CN116777616A - Probability density distribution-based future market new energy daily transaction decision method - Google Patents
Probability density distribution-based future market new energy daily transaction decision method Download PDFInfo
- Publication number
- CN116777616A CN116777616A CN202310697884.XA CN202310697884A CN116777616A CN 116777616 A CN116777616 A CN 116777616A CN 202310697884 A CN202310697884 A CN 202310697884A CN 116777616 A CN116777616 A CN 116777616A
- Authority
- CN
- China
- Prior art keywords
- data
- transaction
- probability density
- density distribution
- 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 32
- 230000005611 electricity Effects 0.000 claims abstract description 98
- 238000013079 data visualisation Methods 0.000 claims abstract description 18
- 238000010248 power generation Methods 0.000 claims abstract description 16
- 230000003993 interaction Effects 0.000 claims abstract description 7
- 238000004140 cleaning Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 19
- 230000014759 maintenance of location Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 19
- 238000004458 analytical method Methods 0.000 abstract description 6
- 239000004973 liquid crystal related substance Substances 0.000 description 8
- 238000007619 statistical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Pure & Applied Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Technology Law (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of auxiliary decision making of the spot market transaction among provinces of new energy power generation enterprises, and discloses a probability density distribution-based spot market new energy daily transaction decision making method, which comprises the steps of firstly, obtaining data to be processed, wherein the data to be processed comprises weather forecast data, short-term power forecast data, historical actual power, power grid operation mode information and an inter-province spot transaction result; and secondly, data marking is carried out in a data visualization and man-machine interaction mode, so that data cleaning is realized. According to the future market new energy daily transaction decision method based on probability density distribution, a prediction model of key data is established through comprehensive analysis of historical data, and factors such as market rule information, electricity price prediction information, power prediction information and the like are comprehensively considered to dynamically balance benefits and risks.
Description
Technical Field
The application relates to the technical field of auxiliary decision making of spot market transaction among provinces of new energy power generation enterprises, in particular to a probability density distribution-based spot market new energy daily transaction decision making method.
Background
In 2021, 11 months, the national grid company issues "provincial power spot transaction rules (trial run)", and compared with cross-regional spot transaction and provincial spot transaction, the transaction range and the seller main body of the provincial spot transaction are enlarged, meanwhile, the transaction frequency is increased, and a bid clearing mode of bidirectional quotation, centralized matching and marginal clearing is adopted, so that the transaction mechanism is more perfect, and the transaction situation is more complex. Under the background, a new energy power generation enterprise participates in the current spot transaction between provinces, and a 96-point price curve is required to be declared. How to realize the maximization of the benefits while avoiding risks becomes a key problem to be solved by new energy power generation enterprises.
At present, the day-ahead decision-making modes of new energy power generation enterprises mainly comprise: the first method is to directly use the original power prediction data in the wind power prediction system as the declaration quantity, and declare or declare in a sectional manner based on the subjective judgment of traders on the clear electricity price; secondly, the original power prediction data is corrected manually, the corrected data is used as a declaration quantity, and a single price declaration or a segmented declaration is carried out on the basis of subjective judgment of a transactor on the electricity clearing price; and thirdly, the original power prediction data is manually corrected, the corrected data is taken as Shen Baoliang, the clear electricity price is predicted by an informatization means, and the predicted result is taken as the declaration price. The first mode ignores the deviation between the predicted power and the actual power, and has deviation assessment and trade risks of high buying and low selling; the decision level of the second mode to the trade staff is higher, lacks objective theoretical basis; the third way does not combine the decision of reporting quantity and reporting quotation organically, and it is difficult to ensure that the profit maximization can be realized for each decision.
Disclosure of Invention
The application aims to provide a spot market new energy daily transaction decision method based on probability density distribution, which aims to improve the prediction accuracy of decision key data and solve the technical problems in partial related technologies by establishing a plurality of probability density distribution models.
In order to avoid transaction risks such as deviation assessment and low-price trading caused by inaccurate power prediction, the application provides a method for deciding the daily trading of new energy sources in the provincial spot market based on probability density distribution, which solves the technical problems that the reporting scheme is narrow in scope and is difficult to realize avoiding risks and improving profits due to the fact that the prior method excessively depends on subjective judgment of trading staff, lacks analysis summary of related data and lacks rational knowledge of market supply and demand relations, comprehensively considers factors such as market supply and demand relations, power prediction deviation, electricity price prediction and the like, maximizes profits while avoiding risks, generates a format specified by a trading platform by the reporting scheme, and reduces the manual labor intensity of trading staff.
The application is realized by the following technical scheme.
A probability density distribution-based spot market new energy daily transaction decision method comprises the following steps:
step one, obtaining data to be processed, wherein the data to be processed comprises weather forecast data, short-term power forecast data, historical actual power, power grid operation mode information and provincial spot transaction success results;
step two, data marking is carried out in a data visualization and man-machine interaction mode so as to realize data cleaning;
and thirdly, respectively establishing probability density distribution models of electricity limiting retention depth, daily electricity clearing price and auxiliary service cost by using the cleaned data.
Predicting the electricity limiting retention depth, the day-ahead electricity clearing price and the auxiliary service cost of a future period based on a probability density distribution model to obtain prediction data;
and fifthly, 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 power grid operation mode information and the provincial spot transaction success results to obtain an optimal daily declaration scheme.
The application further comprises a system for making a decision on the trade before the date of the new energy of the provincial spot market based on probability density distribution, which comprises a data arrangement module, a model training module, a trade decision module, a process backtracking module, a meteorological data visualization module and a trade duplication module.
According to a further technical scheme, the data sorting module performs marking processing on data in a data visualization and man-machine interaction mode, so that data cleaning is realized.
According to a further technical scheme, the model training module is used for predicting the electricity clearing price, the auxiliary service cost, the power prediction deviation and the electricity limiting condition of the future province spot market based on historical data to obtain prediction data.
According to a further technical scheme, the transaction decision module solves the problems by taking an objective function as a solving target and based on constraint conditions according to power grid operation mode information, wind farm maintenance scheduling, contract data and prediction data to obtain an optimal future declaration scheme.
According to a further technical scheme, the process backtracking module stores the transaction decision as a transaction decision log according to the step process, and the transaction decision log comprises all decision details and results. By accessing the transaction decision log, a certain transaction decision is reviewed, so that the transaction personnel can uniformly think, and the transaction auditing, the transaction evaluation and other works can be conveniently carried out.
According to a further technical scheme, the meteorological data visualization module is used for numerical weather forecast and visually displaying meteorological prediction data through a visualization period.
According to the further technical scheme, the transaction multi-disc module carries out multi-disc calculation and display on the transaction income condition by comparing the clearing result with the actual power generation condition.
According to a further technical scheme, the meteorological data visualization module can be in the forms of a line graph, a bar graph, a thermodynamic diagram, a GL vector field diagram and the like.
The application also includes a computer device comprising: a processor; a memory for storing the processor-executable instructions; when the processor executes the executable instructions stored in the memory, the method for deciding the daily transaction of the new energy source of the provincial spot market based on the probability density distribution is realized.
The application has the beneficial effects that:
according to the future market new energy daily transaction decision-making method based on probability density distribution, the historical data is comprehensively analyzed, the prediction model of key data is established, factors such as market rule information, electricity price prediction information and power prediction information are comprehensively considered, dynamic balance is carried out between benefits and risks, an auxiliary decision-making model taking expected benefits as an objective function is established, a daily reporting scheme is formed, objectivity is higher, and consideration factors are more comprehensive.
The application relates to a daily trading decision method of new energy sources in spot market based on probability density distribution, which solves the technical problems that the reporting scheme is narrow and objective on one side, avoiding risks and improving profits are difficult to realize due to the fact that the prior method excessively depends on subjective judgment of traders, lacks analysis summary of related data and lacks rational knowledge of market supply and demand relations, realizes the maximization of profits while avoiding risks by comprehensively considering factors such as market supply and demand relations, power prediction deviation, electricity price prediction and the like, generates a format specified by a trading platform by a reporting scheme, and reduces the manual labor intensity of the traders
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained from these drawings without inventive effort for a person skilled in the art.
The application will be further described with reference to the drawings and examples.
FIG. 1 is a flow chart of a decision making method of the present application;
Detailed Description
The present application will be described in detail with reference to examples.
The probability density distribution-based future market new energy daily transaction decision method comprises the following steps:
data access, data arrangement, data visualization, model training, and transaction decision. The data access means that data such as weather forecast data, short-term power forecast data, historical actual power, power grid operation mode information, provincial spot transaction success results and the like are automatically acquired in a physical access mode, a web crawler mode and the like; the data arrangement refers to classifying and warehousing related data; the data visualization means that the data is displayed in a chart form through tools such as echorts and the like; model training is to respectively establish probability density distribution models for electricity limiting retention depth, daily electricity clearing prices and auxiliary service fees based on statistical analysis of historical data; the transaction decision is to construct an objective function and constraint conditions, calculate an optimal solution based on the constraint conditions by taking the objective function as a solution target according to a related probability density distribution model, and obtain an optimal daily declaration scheme.
In the inter-provincial spot trading decision process, wind farm power, electricity limiting level prediction and the like in the future trading period are important decision factors. In order to reduce the influence of prediction uncertainty on transaction decisions, the method establishes a probability function model of each decision factor by analyzing the frequency distribution of historical sample data, and quantifies the prediction uncertainty. From a probabilistic perspective, it is understood that the market scenario of the future transaction period is a random event whose occurrence probability is equal to the multidimensional joint probability based on factors such as electricity limit, day-ahead electricity clearing price, auxiliary service cost, etc., i.e., the market of the future period is a set of several market scenarios and their joint probabilities. By calculating expected benefits of different declared price combinations in a future market scene set, finding the price combination with the largest benefits or the price combination with the lowest average cost is the main content of the application.
The specific technical scheme is as follows:
1. based on statistical analysis of historical data, probability density distribution models are respectively built for electricity limiting retention depth, daily electricity clearing prices and auxiliary service fees.
Electricity limit retention depth model:
wherein C is Electricity limiting reserve depth Representing the limit electricity reserve depth; f (C) Electricity limiting reserve depth ) Probability density representing the limit reserve depth;
β electricity limiting reserve depth Representing the limit electricity retention depth as [ a, b ]]Probability of an interval.
And obtaining the limit electricity reserve depth probability function through differentiating and discretizing the value range of the limit electricity reserve depth.
β Electricity limiting reserve depth ＝β(C Electricity limiting reserve depth ＝C Electricity limiting reserve depth, i )(i＝1,2,......m)
Wherein, the liquid crystal display device comprises a liquid crystal display device,
C electricity limiting reserve depth, i Representing a limit reserve depth discrete value;
m represents the number of discrete values in the value interval of the electricity limiting retention depth;
0≤C electricity limiting reserve depth, i ≤1。
β Limit electricity retention depth, t ＝β t (C Electricity limiting reserve depth ＝C Electricity limiting reserve depth, i )(i＝1,2,......m)
To sum up, the probability beta of the future time limit electricity reserve depth being a certain value in the value range can be obtained Limit electricity retention depth, t 。
Current price model:
wherein C is Day-ahead clear electricity price The day-ahead clear electricity price is represented; f (C) Day-ahead clear electricity price ) Probability density representing the current price of the day-ahead;
β day-ahead clear electricity price Indicating that the current price of the solar energy is [ c, d ]]Probability of an interval.
And obtaining the daily clear electricity price probability function through differentiating and discretizing the daily clear electricity price value range.
β Day-ahead clear electricity price ＝β(C Day-ahead clear electricity price ＝C The electricity price of the current day, j )(j＝1,2,......n)
Wherein, the liquid crystal display device comprises a liquid crystal display device,
C the electricity price of the current day, j Representing a discrete value of the daily output clear electricity price;
n represents the number of discrete values in a value interval of the current clearing price before the day;
0≤C the electricity price of the current day, j Less than 10000 yuan/megawatt hour.
β The clear electricity price, t ＝β t (C Day-ahead clear electricity price ＝C The electricity price of the current day, j )(j＝1,2,......n)
To sum up, the probability beta of the current clearing price in the future within a certain value range can be obtained The clear electricity price, t 。
Auxiliary service cost model:
wherein C is Auxiliary service charge Representing auxiliary service fees; f (C) Auxiliary service charge ) A probability density representing auxiliary service charges;
β auxiliary service charge Indicating that the auxiliary service charge is in [ e, f ]]Probability of an interval.
And obtaining the auxiliary service cost probability function through differentiating and discretizing the auxiliary service cost value range.
β Auxiliary service charge ＝β(C Auxiliary service charge ＝C Auxiliary service charge, k )(k＝1,2,......r)
Wherein, the liquid crystal display device comprises a liquid crystal display device,
C auxiliary service charge, k Representing a discrete value of auxiliary service charge;
r represents the number of discrete values in the auxiliary service expense value interval;
0≤C auxiliary service charge, k 224.4 yuan/megawatt hour.
β Auxiliary service cost, t ＝β t (C Auxiliary service charge ＝C Auxiliary service charge, k )(k＝1,2,......r)
To sum up, the probability beta of the auxiliary service charge in the future being a value in the value range can be obtained Auxiliary service cost, t 。
2. Constructing a set of market scenarios at a future trade time
Observing a specific market scene based on three dimensions of day-ahead electricity clearing price, electricity limiting reservation depth and auxiliary service cost, wherein the probability of the specific market scene is beta Market scene, t 。。
β Market scene, t ＝β The clear electricity price, t ×β Limit electricity retention depth, t ×β Auxiliary service cost, t
All the specific market scenes form a future t-moment market scene set, and the probability of the market scene set is 1.
3. Transaction loss and benefit analysis calculation under specific market scene
When participating in the spot transaction between provinces, the new energy enterprises need to analyze and calculate the transaction profit and loss, and mainly conduct quantitative price analysis from three dimensions of cost, income and loss.
The cost is mainly the auxiliary service cost.
The trade benefits include high electricity price power generation revenue generation and electricity limiting revenue alleviation.
Trade losses include low electricity price power generation losses, bias check losses.
The cost, benefit and loss price analysis in the market scene set can be used for summarizing the damage and benefit of the new energy enterprises in the spot transaction among provinces, wherein the damage and benefit are respectively 'power generation damage and benefit when the power is not limited', 'power generation damage and benefit when the power is limited', 'minimum expected benefit when the power is limited', 'benefit when the power is limited and the power is not limited'. The combined application of five types of damage can express the overall damage of the new energy enterprises participating in the spot transaction among provinces.
In a specific market scene g at a future time t, selecting a certain group of price declarations to participate in the trade and be in contact, wherein the group of price returns in the specific market scene are as follows:
GL electricity limiting and hair increasing ＝(C Clear electricity price, g +C Subsidy electricity price )×(P Reporting electric power -P Limit electricity retention depth g )
EI Time-limited transaction ＝C Subsidy electricity price ×P Reporting electric power
GL Add up g ＝(GL Non-electricity-limiting time power generation )×(1-β Limit electricity, t )+(GL Electricity limiting and hair increasing -EI Time-limited transaction )×β Limit electricity, t
GL Desirably, g ＝GL Add up g ×β Market scenario = g, t
The constraint conditions are as follows: c (C) Reporting electricity price ＜C Clear electricity price, g 。
Wherein, the liquid crystal display device comprises a liquid crystal display device,
C reporting electricity price The declaration electricity price under the market scene g is represented;
C clear electricity price, g The day-ahead clear electricity price under the market scene g is represented;
C medium and long term electricity price Representing medium-and-long-term trading electricity prices;
C auxiliary service expense g Representing auxiliary service costs in market scenario g;
C subsidy electricity price Representing the subsidy electricity price;
P reporting electric power Representing wind farm declaration power in market scene g;
P limit electricity retention depth g Representing the electricity limiting reserve depth of the wind farm in the market scene g;
GL non-electricity-limiting time power generation The power generation loss when the power is not limited is represented;
GL electricity limiting and hair increasing The gain of increasing the power generation amount during the power limiting is expressed;
EI time-limited transaction Representing the lowest expected revenue for participating in the trade at the time of the limit;
GL add up g The total value of the damage and benefit in the market scene g is shown.
GL Desirably, g The expected value of damage in the market scene g is shown.
4. Solving optimal declaration price combinations
According to different market environments and competition situations, constraint conditions for solving the optimal declaration price combination are different, and the system selects the benefit maximization as an objective function.
The objective function is:
the constraint conditions are as follows: c (C) Reporting electricity price ＜C Clear electricity price, g 。
Where s represents the number of market scenarios.
And calculating the total expected value of all declared value combinations in all market scenes at the time t, and when the total expected value of the total expected value is maximum, obtaining the optimal value combination.
In order to achieve the above purpose, the application provides a system for making a decision on the daily transaction of new energy in the provincial spot market based on probability density distribution, which comprises a data arrangement module, a model training module, a transaction decision module, a process backtracking module, a meteorological data visualization module and a transaction multi-disc module.
And the data arrangement module is used for marking the data in a data visualization and man-machine interaction mode, so that the data is cleaned.
And the model training module is used for predicting the electricity discharge price, the auxiliary service cost, the power prediction deviation and the electricity limiting condition of the spot market among future provinces based on the historical data to obtain prediction data.
And the transaction decision module is used for solving the problems based on constraint conditions by taking the objective function as a solving target according to the power grid operation mode information, the wind farm maintenance scheduling, the contract data and the prediction data to obtain an optimal daily declaration scheme.
And the process backtracking module stores the transaction decision as a transaction decision log according to the step process, and comprises all decision details and results. By accessing the transaction decision log, a certain transaction decision is reviewed, so that the transaction personnel can uniformly think, and the transaction auditing, the transaction evaluation and other works can be conveniently carried out.
And the weather data visualization module is used for numerical weather forecast and visually displaying weather forecast data through a visualization period.
Alternatively, the meteorological data visualization module may take the form of a line graph, a bar graph, a thermodynamic diagram, a GL vector field diagram, or the like.
And the transaction multi-disc module performs multi-disc calculation and display on the transaction income condition by comparing the clearing result with the actual power generation condition.
To achieve the above object, the present application proposes a computer device comprising: a processor; a memory for storing the processor-executable instructions; when the processor executes the executable instructions stored in the memory, the method for deciding the daily transaction of the new energy source of the provincial spot market based on the probability density distribution is realized.
As shown in fig. 1, the method for deciding the daily transaction of new energy of inter-provincial spot market based on probability density distribution comprises the following steps:
step 1, obtaining data to be processed, wherein the data to be processed comprises weather forecast data, short-term power forecast data, historical actual power, power grid operation mode information and provincial spot transaction results;
step 2, data marking is carried out in a data visualization and man-machine interaction mode so as to clean the data;
and 3, respectively establishing probability density distribution models of electricity limiting retention depth, daily electricity clearing price and auxiliary service cost by using the cleaned data.
Step 4, predicting the electricity limiting retention depth, the day-ahead electricity clearing price and the auxiliary service cost of a future period based on the probability density distribution model to obtain prediction data;
and 5, constructing a daily declaration objective function and constraint conditions, and solving the daily declaration objective function based on the constraint conditions according to the prediction data, the power grid operation mode information and the provincial spot transaction success-to-transaction result to obtain an optimal daily declaration scheme.
According to the inter-provincial spot market new energy daily transaction decision-making method based on probability density distribution, through comprehensively analyzing historical data, a prediction model of key data is established, factors such as market rule information, electricity price prediction information and power prediction information are comprehensively considered, dynamic balance is carried out between benefits and risks, an auxiliary decision-making model taking expected benefits as an objective function is established, a daily reporting scheme is formed, objectivity is higher, and consideration factors are more comprehensive.
The above embodiments are only for illustrating the technical concept and features of the present application, and are intended to enable those skilled in the art to understand the present application and implement it without limiting the scope of the present application. All equivalent changes or modifications made in accordance with the spirit of the present application should be construed to be included in the scope of the present application.
Claims (10)
1. The utility model provides a market new energy daily transaction decision method based on probability density distribution, which is characterized by comprising the following steps:
step one, obtaining data to be processed, wherein the data to be processed comprises weather forecast data, short-term power forecast data, historical actual power, power grid operation mode information and provincial spot transaction success results;
step two, data marking is carried out in a data visualization and man-machine interaction mode so as to realize data cleaning;
thirdly, respectively establishing probability density distribution models of electricity limiting retention depth, daily electricity clearing price and auxiliary service cost by using the cleaned data;
predicting the electricity limiting retention depth, the day-ahead electricity clearing price and the auxiliary service cost of a future period based on a probability density distribution model to obtain prediction data;
and fifthly, 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 power grid operation mode information and the provincial spot transaction success results to obtain an optimal daily declaration scheme.
2. An inter-provincial spot market new energy day-ahead transaction decision-making system based on probability density distribution, comprising: the system comprises a data arrangement module, a model training module, a transaction decision module, a process backtracking module, a meteorological data visualization module and a transaction multi-disc module.
3. The inter-provincial spot-market new energy day-ahead transaction decision-making system based on probability density distribution of claim 2, wherein: and the data sorting module performs marking processing on the data in a data visualization and man-machine interaction mode to realize data cleaning.
4. The inter-provincial spot-market new energy day-ahead transaction decision-making system based on probability density distribution of claim 2, wherein: the model training module is used for predicting the electricity clearing price, the auxiliary service cost, the power prediction deviation and the electricity limiting situation of the future provincial spot market based on the historical data to obtain prediction data.
5. The inter-provincial spot-market new energy day-ahead transaction decision-making system based on probability density distribution of claim 2, wherein: and the transaction decision module is used for solving the problems based on constraint conditions by taking the objective function as a solving target according to the power grid operation mode information, the wind farm maintenance scheduling, the contract data and the prediction data to obtain an optimal daily declaration scheme.
6. The inter-provincial spot-market new energy day-ahead transaction decision-making system based on probability density distribution of claim 2, wherein: the process backtracking module stores the transaction decision as a transaction decision log according to the step process, and comprises all decision details and results. By accessing the transaction decision log, a certain transaction decision is reviewed, so that the transaction personnel can uniformly think, and the transaction auditing, the transaction evaluation and other works can be conveniently carried out.
7. The inter-provincial spot-market new energy day-ahead transaction decision-making system based on probability density distribution of claim 2, wherein: the weather data visualization module is used for numerical weather forecast and visually displaying weather forecast data through a visualization period.
8. The inter-provincial spot-market new energy day-ahead transaction decision-making system based on probability density distribution of claim 2, wherein: and the transaction multi-disc module performs multi-disc calculation and display on the transaction income condition by comparing the clearing result with the actual power generation condition.
9. The inter-provincial spot-market new energy day-ahead transaction decision-making system based on probability density distribution of claim 7, wherein: the meteorological data visualization module can take the form of a line graph, a bar graph, a thermodynamic diagram, a GL vector field diagram and the like.
10. A computer device, comprising: a processor; a memory for storing the processor-executable instructions; when the processor executes the executable instructions stored in the memory, the method for deciding the daily transaction of the new energy source of the provincial spot market based on the probability density distribution is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310697884.XA CN116777616A (en) | 2023-06-13 | 2023-06-13 | Probability density distribution-based future market new energy daily transaction decision method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310697884.XA CN116777616A (en) | 2023-06-13 | 2023-06-13 | Probability density distribution-based future market new energy daily transaction decision method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116777616A true CN116777616A (en) | 2023-09-19 |
Family
ID=87990759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310697884.XA Pending CN116777616A (en) | 2023-06-13 | 2023-06-13 | Probability density distribution-based future market new energy daily transaction decision method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116777616A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117788082A (en) * | 2024-02-26 | 2024-03-29 | 南京南自华盾数字技术有限公司 | Power market quotation decision method and system based on electricity price prediction |
-
2023
- 2023-06-13 CN CN202310697884.XA patent/CN116777616A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117788082A (en) * | 2024-02-26 | 2024-03-29 | 南京南自华盾数字技术有限公司 | Power market quotation decision method and system based on electricity price prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11699198B2 (en) | Methods and systems for machine-learning for prediction of grid carbon emissions | |
| Wu et al. | An integrated decision-making model for sustainable photovoltaic module supplier selection based on combined weight and cumulative prospect theory | |
| CN111028004A (en) | Market assessment analysis method based on big data technology | |
| CN112561730A (en) | Power supply service analysis method based on double-layer clustering and fuzzy comprehensive evaluation | |
| CN114943565A (en) | Electric power spot price prediction method and device based on intelligent algorithm | |
| CN116777616A (en) | Probability density distribution-based future market new energy daily transaction decision method | |
| CN111738854A (en) | New energy spot transaction decision-making data service system based on cloud computing | |
| Yi et al. | Managers' overconfidence, risk preference, herd behavior and non-efficient investment | |
| CN114254916A (en) | Multi-dimensional supplier risk real-time early warning method with power grid service characteristics | |
| Chen et al. | Toward future information market: An information valuation paradigm | |
| CN116757717A (en) | Method, device, equipment, medium and product for evaluating electric carbon market coupling operation | |
| Dhavale et al. | Integrating carbon market uncertainties into a sustainable manufacturing investment decision: A Bayesian NPV approach | |
| Cui | Iot financial management system for energy enterprise management risk and prevention and control strategy under the background of double carbon | |
| CN117236532B (en) | Load data-based electricity consumption peak load prediction method and system | |
| Chaoqun et al. | Evaluating the impact of uncertainty and risk on the operational efficiency of credit business of commercial banks in China based on dynamic network DEA and Malmquist Index Model | |
| Xing et al. | Supplier evaluation model based on entropy-TOPSIS and 0-1 programming algorithm | |
| Schlör et al. | MEASURING THE SOCIAL WELFARE OF A SOLAR POWER PLANT IN WEST AFRICA-A SOCIAL RETURN ON INVESTMENT (SROI) MODEL | |
| CN113191807B (en) | Natural gas customer rating system and method | |
| Gu et al. | Judging the True Health of Finance Institutions Based on Risk Behavior and Operation Performance | |
| Chen | Are China Green Bond Issuer Financing Efficient in Recent Years?-A Comparative Industry Study from DEA Perspective | |
| CN117788082A (en) | Power market quotation decision method and system based on electricity price prediction | |
| Peng et al. | DCGAN-Based Power Trading Market Dispatch Model Design | |
| Mokoena | The influence of continuous electricity supply on selected commercial customers in Klerksdorp | |
| CN115619072A (en) | Comprehensive benefit evaluation method and device for comprehensive energy network | |
| Li et al. | A New Approach to Assess Climate Change Risk in Coal-Power Generation Sector |
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 |