CN115496603A - Artificial intelligence technology-based new energy day-ahead transaction decision method for power market - Google Patents
Artificial intelligence technology-based new energy day-ahead transaction decision method for power market Download PDFInfo
- Publication number
- CN115496603A CN115496603A CN202211202436.XA CN202211202436A CN115496603A CN 115496603 A CN115496603 A CN 115496603A CN 202211202436 A CN202211202436 A CN 202211202436A CN 115496603 A CN115496603 A CN 115496603A
- Authority
- CN
- China
- Prior art keywords
- time
- power
- data
- day
- new energy
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 238000005516 engineering process Methods 0.000 title claims abstract description 23
- 230000005611 electricity Effects 0.000 claims abstract description 66
- 230000007774 longterm Effects 0.000 claims abstract description 14
- 238000011084 recovery Methods 0.000 claims description 47
- 230000006870 function Effects 0.000 claims description 25
- 238000010248 power generation Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 230000004931 aggregating effect Effects 0.000 claims description 2
- 230000005684 electric field Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011664 nicotinic acid Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012896 Statistical algorithm Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q30/0283—Price estimation or determination
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Technology Law (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a new energy day-ahead trading decision method for an electric power market based on an artificial intelligence technology, and relates to the technical field of electric field electric power trading auxiliary decision, wherein the method comprises the following steps: acquiring data to be processed, wherein the data to be processed comprises historical data, contract data and market environment information, and the historical data comprises comprehensive historical trading price data; predicting the new energy trading price of the electric power market based on historical data to obtain predicted data; and constructing a future declaration objective function and constraint conditions, and solving based on the constraint conditions by taking the objective function as a solving target according to the prediction data, the contract data and the market environment information to obtain an optimal future declaration scheme. By adopting the scheme, the factors such as market rule information, medium and long-term transaction information, electricity price prediction information, power prediction information and the like are comprehensively considered, dynamic balance is performed between income and risk, the problem declared in the future is quantitatively processed, and the objectivity is higher.
Description
Technical Field
The application relates to the technical field of electric field electric power transaction auxiliary decision-making, in particular to a method and a device for electric power market new energy day-ahead transaction decision-making based on an artificial intelligence technology.
Background
Under the scene of the electric power spot market, new energy power generation enterprises participate in electric power spot trade and need to make future declaration according to the requirements of current market rules. The future declaration scenario is a 96-point power curve. Therefore, how to make a reasonable and effective day-ahead declaration scheme and realize the maximization of the income is a core problem which needs to be solved urgently.
At present, most new energy power generation enterprises have three main day-ahead declaration modes: the first is to directly use the original power prediction data of the wind power prediction system as a market declaration scheme; secondly, the original power prediction data is adjusted in a manual mode to form a market declaration scheme; and thirdly, generating a market declaration scheme by means of a software system. However, the first method completely depends on the original power prediction data, does not comprehensively consider various factors such as medium and long term contract conditions, market supply and demand conditions, market assessment rules and the like, and has the advantages that the power prediction result generally has large deviation, and assessment cost is generated in settlement generally. In the second mode, although the original power prediction data is adjusted to some extent, the adjustment operation depends excessively on the capability and experience of individuals, there is no explicit intermediate process of quantitative processing, some factors in the actually generated market declaration scheme have artificial randomness, and the working efficiency is low. The third mode is based on informatization means, but usually based on historical transaction data, a statistical analysis method is adopted for carrying out price trend analysis, error analysis is carried out on short-term power prediction data and actual power data, and an error result is used as a basis for short-term power adjustment to generate a market declaration scheme.
Disclosure of Invention
The present application is directed to solving, at least in part, one of the technical problems in the related art.
Therefore, the first purpose of the application is to provide a new energy day-ahead trading decision method for the power market based on the artificial intelligence technology, so that the technical problems that the existing method is incomplete in consideration factors, and lacks deep analysis and mining of full data, so that the generated market declaration scheme is insufficient in comprehensiveness, loss is difficult to be reduced to the maximum extent, and income is difficult to be increased are solved, the factors such as market rule information, medium-and-long-term trading information, electricity price prediction information, power prediction information and the like are comprehensively considered, dynamic balance is performed between income and risk, the day-ahead declaration problem is subjected to quantitative processing, the objectivity is higher, and the consideration factors are more comprehensive.
The second purpose of the application is to provide an electric power market new energy day-ahead transaction assistant decision-making system based on an artificial intelligence technology.
A third object of the present application is to propose a computer device.
In order to achieve the above object, an embodiment of the first aspect of the present application provides a new energy day-ahead transaction decision method for an electric power market based on an artificial intelligence technology, including: acquiring data to be processed, wherein the data to be processed comprises historical data, contract data and market environment information, and the historical data comprises comprehensive historical trading price data; predicting the new energy trading price of the power market based on historical data to obtain predicted data; and constructing a day-ahead declaration objective function and constraint conditions, and solving based on the constraint conditions by taking the objective function as a solving target according to the prediction data, contract data and market environment information to obtain an optimal day-ahead declaration scheme.
According to the method for deciding the day-ahead transaction of the new energy of the electric power market based on the artificial intelligence technology, the medium-long term transaction and the day-ahead transaction are organically combined, the cost generated by the excessive profit recovery loss and the two fine losses of the market assessment loss is also used as a factor influencing the profit, the factors such as market rule information, medium-long term transaction information, electricity price prediction information, power prediction information and the like are comprehensively considered, dynamic balance is carried out between the profit and the risk, the day-ahead declaration problem is quantitatively processed, a day-ahead declaration auxiliary decision model is constructed, and a day-ahead declaration scheme is formed.
Optionally, in an embodiment of the present application, the market environment information includes market rules (such as deviation proportionality coefficients allowed by a market), station information (such as installed capacity of a wind farm, short-term power data), and the like, the historical data further includes a system load rate curve, and the new energy trading price of the electric power market is predicted based on the historical data to obtain predicted data, including:
by integrating historical price data and system load rate curve related data, constructing a characteristic project, extracting key characteristics, predicting the current and real-time prices for multiple days in the future by using a convolutional neural network algorithm, a bionic optimization algorithm and a typical curve statistical algorithm, and performing rolling prediction on the real-time prices by using an artificial intelligent autonomous learning mode and a deviation processing algorithm; acquiring needed forecast data including day-ahead price forecast and real-time price forecast,
after acquiring the data to be processed, the method further comprises the following steps:
the classification and aggregation processing are performed on the held contract data such as medium and long-term contracts, time-sharing contracts, and base contracts.
Optionally, in one embodiment of the present application, the objective function includes settlement revenue, two fine check losses, excess profit recovery losses, wherein,
an objective function, expressed as:
J=max(J jiesuan -J chaoe -J xize )
wherein, J jiesuan Shows settlement income, J chaoe Represents excess profit recovery loss, J xize Two detailed examination losses are shown,
the settlement revenue, expressed as:
J_jiesuan t =P_zhong t ×Q_zhong t +(Q_riqian t -Q_zhong t )×P_riqian t +(Q_shishi t -Q_riqian t )×P_shishi t
wherein, J jiesuan Denotes settlement income, J-jiesuan t Representing spot-clearing income at time t, P-zhong t Representing a point of sale held mid-to-long-term weighted electricity price at time t, Q-zhong t Indicating the current good-hold medium and long term electricity quantity at time t, Q-riqian t Indicating the quantity of current day-ahead electricity at time t, P-riqian t Indicating the spot-stock day-ahead electricity price at time t, Q-shishi t Representing the real-time electric quantity of the spot goods at time t, P-shishi t Represents the spot real-time electricity price at time T, T represents the total number of times of the day-ahead declared power curve, T represents the tth time, T =1, 2.. T,
two rules assess the loss, expressed as:
J xize =J ae +J duanqi
wherein, J ae Representing the maximum absolute error assessment of the wind field, J duanqi The examination expense of the medium and short term in the next day is shown,
excess profit recovery loss, expressed as:
wherein, J 11,t Represents the bias recovery loss, J 12,t And the deviation recovery loss is represented by the deviation recovery loss of the real power generation amount at the time t, which is higher than the allowable deviation upper limit of the power generation amount before the current date.
Optionally, in an embodiment of the present application, the constraint condition includes two fine rule assessment loss constraints, a power proportion constraint, an excess profit recovery loss constraint, a settlement revenue constraint, and a reporting power constraint.
Optionally, in an embodiment of the present application, the two fine-rule assessment loss constraints include a medium-short term wind power forecast assessment, a late peak and valley period wind power maximum absolute value error rate assessment, wherein,
when the prediction accuracy of the medium-short term power of the new energy is lower than a threshold value, generating medium-short term power prediction deviation assessment, wherein the medium-short term power prediction accuracy and the next day medium-short term assessment cost are respectively expressed as:
J duanqi =(85%-Acc day-ahead )×P w ×0.4×P-biaogan
wherein Acc day-ahead The prediction accuracy of the medium-short term power of the new energy is shown, T is the prediction point number examined on the day, P i Representing the actual power of the new energy power station at the moment i, P i ' represents the predicted power of the new energy power station at the moment i, cap is the maximum starting capacity of the new energy power station on the examination day, J duanqi Showing the next day's short and medium examination cost, P w Represents the installed capacity, P, of the new energy power station biaogan The electricity price of the post is shown,
when the maximum absolute value error rate of the wind power at the late peak and the low valley time period is greater than a preset threshold value, the maximum absolute value error rate of the wind power field is examined, and the maximum absolute value error rate is expressed as:
J ae =(AE-15%)×P w ×P_biaogan
wherein AE represents the maximum absolute error rate, P pi Representing predicted power, P, of the new energy power station at time i i Representing available power, P, of the new energy plant at time i Mi Representing the available generated power at time i of the limited period, i representing time, m representing the number of segments of the late peak and valley periods, J ae Represents the maximum absolute error assessment of the wind field, P w Represents the installed capacity, P, of the new energy power station biaogan The electricity price of the post is shown,
optionally, in an embodiment of the present application, the electric quantity proportion constraint is expressed as:
Q_jishu t =k t Q_riqian t
wherein, Q _ jishu t Indicating the base number of electricity at time t, Q-riqian t Indicating the quantity of electricity before the current day at time t, k 1 The ratio of the base number electric quantity at the time t to the reported electric quantity before the day is represented,
the excess profit recovery loss constraint is expressed as:
if the actual power generation amount is lower than the allowable deviation lower limit of the power amount before the spot date, the deviation recovery loss is expressed as:
J 11,t =max(Q_riqian t -(1+λ)×Q_shishi t ,0)×max(Pzr t -P_shishi t ,0)
wherein Q _ riqian t Represents the quantity of electricity before the current date of stock at time t, lambda represents the excess profit recovery ratio, pzr t The price of the electric power of the mark post at the time t andweighted electricity prices of day-ahead electricity prices, Q _ shishi t Represents the real-time electric quantity of the spot goods at the moment t, P _ shishi t Represents the spot real-time electricity rate at time t,
if the actual power generation amount is lower than the allowable deviation lower limit of the power amount before the spot date, the deviation recovery loss is expressed as:
J 11,t =max(Q_riqian t -(1+λ)×Q_shishi t ,0)×max(Pzr t -P_shishi t ,0)
wherein Q _ riqian t Represents the quantity of electricity before the current date of stock at time t, lambda represents the excess profit recovery ratio, pzr t Weighted electricity prices Q _ shishi, representing the post electricity prices and day-ahead electricity prices at time t t Represents the real-time electric quantity of the spot goods at the time t, P _ shishi t And the spot real-time electricity price at the time t is shown.
Optionally, in one embodiment of the present application, the settlement revenue constraint is expressed as:
J chaoe,h =min(J 11,h +J 12,h ,J jiesuan,h )
wherein, J jiesuan,h Denotes the spot settlement income at h, Q zhong,4h+i Represents the medium-and long-term electric quantity at h-hour i, P zhong,4h+i Represents the medium-and long-term weighted electric quantity at h-hour i, Q riqian,4h+i Real-time electric quantity of stock in h hour i moment, P riqian,4h+i Indicating spot-time day-ahead electricity price at h hour i, Q shishi,4h+i Real-time electric quantity of stock in h hour i hour, P shishi,4h+i Representing the spot real-time electricity price at h hour i time, J chaoe,h Represents the excess profit recovery loss at h, J 11,h Represents a deviation recovery loss in which the amount of generated electric power at h is lower than the lower limit of the deviation allowable for the electric power before the actual date, J 22,h Represents a deviation recovery loss in which the h-time power generation amount is higher than the allowable deviation upper limit of the actual-date power amount,
the declared power constraint is expressed as:
Q_riqian t ≤P w ×Δt
wherein Q _ riqian t Indicating the quantity of electricity in the spot at time t, P w The installed capacity of the new energy power station is shown, and delta t represents a time interval.
Optionally, in an embodiment of the present application, according to the prediction data, the contract data, and the market environment information, solving based on a constraint condition with an objective function as a solving objective, to obtain an optimal daily declaration scheme, includes:
according to medium-long term contract historical data, market disclosure data, power prediction data and prediction data contained in contract data, an objective function is taken as a solving target, a constructed constraint condition is taken as a limit, and an ant colony algorithm is adopted for solving to obtain an optimal future declaration scheme.
In order to achieve the above object, a second aspect of the present invention provides an electric power market new energy day-ahead transaction assistant decision-making system based on artificial intelligence technology, including an obtaining module, a predicting module, and a scheme generating module, wherein,
the acquisition module is used for acquiring data to be processed, wherein the data to be processed comprises historical data, contract data and market environment information, and the historical data comprises comprehensive historical trading price data;
the forecasting module is used for forecasting the new energy trading price of the electric power market based on historical data to obtain forecasting data;
and the scheme generation module is used for solving by taking the objective function as a solving target and based on constraint conditions according to the market environment information, the processed contract data and the prediction data to obtain an optimal daily declaration scheme.
To achieve the above object, a third embodiment of the present invention provides a computer device, including: a processor; a memory for storing the processor-executable instructions; when the processor executes the executable instructions stored in the memory, the method for making the decision on the day-ahead trading of the new energy in the electric power market based on the artificial intelligence technology is realized.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a method for making a decision on a new energy day-ahead transaction in an electric power market based on an artificial intelligence technology according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a power market new energy day-ahead transaction decision system based on an artificial intelligence technology according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present application and should not be construed as limiting the present application.
The method and the device for making a decision on the day-ahead transaction of the new energy in the electric power market based on the artificial intelligence technology are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a new energy day-ahead transaction decision-making method for an electric power market based on an artificial intelligence technology according to an embodiment of the present application.
As shown in fig. 1, the artificial intelligence technology-based electric power market new energy day-ahead transaction decision-making method includes the following steps:
step 101, acquiring data to be processed, wherein the data to be processed comprises historical data, contract data and market environment information, and the historical data comprises comprehensive historical trading price data;
and 103, constructing a day-ahead declaration objective function and constraint conditions, and solving by taking the objective function as a solving target and based on the constraint conditions according to the prediction data, contract data and market environment information to obtain an optimal day-ahead declaration scheme.
According to the method for deciding the day-ahead transaction of the new energy of the electric power market based on the artificial intelligence technology, the medium-long term transaction and the day-ahead transaction are organically combined, the cost generated by the excessive profit recovery loss and the two fine losses of the market assessment loss is also used as a factor influencing the profit, the factors such as market rule information, medium-long term transaction information, electricity price prediction information, power prediction information and the like are comprehensively considered, dynamic balance is carried out between the profit and the risk, the day-ahead declaration problem is quantitatively processed, a day-ahead declaration auxiliary decision model is constructed, and a day-ahead declaration scheme is formed.
Optionally, in an embodiment of the present application, the historical data further includes a system load rate curve, and the predicting the new energy trading price of the power market based on the historical data to obtain predicted data includes:
constructing a characteristic project based on comprehensive historical transaction price data and a system load rate curve, and extracting key characteristics;
predicting the day-ahead price and the real-time price in a preset time period based on the key characteristics to obtain prediction data,
after acquiring the data to be processed, the method further comprises the following steps:
and classifying and aggregating the contract data to obtain the processed contract data.
Optionally, in one embodiment of the present application, the objective function includes settlement revenue, two fine check losses, excess profit recovery losses, wherein,
an objective function, expressed as:
J=max(J jiesuan -J chaoe -J xize )
wherein, J jiesuan Shows settlement income, J chaoe Represents excess profit recovery loss, J xize Represents two rules of detailThe loss of the nucleus is reduced by the loss of the nucleus,
settlement revenue, expressed as:
J_jiesuan t =P_zhong t ×Q_zhong t +(Q_riqian t -Q_zhong t )×P_riqian t +(Q_shishi t -Q_riqian t )×P_shishi t
wherein, J jiesuan Represents settlement income, J _ jiesuan t Indicating spot settlement revenue at time t, P _ zhong t Represents the spot-held medium-and long-term weighted electricity rate at time t, Q _ zhong t Indicating that the current good at time t has a medium or long term charge, Q _ riqian t Indicating the quantity of current-in-stock-day-ahead electricity at time t, P _ riqian t Indicating the spot-stock day-ahead electricity price at time t, Q _ shishi t Represents the real-time electric quantity of the spot goods at the time t, P _ shishi t Represents the spot real-time electricity price at time T, T represents the total number of times of the day-ahead declared power curve, T represents the tth time, T =1, 2.. T,
two fine rules assess the loss, expressed as:
J xize =J ae +J duanqi
wherein, J ae Representing the maximum absolute error assessment of the wind field, J duanqi The short-term assessment cost in the next day is shown,
excess profit recovery loss, expressed as:
wherein, J 11,t Represents the bias recovery loss, J 12,t And the deviation recovery loss is represented by the deviation recovery loss of the real power generation amount at the time t, which is higher than the allowable deviation upper limit of the power generation amount before the current date.
Optionally, in an embodiment of the present application, the constraint condition includes two rules assessment loss constraints, a power proportion constraint, an excess profit recovery loss constraint, a settlement income constraint, and a declared power constraint.
Optionally, in an embodiment of the present application, two fine-rule assessment loss constraints are mainly applied to wind power prediction mixture, mainly a deviation (or Accuracy, ACC) assessment for a whole day and an absolute error assessment for a peak and valley time in a day, which are as follows:
(1) Medium and short term wind power prediction and assessment
When the power of new energy (wind field) in the middle and short term predicts the accuracy Acc day-ahead <When 85 percent of the total power is calculated, a medium-short term power forecast deviation assessment (short term wind power forecast deviation loss) J is generated duanqi Wherein, the accuracy rate of the medium-short term power prediction is calculated according to the following formula:
next day short and medium term assessment cost J duanqi =(85%-Acc day-ahead )×P w ×0.4×P-biaogan,
Wherein Acc day-ahead The prediction accuracy of the power of the new energy in the medium and short term is shown, T is the number of prediction points examined on the day, P i Representing the actual power (unit: MW) of the new energy power station at the moment i, P i ' represents the predicted power (unit: MW) of the new energy power station at the moment i, cap is the maximum starting capacity (unit: MW) of the new energy power station on the assessment day, J duanqi Representing the next day's short and medium term assessment costs, P w Represents the installed capacity (unit: MW) of the new energy power station, P biaogan The power price of the post is shown,
(2) Wind power maximum absolute value error rate examination in late peak and low valley periods
Maximum absolute value error rate AE when wind power is in late peak and valley periods>At 15%, the maximum absolute error assessment (AE absolute error assessment loss) J of the wind field is generated ae Defined as one of the optimization objectives. The valley period is 22; 11; the peak time period is 17.
The maximum absolute error rate is calculated as follows:
J ae =(AE-15%)×P w ×P_biaogan
wherein AE represents the maximum absolute error rate, P pi Represents the predicted power, P, of the new energy power station at the moment i i Representing available power, P, of the new energy plant at time i Mi Representing the available generated power at time i of the limited period, i representing time, m representing the number of segments of the late peak and valley periods, J ae Represents the maximum absolute error assessment of the wind field, P w Represents the installed capacity, P, of the new energy power station biaogan The electricity price of the post is shown,
optionally, in an embodiment of the present application, the electric quantity proportional constraint, that is, the proportional constraint between Q _ jishu and Q _ riqian, is specifically:
aiming at each time t, the base number electric quantity and the day-ahead declared electric quantity need to meet a certain proportion k 1 I.e. the constraint is:
Q_jishu t =k t Q_riqian t
wherein, Q _ jishu t Base number of electric quantities, Q _ riqian, representing time t t Indicating the quantity of electricity before the current day at time t, k 1 The ratio of the base number electric quantity at the time t to the reported electric quantity before the day is represented,
the excess profit recovery loss constraint is expressed as:
if Q _ riqian t >(1+λ)×Q_shishi t I.e. the real power generation amount Q _ shishi t Lower than the amount of the daily output power Q _ riqian t The lower deviation limit allowed, the deviation recovery loss is:
J 11,t =max(Q_riqian t -(1+λ)×Q_shishi t ,0)×max(Pzr t -P_shishi t ,0)
wherein Q _ riqian t Represents the quantity of electricity before the current date of stock at time t, lambda represents the excess profit recovery ratio, pzr t Weighted electricity prices, Q _ shishi, representing the benchmarking electricity prices at time t and the day-ahead electricity prices t Represents the real-time electric quantity of the spot goods at the time t, P _ shishi t Represents the spot real-time electricity rate at time t,
if Q _ riqian t <(1-λ)×Q_shishi t I.e. the real power generation amount Q _ shishi t Higher than the day-ahead clear electricity Q _ riqian t The upper deviation limit allowed, the deviation recovery loss is:
J 11,t =max(Q_riqian t -(1+λ)×Q_shishi t ,0)×max(Pzr t -P_shishi t ,0)
wherein Q _ riqian t Represents the quantity of electricity before the current date of stock at time t, lambda represents the excess profit recovery ratio, pzr t Weighted electricity prices, Q _ shishi, representing the benchmarking electricity prices at time t and the day-ahead electricity prices t Represents the real-time electric quantity of the spot goods at the moment t, P _ shishi t Indicating the spot real-time electricity prices at time t.
Optionally, in an embodiment of the present application, the settlement revenue constraint is that the excess recovery loss per hour is not greater than the settlement revenue, specifically:
for each h hour, the fee deducted cannot be greater than the profit revenue of the station itself, that is:
J chaoe,h =min(J 11,h +J 12,h ,J jiesuan,h )
wherein, J jiesuan,h Denotes the spot settlement income at h, Q zhong,4h+i Represents the medium-and long-term electric quantity at h, i, P zhong,4h+i Represents the medium-and long-term weighted electric quantity at h-hour i, Q riqian,4h+i Indicating the current quantity of electricity at time h and i, P riqian,4h+i Indicating the spot-time day-ahead electricity price at time h, i, Q shishi,4h+i Real-time electric quantity of stock in h hour i hour, P shishi,4h+i Representing the spot real-time electricity price at h hour i time, J chaoe,h Represents the excess profit recovery loss at h, J 11,h Deviation indicating that the amount of generated electricity at h time is lower than the allowable deviation lower limit of the amount of electricity before the actual datePoor recovery loss, J 22,h Represents a deviation recovery loss in which the h-time power generation amount is higher than the allowable deviation upper limit of the actual-date power amount,
the reporting electric quantity constraint is that the reporting electric quantity does not exceed the installed capacity constraint, specifically:
because the power plant can not exceed self power generation capacity in the actual power generation process, the reported electric quantity can not exceed self power generation capacity too much, namely:
Q_riqian t ≤P w ×Δt
wherein, Q _ riqian t Indicating the quantity of electricity in the spot at time t, P w The installed capacity of the new energy power station is shown, and delta t represents a time interval.
Optionally, in an embodiment of the application, after the objective function and the constraint equation are determined, an advanced bionic intelligent optimization algorithm, namely an ant colony optimization algorithm, is adopted according to existing medium-long term contract historical data, market disclosure data, power prediction data of the wind farm, and data such as day-ahead price and real-time price prediction data obtained through a price prediction model, in a day-ahead transaction declaration process of the power market, dynamic balance is performed on declaration risk and revenue, factors to be considered in the day-ahead declaration are used as constraint conditions, and finally an optimal day-ahead declaration scheme is obtained through the ant colony algorithm.
In order to realize the embodiment, the application further provides a power market new energy day-ahead trading decision system based on the artificial intelligence technology.
Fig. 2 is a schematic structural diagram of a new energy day-ahead transaction decision making system of an electric power market based on an artificial intelligence technology according to an embodiment of the present application.
As shown in fig. 2, the system for making a decision on the day-ahead transaction of new energy in the electricity market based on the artificial intelligence technology comprises an acquisition module, a prediction module and a scheme generation module, wherein,
the acquisition module is used for acquiring data to be processed, wherein the data to be processed comprises historical data, contract data and market environment information, and the historical data comprises comprehensive historical trading price data;
the forecasting module is used for forecasting the new energy trading price of the electric power market based on historical data to obtain forecasting data;
and the scheme generation module is used for solving by taking the objective function as a solving target and based on constraint conditions according to the market environment information, the processed contract data and the prediction data to obtain an optimal daily declaration scheme.
It should be noted that the explanation of the embodiment of the artificial intelligence technology-based new energy day-ahead trading decision method for the electric power market is also applicable to the artificial intelligence technology-based new energy day-ahead trading decision system for the electric power market of the embodiment, and details are not repeated here.
In order to implement the foregoing embodiments, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the method described in the foregoing embodiments is implemented.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A day-ahead trading decision method for new energy in an electric power market based on an artificial intelligence technology is characterized by comprising the following steps:
acquiring data to be processed, wherein the data to be processed comprises historical data, contract data and market environment information, and the historical data comprises comprehensive historical trading price data;
predicting the new energy trading price of the power market based on the historical data to obtain predicted data;
and constructing a daily declaration objective function and constraint conditions, and solving based on the constraint conditions by taking the objective function as a solving target according to the prediction data, the contract data and the market environment information to obtain an optimal daily declaration scheme.
2. The method of claim 1, wherein the historical data further comprises a system load rate curve, and wherein predicting new energy trading prices for the electricity market based on the historical data results in predicted data comprising:
constructing a characteristic project based on the comprehensive historical transaction price data and the system load rate curve, and extracting key characteristics;
predicting a day-ahead price and a real-time price within a preset time period based on the key features to obtain the prediction data,
after the data to be processed is obtained, the method further comprises the following steps:
and classifying and aggregating the contract data to obtain processed contract data.
3. The method of claim 1, wherein the objective functions include settlement revenue, fine check loss, excess profit recovery loss, wherein,
the objective function is expressed as:
J=max(J jiesuan -J chaoe -J xize )
wherein, J jiesuan Shows settlement income, J chaoe Represents excess profit recovery loss, J xize The loss of the examination is expressed in terms of fine rules,
the settlement revenue, expressed as:
J_jiesuan t =P_zhong t ×Q_zhong t +(Q_riqian t -Q_zhong t )×P_riqian t +(Q_shishi t -Q_riqian t )×P_shishi t
wherein, J jiesuan Represents settlement income, J _ jiesuan t Indicating the spot settlement income at time t, P _ zhong t Represents the spot-held medium-and long-term weighted electricity rate at time t, Q _ zhong t Indicating that the current good at time t has a medium or long term charge, Q _ riqian t Indicating the quantity of current day power at time t, P _ riqian t Indicating the spot-stock day-ahead electricity price at time t, Q _ shishi t Represents the real-time electric quantity of the spot goods at the time t, P _ shishi t Represents the spot real-time electricity price at time T, T represents the total number of times of the day-ahead declared power curve, T represents the tth time, T =1, 2.. T,
the fine assessment loss is expressed as:
J xize =J ae +J duanqi
wherein, J ae Representing the maximum absolute error assessment of the wind field, J duanqi The short-term assessment cost in the next day is shown,
the excess profit recovery loss is expressed as:
wherein, J 11,t Represents the bias recovery loss, J 12,t And a deviation recovery loss indicating that the actual power generation amount at time t is higher than the allowable deviation upper limit of the power amount before the spot date.
4. The method of claim 1, wherein the constraints include a fine check loss constraint, a power proportion constraint, an excess profit recovery loss constraint, a settlement revenue constraint, and a declared power constraint.
5. The method of claim 4, in which the fine grain assessment loss constraints comprise medium and short term wind power forecast assessment, late peak and valley time period wind maximum absolute value error rate assessment, wherein,
when the prediction accuracy of the new energy medium-short term power is lower than a threshold value, medium-short term power prediction deviation assessment is generated, wherein the medium-short term power prediction accuracy and the next day medium-short term assessment cost are respectively expressed as follows:
wherein, acc day-ahead The prediction accuracy of the medium-short term power of the new energy is shown, T is the prediction point number examined on the day, P i Representing the actual power of the new energy power station at the moment i, P i ' represents the predicted power of the new energy power station at the moment i, cap is the maximum starting capacity of the new energy power station on the examination day, J duanqi Showing the next day's short and medium examination cost, P w Represents the installed capacity, P, of the new energy power station biaogan The power price of the post is shown,
when the maximum absolute error rate of the wind power at late peak and low valley time periods is greater than a preset threshold value, the maximum absolute error rate of the wind power field is checked, and the maximum absolute error rate is expressed as follows:
J ae =(AE-15%)×P w ×P_biaogan
wherein AE represents the maximum absolute error rate, P pi When represents iPredicted power, P, of new energy power station i Representing available power, P, of the new energy plant at time i Mi Representing the available generated power at time i of the limited period, i representing time, m representing the number of segments of the late peak and valley periods, J ae Shows the maximum absolute error assessment of the wind field, P w Represents the installed capacity, P, of the new energy power station biaogan Indicating the price of the post.
6. The method of claim 4, wherein the charge proportion constraint is expressed as:
Q_jishu t =k t Q_riqian t
wherein, Q _ jishu t Base number of electric quantities, Q _ riqian, representing time t t Indicating the current day-ahead power at time t, k 1 The ratio of the base number electric quantity at the time t to the reported electric quantity before the day is represented,
the excess profit recovery loss constraint is expressed as:
if the actual power generation amount is lower than the allowable deviation lower limit of the power amount before the spot date, the deviation recovery loss is expressed as:
J 11,t =max(Q_riqian t -(1+λ)×Q_shishi t ,0)×max(Pzr t -P_shishi t ,0)
wherein, Q-riqian t Represents the quantity of electricity before the current date of stock at time t, lambda represents the excess profit recovery ratio, pzr t Weighted electricity prices, Q _ shishi, representing the benchmarking electricity prices at time t and the day-ahead electricity prices t Represents the real-time electric quantity of the spot goods at the moment t, P _ shishi t Represents the spot real-time electricity rate at time t,
if the actual power generation amount is lower than the allowable deviation lower limit of the power amount before the spot date, the deviation recovery loss is expressed as:
J 11,t =max(Q_riqian t -(1+λ)×Q_shishi t ,0)×max(Pzr t -P_shishi t ,0)
wherein, Q-riqian t Represents the quantity of electricity before the current date of stock at time t, lambda represents the excess profit recovery ratio, pzr t Weighted electricity prices, Q-sh, representing the benchmarking electricity prices at time t and the day-ahead electricity pricesishi t Real-time electric quantity of stock at time t, P-shishi t Indicating the spot real-time electricity prices at time t.
7. The method of claim 4, wherein the settlement revenue constraint is expressed as:
J chaoe,h =min(J 11,h +J 12,h ,J jiesuan,h )
wherein, J jiesuan,h Denotes the spot-settlement income at h, Q zhong,4h+i Represents the medium-and long-term electric quantity at h, i, P zhong,4h+i Represents the medium-and long-term weighted electric quantity at h-hour i, Q riqian,4h+i Current day-ahead power, P, representing h hours, i time riqian,4h+i Indicating the spot-time day-ahead electricity price at time h, i, Q shishi,4h+i Real-time electric quantity of stock in h hour i moment, P shishi,4h+i Express the spot real-time electricity price at time h, i, J chaoe,h Represents the excess profit recovery loss at h, J 11,h A deviation recovery loss representing that the generated electric power at h is lower than the allowable deviation lower limit of the electric power before the actual date, J 22,h Represents a deviation recovery loss in which the h-time power generation amount is higher than the allowable deviation upper limit of the actual-date power amount,
the declared power constraint is expressed as:
Q_riqian t ≤P w ×Δt
wherein Q _ riqian t Indicating the quantity of electricity in the spot at time t, P w And the installed capacity of the new energy power station is shown, and delta t represents a time interval.
8. The method of claim 1, wherein said solving based on said constraints based on said objective function as a solution objective based on said forecast data, said contract data, and said market environment information to obtain an optimal future declaration scheme comprises:
and according to the medium-long term contract historical data, the market disclosure data, the power prediction data and the prediction data contained in the contract data, taking the objective function as a solving target, taking the constructed constraint condition as a limit, and adopting an ant colony algorithm to solve to obtain an optimal future declaration scheme.
9. An auxiliary decision making system for the day-ahead transaction of new energy in an electric power market based on an artificial intelligence technology is characterized by comprising an acquisition module, a prediction module and a scheme generation module, wherein,
the acquisition module is used for acquiring data to be processed, wherein the data to be processed comprises historical data, contract data and market environment information, and the historical data comprises comprehensive historical trading price data;
the prediction module is used for predicting the new energy trading price of the electric power market based on the historical data to obtain prediction data;
and the scheme generation module is used for solving by taking the objective function as a solving target and based on the constraint condition according to the market environment information, the processed contract data and the prediction data to obtain an optimal daily declaration scheme.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1-8 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211202436.XA CN115496603A (en) | 2022-09-29 | 2022-09-29 | Artificial intelligence technology-based new energy day-ahead transaction decision method for power market |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211202436.XA CN115496603A (en) | 2022-09-29 | 2022-09-29 | Artificial intelligence technology-based new energy day-ahead transaction decision method for power market |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115496603A true CN115496603A (en) | 2022-12-20 |
Family
ID=84472246
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211202436.XA Pending CN115496603A (en) | 2022-09-29 | 2022-09-29 | Artificial intelligence technology-based new energy day-ahead transaction decision method for power market |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115496603A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115641175A (en) * | 2022-12-26 | 2023-01-24 | 国能日新科技股份有限公司 | Medium-and-long-term power transaction assistant decision-making determination method and device for new energy power station |
CN116128323A (en) * | 2023-04-07 | 2023-05-16 | 阿里巴巴达摩院(杭州)科技有限公司 | Power transaction decision processing method, storage medium and electronic equipment |
-
2022
- 2022-09-29 CN CN202211202436.XA patent/CN115496603A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115641175A (en) * | 2022-12-26 | 2023-01-24 | 国能日新科技股份有限公司 | Medium-and-long-term power transaction assistant decision-making determination method and device for new energy power station |
CN116128323A (en) * | 2023-04-07 | 2023-05-16 | 阿里巴巴达摩院(杭州)科技有限公司 | Power transaction decision processing method, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11699198B2 (en) | Methods and systems for machine-learning for prediction of grid carbon emissions | |
Chen et al. | Local energy trading behavior modeling with deep reinforcement learning | |
CN111492559B (en) | System and method for optimal control of an energy storage system | |
Shin et al. | Operational planning and optimal sizing of microgrid considering multi-scale wind uncertainty | |
Bottieau et al. | Very-short-term probabilistic forecasting for a risk-aware participation in the single price imbalance settlement | |
Gonzalez et al. | Forecasting power prices using a hybrid fundamental-econometric model | |
CN115496603A (en) | Artificial intelligence technology-based new energy day-ahead transaction decision method for power market | |
WO2013102932A2 (en) | System and method facilitating forecasting, optimization and visualization of energy data for an industry | |
CA2846722A1 (en) | Systems and methods of determining optimal scheduling and dispatch of power resources | |
CN115511634A (en) | New energy day-ahead transaction decision-making method and device for electricity market based on settlement income | |
CN115102202B (en) | Energy storage control method based on rolling type real-time electricity price prediction | |
Qi et al. | Energyboost: Learning-based control of home batteries | |
CN114943565A (en) | Electric power spot price prediction method and device based on intelligent algorithm | |
Sai et al. | Event-driven forecasting of wholesale electricity price and frequency regulation price using machine learning algorithms | |
Pourdaryaei et al. | A new framework for electricity price forecasting via multi-head self-attention and CNN-based techniques in the competitive electricity market | |
Toubeau et al. | Forecast-driven stochastic scheduling of a virtual power plant in energy and reserve markets | |
Keles et al. | Evaluation of photovoltaic storage systems on energy markets under uncertainty using stochastic dynamic programming | |
CN113052630B (en) | Method for configuring electric power equipment by using model and electric power equipment configuration method | |
Lago et al. | Building day-ahead bidding functions for seasonal storage systems: A reinforcement learning approach | |
Sapio | Econometric modelling and forecasting of wholesale electricity prices | |
CN115587890A (en) | Detailed examination loss-based power market new energy day-ahead transaction decision-making method | |
CN115601067A (en) | New energy day-ahead transaction decision-making method and device for electric power market | |
US11221366B2 (en) | System and method for management of electrochemical energy storage devices | |
Shavandi et al. | An Efficient Data Driven Model for Generation Expansion Planning with Short Term Operational Constraints | |
Visser et al. | Probabilistic solar power forecasting: An economic and technical evaluation of an optimal market bidding strategy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |