein, QihTo declare scheme SchemeiEach report amount --- centering is highest declares magnitude, Q for quotationaboveFor the side of declaring
Case SchemeiIn quotation be higher than in one month and average out the report amount summation of clear valence,To declare scheme SchemeiIn Shen
Report amount summation,To declare scheme SchemeiIt is corresponding to predict clear amount summation, wROH,wROC,wROAIt is preset weight
Value.
6. a kind of power spot market neural network based according to claim 1 assists method of commerce, feature exists
It is in the preset appraisal procedure:Foundation each declares the prediction income of scheme and risk factor beats each scheme of declaring
Point, and the scheme of final choice highest scoring declares scheme as the optimal of the period;
Declare the score Grade of scheme iiIt is calculated using the following equation:
Gradei=wPR·PRi-wRisk·Riski
Wherein, PRiFor the prediction income for declaring scheme i, RiskiFor the risk factor for declaring scheme i, wPRFor preset usufruct
Weight, wRiskFor preset Risk rated ratio.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810638002.1A CN108921601A (en) | 2018-06-20 | 2018-06-20 | A kind of power spot market auxiliary method of commerce neural network based |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810638002.1A CN108921601A (en) | 2018-06-20 | 2018-06-20 | A kind of power spot market auxiliary method of commerce neural network based |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108921601A true CN108921601A (en) | 2018-11-30 |
Family
ID=64421507
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810638002.1A Pending CN108921601A (en) | 2018-06-20 | 2018-06-20 | A kind of power spot market auxiliary method of commerce neural network based |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108921601A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109858783A (en) * | 2019-01-16 | 2019-06-07 | 国能日新科技股份有限公司 | Wind power plant electricity transaction auxiliary decision-making support system and aid decision support method |
CN109858712A (en) * | 2019-03-11 | 2019-06-07 | 北京天润新能投资有限公司西北分公司 | The transregional automated transaction of the stock a few days ago strategy of one kind and economic evaluation method |
CN110991731A (en) * | 2019-11-28 | 2020-04-10 | 中国南方电网有限责任公司 | Electric power real-time market constraint self-identification clearing method and system based on deep learning |
CN110991741A (en) * | 2019-12-02 | 2020-04-10 | 中国南方电网有限责任公司 | Section constraint probability early warning method and system based on deep learning |
CN111598719A (en) * | 2020-04-09 | 2020-08-28 | 云南电网有限责任公司 | New energy seller transaction method and system for spot power market |
CN111612419A (en) * | 2020-05-18 | 2020-09-01 | 中国南方电网有限责任公司 | Method and device for processing power declaration data and computer equipment |
CN111784203A (en) * | 2020-07-28 | 2020-10-16 | 南方电网能源发展研究院有限责任公司 | Electric power spot market risk simulation analysis method suitable for generator set participation |
CN111951121A (en) * | 2020-07-20 | 2020-11-17 | 广东电力交易中心有限责任公司 | Electric power spot market quotation mode classification method, device and storage medium |
CN111985767A (en) * | 2020-07-06 | 2020-11-24 | 广州汇电云联互联网科技有限公司 | Quotation dividing method, device, equipment and medium for electric power spot market |
-
2018
- 2018-06-20 CN CN201810638002.1A patent/CN108921601A/en active Pending
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109858783A (en) * | 2019-01-16 | 2019-06-07 | 国能日新科技股份有限公司 | Wind power plant electricity transaction auxiliary decision-making support system and aid decision support method |
CN109858783B (en) * | 2019-01-16 | 2021-04-09 | 国能日新科技股份有限公司 | Wind power plant electric power transaction assistant decision support system and assistant decision support method |
CN109858712A (en) * | 2019-03-11 | 2019-06-07 | 北京天润新能投资有限公司西北分公司 | The transregional automated transaction of the stock a few days ago strategy of one kind and economic evaluation method |
CN110991731A (en) * | 2019-11-28 | 2020-04-10 | 中国南方电网有限责任公司 | Electric power real-time market constraint self-identification clearing method and system based on deep learning |
CN110991741A (en) * | 2019-12-02 | 2020-04-10 | 中国南方电网有限责任公司 | Section constraint probability early warning method and system based on deep learning |
CN110991741B (en) * | 2019-12-02 | 2022-07-12 | 中国南方电网有限责任公司 | Section constraint probability early warning method and system based on deep learning |
CN111598719A (en) * | 2020-04-09 | 2020-08-28 | 云南电网有限责任公司 | New energy seller transaction method and system for spot power market |
CN111612419A (en) * | 2020-05-18 | 2020-09-01 | 中国南方电网有限责任公司 | Method and device for processing power declaration data and computer equipment |
CN111985767A (en) * | 2020-07-06 | 2020-11-24 | 广州汇电云联互联网科技有限公司 | Quotation dividing method, device, equipment and medium for electric power spot market |
CN111951121A (en) * | 2020-07-20 | 2020-11-17 | 广东电力交易中心有限责任公司 | Electric power spot market quotation mode classification method, device and storage medium |
CN111784203A (en) * | 2020-07-28 | 2020-10-16 | 南方电网能源发展研究院有限责任公司 | Electric power spot market risk simulation analysis method suitable for generator set participation |
CN111784203B (en) * | 2020-07-28 | 2021-03-16 | 南方电网能源发展研究院有限责任公司 | Electric power spot market risk simulation analysis method suitable for generator set participation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108921601A (en) | A kind of power spot market auxiliary method of commerce neural network based | |
Lee | Cost-benefit analysis, LCOE and evaluation of financial feasibility of full commercialization of biohydrogen | |
CN105844367A (en) | Sensitivity factor based calculating method for power grid node marginal pricing | |
CN104851023A (en) | Real-time bidding online feedback control method and system | |
Wang et al. | Performance based regulation of the electricity supply industry in Hong Kong: An empirical efficiency analysis approach | |
CN113344467A (en) | Method and device for predicting capital of electric power engineering | |
CN109272419A (en) | A kind of power distribution network formula investing methods of comparison and selection based on optimal solution | |
Gladysz et al. | A framework for strategic assessment of far-reaching technologies: A case study of Combined Heat and Power technology | |
CN114862457A (en) | Bidding electric quantity boundary determination method for step hydropower station group participating in spot market before day | |
Richardson et al. | Economic viability of a reverse engineered algae farm (REAF) | |
CN105260944A (en) | Method for calculating statistical line loss based on LSSVM (Least Square Support Vector Machine) algorithm and association rule mining | |
CN107578130A (en) | A kind of method of the copper forecasting of futures prix of the TSK fuzzy systems of structure and parameter combination learning | |
CN109523309B (en) | Power quotation simulation method and system based on load flow analysis and calculation | |
Smetters et al. | Opting out of social security | |
CN106228279A (en) | The electricity price optimized calculation method of electricity market Generation Side based on Protect advantage model | |
Sánchez et al. | A multidisciplinary approach to model long-term investments in electricity generation: Combining system dynamics, credit risk theory and game theory | |
Zhang et al. | Day-ahead electricity price forecasting using artificial intelligence | |
CN105808960A (en) | Grounding grid erosion rate prediction method based on grey neural network combination model | |
CN111754076A (en) | Method and equipment suitable for electric power wholesale market mode evaluation | |
Tang et al. | Renewable energy investment in emerging markets: evaluating improvements to the clean development mechanism | |
Ji et al. | Application of Set-Valued Statistical Methods for Excellent Performance Evaluation | |
Li et al. | SD-based research on industrialized construction supply chain | |
CN111899122B (en) | User decentralized clearing method based on energy storage control | |
CN109190858A (en) | A kind of power network construction project investment policy making period method | |
CN107958342A (en) | A kind of the production and marketing competitiveness evaluation method and system of microgrid type electricity transaction business |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181130 |