CN113887800A - Monthly or ten-day time period transaction auxiliary decision making method and system - Google Patents
Monthly or ten-day time period transaction auxiliary decision making method and system Download PDFInfo
- Publication number
- CN113887800A CN113887800A CN202111151549.7A CN202111151549A CN113887800A CN 113887800 A CN113887800 A CN 113887800A CN 202111151549 A CN202111151549 A CN 202111151549A CN 113887800 A CN113887800 A CN 113887800A
- Authority
- CN
- China
- Prior art keywords
- decision
- monthly
- transaction
- model
- day
- 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 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 230000002068 genetic effect Effects 0.000 claims abstract description 21
- 230000007774 longterm Effects 0.000 claims abstract description 18
- 230000005611 electricity Effects 0.000 claims description 34
- 230000006870 function Effects 0.000 claims description 22
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012098 association analyses Methods 0.000 claims description 6
- 238000000611 regression analysis Methods 0.000 claims description 6
- 238000012896 Statistical algorithm Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims 3
- 238000010248 power generation Methods 0.000 abstract description 15
- 230000008901 benefit Effects 0.000 abstract description 8
- 238000005096 rolling process Methods 0.000 abstract description 8
- 238000007619 statistical method Methods 0.000 abstract description 6
- 230000007246 mechanism Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000454 anti-cipatory effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012954 risk control 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- 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
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
Abstract
The invention discloses a monthly or ten-day time-phased transaction assistant decision method and a system, wherein historical data and held medium and long term contract data are preprocessed by a statistical analysis method; secondly, establishing an auxiliary decision model with the aim of maximizing the day-ahead settlement income, then performing nominal estimation on the declared electric quantity through the model transaction probability and constraining the model by combining monthly or ten-day time period trading market rules; and finally, solving the auxiliary decision-making scheme for the monthly or ten-day time-share transaction by combining an operational research method and a genetic algorithm, and assisting a power generation side user to finish concentrated bidding monthly or ten-day time-share transaction and rolling monthly or ten-day time-share transaction declaration decisions, so that a declaration decision-making scheme is provided for a decision maker, human resources are saved, scientific reliability is improved, economic benefit maximization is realized, and income maximization is realized.
Description
Technical Field
The invention belongs to the field of declaration decision of an electric power market, and particularly relates to a monthly or ten-day time-interval transaction auxiliary decision method and system.
Background
According to the relevant requirements of the national energy agency on spot market construction, the construction of a provincial power market is further promoted, the relevant mechanisms of long-term transaction in a wholesale market, the wholesale market and a retail market under a spot mode are perfected, the problems that the long-term transaction mechanisms are not matched and flexible, the wholesale price and the retail price are not smooth and the like in the spot market construction are solved, a market system with the integrated integration of the long-term transaction and the spot transaction and the transparent and smooth transmission of the wholesale price and the retail market price is established, and the guiding effect of a power market price signal on power production and consumption is realized. The medium-long time-sharing trading mechanism and the retail market time-sharing trading mechanism which are connected with the spot trade in the wholesale market are established, and the full electric quantity time-sharing price of the electric power market is realized. But how to make reasonable time-interval declaration decision is the key to obtain effective benefit.
At present, the domestic time-phased trading market is gradually developed, and a guiding theory is not provided for how a power generation side user makes a reasonable declaration decision scheme, most power generation side users only rely on industry knowledge and experts with abundant experience to make trial declaration decisions by means of the general market trend, and the influences of factors such as benefit maximization, power utilization side user declaration volume price and the like are not considered; the method not only consumes time, but also occupies a large amount of human resources, so that the efficiency is low, the randomness is too strong, scientific basis support calculation is not available, the repeatability is too poor, the instantaneity is not strong, and the like.
Disclosure of Invention
The invention aims to solve the technical problems and provides a monthly or ten-day time-share transaction assistant decision-making method and system.
In order to solve the technical problem, the technical scheme of the invention is as follows:
a monthly or ten-day time-phased transaction aid decision method, the method comprising:
preprocessing the held medium and long term contract data to obtain electric quantity data and electricity price data in different time periods;
carrying out numerical association analysis on preset market disclosure information and historical data to obtain an association analysis result;
solving the correlation analysis result by adopting a regression analysis method to obtain a typical curve of the historical data;
estimating reported electric quantity according to the electric quantity data and the electricity price data of the time intervals and a preset model transaction probability to obtain a target estimated value, a typical curve of the historical data, a preset market transaction rule and a power plant self constraint condition, and establishing a model constraint condition;
establishing an objective function by referring to the aim of maximizing the settlement income of medium and long term and day-ahead market deviation based on a preset day-ahead settlement formula of the electric power spot-market;
generating an auxiliary decision-making model according to the model constraint condition and the objective function;
optimizing and solving the assistant decision model by using a SCIPY solver and a genetic algorithm to obtain an optimal declaration strategy;
firstly, preprocessing historical data and held medium and long term contract data by a statistical analysis method; secondly, establishing an auxiliary decision model with the aim of maximizing the day-ahead settlement income, then performing nominal estimation on the declared electric quantity through the model transaction probability and constraining the model by combining monthly or ten-day time period trading market rules; and finally, solving the auxiliary decision-making scheme for the monthly or ten-day time-share transaction by combining an operational research method and a genetic algorithm, and assisting a power generation side user to finish concentrated bidding monthly or ten-day time-share transaction and rolling monthly or ten-day time-share transaction declaration decisions, so that a declaration decision-making scheme is provided for a decision maker, and the income of the decision maker is maximized.
Further, the preprocessing the held contract data includes: and decomposing the held contract data by using a statistical algorithm.
Further, the historical data includes: day-ahead price data, clear electricity output data and base electricity data.
Further, the optimizing and solving the assistant decision model by using the SCIPY solver and the genetic algorithm to obtain the optimal declaration strategy includes:
solving the assistant decision model by using a SCIPY solver to obtain a plurality of optimal solutions;
and analyzing and comparing the optimal solutions to obtain a first declaration decision scheme.
Further, the optimizing and solving the assistant decision model by using the SCIPY solver and the genetic algorithm to obtain the optimal declaration strategy further includes:
setting a maximum time limit on the SCIPY solver to obtain the SCIPY solver containing the maximum time limit;
solving the assistant decision model by adopting the SCIPY solver with the maximum time limit to obtain a suboptimal solution;
and substituting the suboptimal solution as an initial parameter into a genetic algorithm for solving to obtain a second declaration decision scheme.
Further, the optimizing and solving the assistant decision model by using the SCIPY solver and the genetic algorithm to obtain the optimal declaration strategy further includes:
and analyzing and comparing the first reporting decision scheme and the second reporting decision scheme to obtain an optimal reporting decision scheme.
A monthly or ten-day time period trading aid decision making system, the system comprising:
one or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to perform a method of periodic transaction aid decision making as described above.
Compared with the prior art, the invention has the advantages that:
a month or ten days time interval trade assistant decision method and system, carry on the preconditioning to historical data and already held medium and long term contract data through the statistical analysis method at first; secondly, establishing an auxiliary decision model with the aim of maximizing the day-ahead settlement income, then performing nominal estimation on the declared electric quantity through the model transaction probability and constraining the model by combining monthly or ten-day time period trading market rules; and finally, solving the auxiliary decision-making scheme for the monthly or ten-day time-share transaction by combining an operational research method and a genetic algorithm, and assisting a power generation side user to finish concentrated bidding monthly or ten-day time-share transaction and rolling monthly or ten-day time-share transaction declaration decisions, so that a declaration decision-making scheme is provided for a decision maker, human resources are saved, scientific reliability is improved, economic benefit maximization is realized, and income maximization is realized.
Drawings
FIG. 1 is a flowchart illustrating an embodiment of a method and system for making a decision for a monthly or ten-day time-phased transaction assistance according to the present invention;
FIG. 2 is a flowchart of model solution for a monthly or ten-day time-phased transaction aid decision method and system according to the present invention;
FIG. 3 is a typical graph of 8 month day-ahead prices for a model solution of a monthly or ten-day time-share transaction aid decision method and system of the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to examples:
it should be noted that the structures, proportions, sizes, and other elements shown in the specification are included for the purpose of understanding and reading only, and are not intended to limit the scope of the invention, which is defined by the claims, and any modifications of the structures, changes in the proportions and adjustments of the sizes, without affecting the efficacy and attainment of the same.
In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms is not to be construed as a scope of the present invention.
Example one
As shown in fig. 1, a method for assisting decision-making in monthly or ten-day time-share transaction, the method comprises:
preprocessing the held medium and long term contract data to obtain electric quantity data and electricity price data in different time periods;
carrying out numerical association analysis on preset market disclosure information and historical data to obtain an association analysis result;
solving the correlation analysis result by adopting a regression analysis method to obtain a typical curve of the historical data;
estimating reported electric quantity according to the electric quantity data and the electricity price data of the time intervals and a preset model transaction probability to obtain a target estimated value, a typical curve of the historical data, a preset market transaction rule and a power plant self constraint condition, and establishing a model constraint condition;
establishing an objective function by referring to the aim of maximizing the settlement income of medium and long term and day-ahead market deviation based on a preset day-ahead settlement formula of the electric power spot-market;
generating an auxiliary decision-making model according to the model constraint condition and the objective function;
optimizing and solving the assistant decision model by using a SCIPY solver and a genetic algorithm to obtain an optimal declaration strategy;
firstly, preprocessing historical data and held medium and long term contract data by a statistical analysis method; secondly, establishing an auxiliary decision model with the aim of maximizing the day-ahead settlement income, then performing nominal estimation on the declared electric quantity through the model transaction probability and constraining the model by combining monthly or ten-day time period trading market rules; and finally, solving the auxiliary decision-making scheme for the monthly or ten-day time-share transaction by combining an operational research method and a genetic algorithm, and assisting a power generation side user to finish concentrated bidding monthly or ten-day time-share transaction and rolling monthly or ten-day time-share transaction declaration decisions, so that a declaration decision-making scheme is provided for a decision maker, and the income of the decision maker is maximized.
Further, the preprocessing the held contract data includes: and decomposing the held contract data by using a statistical algorithm.
Further, the historical data includes: day-ahead price data, clear electricity output data and base electricity data.
Further, the optimizing and solving the assistant decision model by using the SCIPY solver and the genetic algorithm to obtain the optimal declaration strategy includes:
solving the assistant decision model by using a SCIPY solver to obtain a plurality of optimal solutions;
and analyzing and comparing the optimal solutions to obtain a first declaration decision scheme.
Further, the optimizing and solving the assistant decision model by using the SCIPY solver and the genetic algorithm to obtain the optimal declaration strategy further includes:
setting a maximum time limit on the SCIPY solver to obtain the SCIPY solver containing the maximum time limit;
solving the assistant decision model by adopting the SCIPY solver with the maximum time limit to obtain a suboptimal solution;
and substituting the suboptimal solution as an initial parameter into a genetic algorithm for solving to obtain a second declaration decision scheme.
Further, the optimizing and solving the assistant decision model by using the SCIPY solver and the genetic algorithm to obtain the optimal declaration strategy further includes:
and analyzing and comparing the first reporting decision scheme and the second reporting decision scheme to obtain an optimal reporting decision scheme.
A monthly or ten-day time period trading aid decision making system, the system comprising:
one or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to perform a method of periodic transaction aid decision making as described above.
Example two
Data pre-processing
One of the purposes of time-interval transaction is to solve the problem of mismatching of medium and long-term transaction mechanisms in the spot market, so that prices and electric quantities declared by transaction in different time intervals are associated with corresponding spot market historical data such as spot price and electric quantity, and the historical data needs to be processed, and the time-interval transaction mainly comprises the following steps:
(1) firstly, obtaining the electric quantity and the price decomposed to different time periods corresponding to months and ten days by utilizing a statistical method for the held medium and long term contracts;
(2) then, according to the market disclosure information and the curve forms of the historical data day-ahead price, the output clear electricity quantity and the base electricity quantity, carrying out numerical analysis to find that the curve forms have a certain correlation with each time period, and determining the correlation;
(3) and finally, solving by using a regression analysis method (such as a least square method) based on the analyzed correlation to obtain a day-ahead price typical curve, a discharged clean electricity quantity typical curve and a base electricity quantity typical curve.
Model building
Based on a day-ahead settlement formula of the electric power spot trading market, the medium-long term and day-ahead market deviation settlement income is maximized to be an objective function, and settlement is carried out by taking a power plant as a main body. The objective function is shown in equation (1) below: (1):
wherein, Model _ QjThe reported electric quantity of time-share transaction is expressed according to the ruleAn estimate of the j-th time segment marker obtained by the rate function; pjRepresenting the declaration of the price of the electricity in the jth time period of the time-period transaction; qriqian,jA value of the j-th period expressed as a curve typical of the amount of fresh electric power; priqian,jA value representing the jth period of the day-ahead price profile; m represents the shortage electric quantity recovery cost of the ten-day time-interval transaction which is not subjected to the market rule requirement. others means days less than 15, days means days; the first of formula (1) is used for the monthly degree of the objective function, and the second of formula (1) is used for the monthly degree of the objective function.
Qzhong,j，Pzhong,jThe contract electric quantity and the contract weighted electricity price in the j time period are respectively calculated as follows:
Qjishu,ja value of a jth period expressed as a base electricity quantity typical curve; pjishu,jRepresenting a base contract price; qhold,j,Phold,jRespectively representing the electric quantity and the weighted electricity price of the held medium and long term contract decomposed to the corresponding month or ten days.
The objective functions established in the monthly or ten-day centralized bidding time-share trading exchange and the rolling matching time-share trading exchange are the same, only the punishment needs to be considered in the ten-day trading, and the day-ahead price, the electric quantity, the medium-long term quantity and the price corresponding to the centralized bidding and the rolling matching are different.
According to the market disclosure information, the market rule and the operation research method, the following steps are carried out to solve the objective function:
according to the time interval price upper and lower limits disclosed by the market, the declared price of each time interval in the time interval transaction of the power generation side should meet the following formula (2):
P_downj≤Pj≤P_upj (2)
wherein, PjRepresenting that the time-share transaction reports the price of electricity in the j time-share period; p _ Downj、P_upjRespectively representing the lower price and the upper price limit of the time-share transaction in the j time-share transaction.
The declared electric quantity of each time interval of the time-interval transaction cannot exceed the electric quantity limit of each time interval of each market main body, and the following formula (3) shows that:
Qj≤Q_lim itj (3)
wherein Q isjRepresenting that the time-interval transaction declares the electric quantity in the j time interval; q _ lim itjIndicating the power limit for the time period transaction during the j-th time period.
According to market rules, a power generation side user follows a power generation principle when carrying out time-share transaction for the first time, and although the user can declare the purchase quantity and the sale quantity of electricity in each time-share transaction, the purchase quantity cannot exceed the sale quantity, otherwise, the power generation side of the user does not accord with the market rules. Therefore, the reported electric quantity can not be the purchased electric quantity in monthly transaction, and the later transaction can purchase the electric quantity in ten days because of the sold quantity of the monthly transaction, but the reported purchased (purchased) electric quantity can not exceed the sum of the net sold electric quantity of the held medium-long term contracts of each batch decomposed to the time period. As shown in equation (4).
Wherein Q _ buy _ lim itjRepresenting the upper limit of the available electric quantity of the time-share transaction in the j time-share period; q _ holdjRepresenting the held medium and long term contract breaking down to the sum of net contract electric quantities at the j-th time period.
Because the power plant generates power according to its own generator set, the sold electric quantity can not exceed its own power generation capacity, that is, the sum of the reported sold electric quantity at each time interval and the net sold electric quantity decomposed to the time interval by the held medium and long term contract at the power generation side in the time interval transaction, and the converted electric power can not exceed the installed capacity of the power plant, as shown in formula (5):
Qj+Q_holdj≤S_max (5)
where S _ max represents the installed capacity of the plant.
According to the market rule, the sum of the total monthly accumulated electricity purchased in each time interval in the time interval transaction of the power generation side is not more than 50% of the sum of the total monthly accumulated electricity sold in the jth time interval in each batch of transaction, as shown in the formula (6):
max(-Qj,0)+Q_buy_holdj≤0.5*(max(Qj,0)+Q_sell_holdj) (6)
wherein Q _ buy _ holdjRepresenting the sum of the electric quantity bought by each batch of transactions in the j time period; q _ sel _ holdjIndicating the sum of the sold electric quantity of each batch of transaction in the j time period.
When the transaction price is higher than the spot price in a certain time interval, the transaction price is called price premium; otherwise, the price is reduced. From the perspective of cost minimization and benefit maximization, the market body hopes to reduce premium price and trade at a discount price as much as possible on the premise of meeting risk control. While future spot prices can be predicted to avoid risk, there is a serious uncertainty; therefore, statistics, target valuation and an AI model are carried out on market main body transactions to summarize different target discount and premium rules of each transaction batch from historical transactions, and the transaction probability of reporting volume price in each time period in time-sharing transactions is established to carry out target valuation in each time period. The invention firstly obtains the psychological expected price and the transaction probability function through data analysis and statistical method, as shown in the formula (7):
from this, the target estimation value of the declared electric quantity at the j-th time period on the power generation side is as shown in equation (8):
Model_Qj＝Qj×P* j (8)
wherein, P _ expectjRepresenting psychological anticipatory value for period j，F1(x),F2(x),F3(x) Representing a deal probability function for an offer; model _ QjIndicating a target estimate for the j-th time period.
Model solution
The method is solved according to the established model, and because the optimal solution is not unique in the solving process, the method can find the unique solution in the optimal window by the following method, the flow chart of which is shown in figure 2, and the specific process is as follows:
(1) according to the proposed objective function and various rule constraints, the SCIPY solver is adopted to solve the objective function and various rule constraints, a plurality of optimal solutions obtained by the solution are stored, then the cost is minimized through comparative analysis, and the benefit is maximized to obtain a final declaration strategy.
(2) Firstly, according to the established model, a suboptimal solution is obtained by setting the maximum solving time and utilizing a SCIPY solver, and then the suboptimal solution is taken as an initial parameter to be brought into a genetic algorithm for solving, so that an optimal declaration decision scheme is obtained.
(3) And comparing the optimal declaration schemes obtained by the two methods, and selecting a declaration decision scheme with the highest benefit and the lowest cost between the two methods.
It can be understood that: the monthly time-share transaction assistant decision-making model and the ten-day time-share transaction assistant decision-making model are respectively established because the monthly time-share transaction and the ten-day time-share transaction both comprise two parts of centralized bidding and rolling matching and are different according to the date and time of payment. There is a certain correlation between the two, but the market rules and the solution are slightly different, and the main flow chart of the model is shown in fig. 1. Firstly, preprocessing the held contract data, and obtaining typical curves of the day-ahead price, the output clear electricity quantity and the base electricity quantity from the historical data of one month in the spot market by using a regression analysis method; then, obtaining a model bargaining probability function by carrying out statistics on market main transactions, estimating the bid value and summarizing rules from historical transactions by an AI model, utilizing the model bargaining probability function to estimate the declared electric quantity, and establishing an auxiliary decision-making model by combining market rules of centralized bidding in month or ten days and time-sharing trading of rolling match; finally, solving the transaction date by an operation research method and a genetic algorithm to obtain an auxiliary decision scheme, and realizing the declaration decision of the transaction date on the redemption date, wherein the redemption date is a natural month or ten days representing that the time-period transaction is actually executed in month or ten days; the date of the transaction represents the date of decision making for declaration, which is generally about 20 months before the date of redemption, the monthly transaction is carried out 15 days ahead, and the ten-day transaction is generally about 5 days before the date of redemption begins.
EXAMPLE III
As shown in table 1, according to the load data of the whole network of the 7-month history of a certain thermal power plant in shanxi province, historical meteorological data, historical day-ahead electricity price data, historical unit winning capacity data and historical base number electricity quantity data, 8-month day-ahead price, leaving clear electricity quantity and base number electricity quantity typical curve data are obtained through statistics and a regression analysis model, wherein a day-ahead price typical curve is shown in fig. 3:
the maximum installed capacity S _ max of the power plant is 1200MWh, the maximum saleable electric quantity Q _ max is 28800MWh, and the upper and lower price limits can be calculated through a calculation mode. And (3) optimally solving 8-month centralized bidding divided-period transaction declaration decision results according to the existing data, the objective function and the constraint equation, wherein the declaration decision results are shown in table 1, and the 8-month medium-long-term daily income can be calculated to be 649.62 ten thousand yuan according to the formula (1).
Taking the 6 th time slot as an example, the first section of the declared electric quantity is 530.3NMh, the sum of the two sections is just the upper limit of the saleable electric quantity, the declared price of electricity is 315.93 yuan/NMh and is equal to the upper limit of the price, the analysis of the current spot market in the day and the psychological forecast price is combined to know that the declared price is the highest price which can be declared, although the price is lower than the current price of 360.36 yuan/NMh in the day and has a smaller difference with the psychological forecast price of 316 yuan/NMh, the probability of bargaining can be 1 according to the probability function, and therefore, the maximum saleable quantity of the time slot sold at the highest price is reasonable.
Taking the 20 th time period as an example, the declaration amount and the price are both 0, the time period can be obtained as the electricity utilization peak time according to the market electricity utilization law, the declaration cannot be committed even if the highest price of 670 yuan/NMh is declared, the price upper limit at the time is 630.36 yuan/NMh which is higher than the psychological expected price of 512.56 yuan/NMh, and the declaration of the highest price as the highest price of 0 can be known according to the probability function to be not committed; in combination with the market at that time, the day-ahead price of 641.89 yuan/NMh is very high, so that the electricity in the time is more favorable for selling in the spot-market.
In conclusion, the auxiliary decision of the monthly centralized bidding and time-share transaction can be effectively declared, and the income of the power generation side is improved.
TABLE 1-August centralized bidding time-share transaction assistant decision-making result
While the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Many other changes and modifications can be made without departing from the spirit and scope of the invention. It is to be understood that the invention is not to be limited to the specific embodiments, but only by the scope of the appended claims.
Claims (7)
1. An aid decision-making method for monthly or ten-day time-phased transactions, the method comprising:
preprocessing the held medium and long term contract data to obtain electric quantity data and electricity price data in different time periods;
carrying out numerical association analysis on preset market disclosure information and historical data to obtain an association analysis result;
solving the correlation analysis result by adopting a regression analysis method to obtain a typical curve of the historical data;
estimating reported electric quantity according to the electric quantity data and the electricity price data of the time intervals and a preset model transaction probability to obtain a target estimated value, a typical curve of the historical data, a preset market transaction rule and a power plant self constraint condition, and establishing a model constraint condition;
establishing an objective function by referring to the aim of maximizing the settlement income of medium and long term and day-ahead market deviation based on a preset day-ahead settlement formula of the electric power spot-market;
generating an auxiliary decision-making model according to the model constraint condition and the objective function;
and optimizing and solving the assistant decision model by using a SCIPY solver and a genetic algorithm to obtain an optimal declaration strategy.
2. The method for assisting decision making during monthly or ten-day time-share transaction according to claim 1, wherein the preprocessing the held contract data comprises: and decomposing the held contract data by using a statistical algorithm.
3. The method of claim 1, wherein the historical data comprises: day-ahead price data, clear electricity output data and base electricity data.
4. The monthly or ten-day time-phased transaction assistant decision making method according to claim 1, wherein the optimal declaration strategy obtained by performing optimization solution on the assistant decision making model by using a SCIPY solver and a genetic algorithm comprises:
solving the assistant decision model by using a SCIPY solver to obtain a plurality of optimal solutions;
and analyzing and comparing the optimal solutions to obtain a first declaration decision scheme.
5. The monthly or ten-day time-phased transaction assistant decision making method according to claim 4, wherein the optimal declaration strategy is obtained by performing optimization solution on the assistant decision making model by using a SCIPY solver and a genetic algorithm, further comprising:
setting a maximum time limit on the SCIPY solver to obtain the SCIPY solver containing the maximum time limit;
solving the assistant decision model by adopting the SCIPY solver with the maximum time limit to obtain a suboptimal solution;
and substituting the suboptimal solution as an initial parameter into a genetic algorithm for solving to obtain a second declaration decision scheme.
6. The monthly or ten-day time-phased transaction assistant decision making method according to claim 5, wherein the optimal declaration strategy is obtained by performing optimization solution on the assistant decision making model by using a SCIPY solver and a genetic algorithm, further comprising:
and analyzing and comparing the first reporting decision scheme and the second reporting decision scheme to obtain an optimal reporting decision scheme.
7. A system for assisting decision-making in monthly or ten-day time-phased transactions, the system comprising:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to perform a monthly or laetime split transaction aid decision making method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111151549.7A CN113887800A (en) | 2021-09-29 | 2021-09-29 | Monthly or ten-day time period transaction auxiliary decision making method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111151549.7A CN113887800A (en) | 2021-09-29 | 2021-09-29 | Monthly or ten-day time period transaction auxiliary decision making method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113887800A true CN113887800A (en) | 2022-01-04 |
Family
ID=79008037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111151549.7A Pending CN113887800A (en) | 2021-09-29 | 2021-09-29 | Monthly or ten-day time period transaction auxiliary decision making method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887800A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971422A (en) * | 2022-07-26 | 2022-08-30 | 中国华能集团清洁能源技术研究院有限公司 | Auxiliary control system and method for ten-day transaction of medium-long time-sharing transaction of electric power |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120232959A1 (en) * | 2011-03-11 | 2012-09-13 | Oracle International Corporation | Optimized pricing solver with prioritized constraints |
| JP2016035719A (en) * | 2014-08-04 | 2016-03-17 | 株式会社東芝 | Electric power transaction support system, electric power transaction system, control method and control program |
| CN107845022A (en) * | 2017-11-02 | 2018-03-27 | 北京恒泰能联科技发展有限公司 | Electricity market aid decision-making systems |
| CN108346112A (en) * | 2017-12-29 | 2018-07-31 | 广州亦云信息技术股份有限公司 | Medium and long-term transaction quantity division method, system, electronic equipment and storage medium |
| CN108960510A (en) * | 2018-07-04 | 2018-12-07 | 四川大学 | A kind of virtual plant optimization trading strategies model based on two stage stochastic programming |
| CN109523309A (en) * | 2018-10-26 | 2019-03-26 | 武汉华中思能科技有限公司 | A kind of electric power quotation emulation mode and system calculated based on tidal current analysis |
| CN109886751A (en) * | 2019-02-26 | 2019-06-14 | 国家电网有限公司 | A kind of monthly concentration Bidding Mechanism method for solving based on Cooperative Evolutionary Algorithm |
| CN110310022A (en) * | 2019-06-18 | 2019-10-08 | 广州汇电云联互联网科技有限公司 | A kind of power plant's monthly generation scheduling decomposition method based on power spot market price |
| CN111144791A (en) * | 2019-12-31 | 2020-05-12 | 新奥数能科技有限公司 | Electric quantity decomposition scheme determination method and device, readable medium and electronic equipment |
| CN111738854A (en) * | 2020-06-22 | 2020-10-02 | 国能日新科技股份有限公司 | New energy spot transaction decision-making data service system based on cloud computing |
| CN111784451A (en) * | 2020-06-29 | 2020-10-16 | 中国电力科学研究院有限公司 | Distributed electric power multilateral transaction method and system based on multiple time scales |
| CN111798024A (en) * | 2020-05-21 | 2020-10-20 | 国电南瑞科技股份有限公司 | Method and device for determining power plant quotation under subsection quotation rule |
| CN111967158A (en) * | 2020-08-15 | 2020-11-20 | 国网福建省电力有限公司 | Medium-and-long-term transaction power curve decomposition method connected with spot transaction |
| CN112001744A (en) * | 2020-07-28 | 2020-11-27 | 安徽电力交易中心有限公司 | Power generator auxiliary quotation system and method based on prospect theory in electric power spot market |
| US20200394712A1 (en) * | 2019-05-31 | 2020-12-17 | Dalian University Of Technology | Electricity Retail Trading System and Method for Coupling Wholesale Market |
| CN112785435A (en) * | 2021-01-29 | 2021-05-11 | 西安峰频能源科技有限公司 | Model for assisting unit to quote in spot transaction declaration |
| CN113011923A (en) * | 2021-03-19 | 2021-06-22 | 西安峰频能源科技有限公司 | Segmented report quotation method based on user-defined strategy |
| CN113032995A (en) * | 2021-03-23 | 2021-06-25 | 山东大学 | Electric power market simulation optimization and operation method, system and simulation platform |
| CN113095628A (en) * | 2021-03-18 | 2021-07-09 | 北京科东电力控制系统有限责任公司 | Electric power transaction platform time-interval bidding clearing method and system for promoting clean consumption |
-
2021
- 2021-09-29 CN CN202111151549.7A patent/CN113887800A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120232959A1 (en) * | 2011-03-11 | 2012-09-13 | Oracle International Corporation | Optimized pricing solver with prioritized constraints |
| JP2016035719A (en) * | 2014-08-04 | 2016-03-17 | 株式会社東芝 | Electric power transaction support system, electric power transaction system, control method and control program |
| CN107845022A (en) * | 2017-11-02 | 2018-03-27 | 北京恒泰能联科技发展有限公司 | Electricity market aid decision-making systems |
| CN108346112A (en) * | 2017-12-29 | 2018-07-31 | 广州亦云信息技术股份有限公司 | Medium and long-term transaction quantity division method, system, electronic equipment and storage medium |
| CN108960510A (en) * | 2018-07-04 | 2018-12-07 | 四川大学 | A kind of virtual plant optimization trading strategies model based on two stage stochastic programming |
| CN109523309A (en) * | 2018-10-26 | 2019-03-26 | 武汉华中思能科技有限公司 | A kind of electric power quotation emulation mode and system calculated based on tidal current analysis |
| CN109886751A (en) * | 2019-02-26 | 2019-06-14 | 国家电网有限公司 | A kind of monthly concentration Bidding Mechanism method for solving based on Cooperative Evolutionary Algorithm |
| US20200394712A1 (en) * | 2019-05-31 | 2020-12-17 | Dalian University Of Technology | Electricity Retail Trading System and Method for Coupling Wholesale Market |
| CN110310022A (en) * | 2019-06-18 | 2019-10-08 | 广州汇电云联互联网科技有限公司 | A kind of power plant's monthly generation scheduling decomposition method based on power spot market price |
| CN111144791A (en) * | 2019-12-31 | 2020-05-12 | 新奥数能科技有限公司 | Electric quantity decomposition scheme determination method and device, readable medium and electronic equipment |
| CN111798024A (en) * | 2020-05-21 | 2020-10-20 | 国电南瑞科技股份有限公司 | Method and device for determining power plant quotation under subsection quotation rule |
| CN111738854A (en) * | 2020-06-22 | 2020-10-02 | 国能日新科技股份有限公司 | New energy spot transaction decision-making data service system based on cloud computing |
| CN111784451A (en) * | 2020-06-29 | 2020-10-16 | 中国电力科学研究院有限公司 | Distributed electric power multilateral transaction method and system based on multiple time scales |
| CN112001744A (en) * | 2020-07-28 | 2020-11-27 | 安徽电力交易中心有限公司 | Power generator auxiliary quotation system and method based on prospect theory in electric power spot market |
| CN111967158A (en) * | 2020-08-15 | 2020-11-20 | 国网福建省电力有限公司 | Medium-and-long-term transaction power curve decomposition method connected with spot transaction |
| CN112785435A (en) * | 2021-01-29 | 2021-05-11 | 西安峰频能源科技有限公司 | Model for assisting unit to quote in spot transaction declaration |
| CN113095628A (en) * | 2021-03-18 | 2021-07-09 | 北京科东电力控制系统有限责任公司 | Electric power transaction platform time-interval bidding clearing method and system for promoting clean consumption |
| CN113011923A (en) * | 2021-03-19 | 2021-06-22 | 西安峰频能源科技有限公司 | Segmented report quotation method based on user-defined strategy |
| CN113032995A (en) * | 2021-03-23 | 2021-06-25 | 山东大学 | Electric power market simulation optimization and operation method, system and simulation platform |
Non-Patent Citations (1)
| Title |
|---|
| 阎啸天;武穆清;: "基于GA的网络最短路径多目标优化算法研究", 控制与决策, no. 07, 15 July 2009 (2009-07-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971422A (en) * | 2022-07-26 | 2022-08-30 | 中国华能集团清洁能源技术研究院有限公司 | Auxiliary control system and method for ten-day transaction of medium-long time-sharing transaction of electric power |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Borenstein et al. | Measuring market inefficiencies in California's restructured wholesale electricity market | |
| CN110909910B (en) | PBR-based deviation electric quantity assessment mechanism optimization design method | |
| CN108388968B (en) | Power generation plan rolling adjustment method based on pre-bidding deviation electric quantity balance mechanism | |
| CN111127137A (en) | Distributed energy P2P trading method based on centralized matching | |
| CN110659772A (en) | Optimal operation strategy determination method of power selling company under piecewise linear deviation electric quantity assessment mechanism | |
| CN112950098A (en) | Energy planning method and device based on comprehensive energy system and terminal equipment | |
| Wang et al. | Bidding strategy optimization for power generation company in carbon emission rights and electricity market | |
| CN114971899A (en) | Day-ahead, day-in and real-time market electric energy trading optimization method with new energy participation | |
| CN106779142A (en) | A kind of sale of electricity main body Contract Energy optimization method and device | |
| Müsgens et al. | Is offshore already competitive? Analyzing German offshore wind auctions | |
| CN111932293A (en) | Resource safety transaction method based on block chain | |
| CN115936756A (en) | Hydropower plant power generation control method considering power grid operation stability | |
| CN113887800A (en) | Monthly or ten-day time period transaction auxiliary decision making method and system | |
| CN111695943A (en) | Optimization management method considering floating peak electricity price | |
| CN116342176A (en) | Thermal power enterprise sectional quotation method for electric market spot electric energy transaction rule | |
| Oren | Combining financial double call options with real options for early curtailment of electricity service | |
| US20030216994A1 (en) | Historical database system for resolving energy imbalance requirements in real-time | |
| Meibom et al. | Power system models-A description of power markets and outline of market modelling in Wilmar | |
| CN111783303A (en) | Pumped storage power station quotation and report quantity determination method, system and device | |
| CN112926811A (en) | Load aggregation commercial power purchasing method considering renewable energy consumption responsibility weight | |
| CN110648012A (en) | Bidding method for demand side resource participation multi-time scale auxiliary service market | |
| CN116362828B (en) | Thermal power generating unit quotation decision method based on similarity scene and particle swarm algorithm | |
| Lolos et al. | The impact of European Structural Funds on the development of the Greek economy: A comparison of two models | |
| Cramton et al. | Eliminating the flaws in New England's reserve markets | |
| CN113919952A (en) | Daily rolling matching transaction auxiliary decision-making method and system based on psychological expected price |
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 |