CN114399345A - Financial power transmission right price prediction method and device - Google Patents
Financial power transmission right price prediction method and device Download PDFInfo
- Publication number
- CN114399345A CN114399345A CN202210297952.9A CN202210297952A CN114399345A CN 114399345 A CN114399345 A CN 114399345A CN 202210297952 A CN202210297952 A CN 202210297952A CN 114399345 A CN114399345 A CN 114399345A
- Authority
- CN
- China
- Prior art keywords
- target node
- power
- price
- financial
- electricity price
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000005611 electricity Effects 0.000 claims abstract description 231
- 238000009826 distribution Methods 0.000 claims abstract description 45
- 238000005070 sampling Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims description 34
- 150000001875 compounds Chemical class 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 22
- 238000007637 random forest analysis Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 7
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 239000013598 vector Substances 0.000 description 5
- 230000000903 blocking effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000007476 Maximum Likelihood Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000764238 Isis Species 0.000 description 1
- 241000135164 Timea Species 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Water Supply & Treatment (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for predicting the price of a financial power transmission right, and relates to the technical field of price prediction of power financial derivatives. The method comprises the following steps: firstly, obtaining historical electricity price data of a target node pair and pre-estimated market power load data of the target node pair; then, inputting the constructed prediction input characteristics into a power price prediction model, outputting to obtain a prediction power price, sampling the joint probability distribution to obtain an error sample, overlapping the prediction power price and the error sample, and determining a power price scene of the target node pair; and finally, according to the power price scene, predicting the financial power transmission right price of the target node in the financial power transmission right holding period. The method makes full use of market load information, has higher prediction precision, is suitable for different application requirements, can guide the trading behavior of a market main body in the financial transmission right market, is beneficial to improving the economic benefit of power market participants, and has good application prospect.
Description
Technical Field
The invention relates to the technical field of price prediction of power financial derivatives, in particular to a method and a device for predicting a financial transmission right price.
Background
With the deepening of the reform of the electric power system in China and the promotion of the construction of the electric power market, the basic construction of the electric power spot market in various places is completed at present. The financial power transmission right is widely applied to the mature electric power market according to Europe and America as an important electric power financial derivative, the price difference of the blocking electricity price between the market node pairs in the day before is mainly used for settlement, reasonable distribution of the blocking surplus of the electric power market can be realized, and market participation main bodies are helped to avoid blocking risks and the like. Investors of the financial transmission right can be roughly divided into two categories, one category is a hedge, the other category is an investor, the hedge needs to be configured with a certain financial transmission right to avoid the blocking risk of the hedge, and the investor wants to gain a profit through the transaction of the financial transmission right. Price prediction of financial power rights is thus an important issue in its auction and trading process.
In the related art, a method for predicting the price of the financial power transmission right is lacking.
Disclosure of Invention
The embodiment of the invention provides a method and a device for predicting a financial power transmission right price, and aims to solve the problems in the background art. In order to solve the technical problem, the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a method for predicting a price of a financial power right, where the method includes:
obtaining historical electricity price data of the target node pair and pre-estimated market power load data of the target node pair;
constructing a prediction input characteristic according to the historical electricity price data and the pre-estimated market power load data;
inputting the predicted input characteristics into a power price prediction model obtained by pre-training, and outputting to obtain the predicted power price of the target node in the financial power transmission right holding period;
obtaining a joint probability distribution of the electricity price prediction error, and sampling the joint probability distribution to obtain an error sample;
superposing the predicted electricity price and the error sample, and determining an electricity price scene of the target node pair;
and determining the financial power transmission right type of the target node pair, and predicting the financial power transmission right price of the target node pair in the financial power transmission right holding period according to the power price scene.
Optionally, the target node pair includes a first target node and a second target node, the electricity price prediction model includes a first target node electricity price prediction model and a second target node electricity price prediction model, and the electricity price prediction model is obtained by training through the following steps:
obtaining sample historical power price data and sample historical market power load data of a first target node and sample historical power price data and sample historical market power load data of a second target node;
the sample historical power price data and the sample historical market power load data of the first target node, and the sample historical power price data and the sample historical market power load data of the second target node are respectively structured according to a sample financial power transmission right holding period to obtain a first prediction input characteristic sample of the first target node and a second prediction input characteristic sample of the second target node;
training a preset first random forest model according to the first prediction input feature sample to obtain a first target node electricity price prediction model and a historical electricity price prediction sequence of the first target node electricity price prediction model;
and training a preset second random forest model according to the second prediction input characteristic sample to obtain a second target node electricity price prediction model and a historical electricity price prediction sequence of the second target node electricity price prediction model.
Optionally, the step of obtaining a joint probability distribution of the electricity price prediction error comprises:
calculating a historical electricity price prediction error sequence of the first target node according to the historical electricity price prediction sequence of the first target node electricity price prediction model and the sample historical electricity price data of the first target node;
calculating a historical electricity price prediction error sequence of the second target node according to the historical electricity price prediction sequence of the electricity price prediction model of the second target node and the sample historical electricity price data of the second target node;
and modeling the historical electricity price prediction error sequence of the first target node and the historical electricity price prediction error sequence of the second target node based on the multivariate Gaussian distribution to obtain the joint probability distribution of the electricity price prediction errors.
Optionally, the step of constructing the predicted input features according to the historical electricity price data and the estimated market power load data comprises:
according to the financial power transmission right holding period, the historical power price data and the estimated market power load data of the first target node are normalized, and a first prediction input characteristic is constructed;
in the formula (I), the compound is shown in the specification,
for the first predicted input feature(s),
the historical electricity price data of the first target node after the regularization processing,
the estimated market power load data of the first target node after the regularization processing,
is a first one of the target nodes, and,
numbering the historical electricity price data according to the time intervals after the financial transmission right holding period is regular;
according to the financial power transmission right holding period, the historical power price data and the estimated market power load data of the second target node are normalized, and a second prediction input characteristic is constructed;
in the formula (I), the compound is shown in the specification,
for the purpose of the second prediction of the input features,
the historical electricity price data of the second target node after the regularization processing,
the estimated market power load data of the second target node after the regularization processing,
is the second target node of the network, and is,
and numbering the historical electricity price data according to the time intervals after the financial transmission right holding period is regulated.
Optionally, the step of inputting the predicted input features into a power price prediction model obtained through pre-training, and outputting the predicted power price of the target node pair in the financial power transmission right holding period includes:
inputting the first prediction input characteristic into a first target node electricity price prediction model, and outputting to obtain the predicted electricity price of the first target node in the financial transmission right holding period;
and inputting the second prediction input characteristic into a second target node electricity price prediction model, and outputting to obtain the predicted electricity price of the second target node in the financial power transmission right holding period.
Optionally, the step of sampling the joint probability distribution to obtain an error sample comprises:
determining the sampling times of error sampling;
and sampling the joint probability distribution based on the sampling times to obtain an error sample of the first target node and an error sample of the second target node.
Optionally, the step of superimposing the predicted electricity price and the error sample, and determining the electricity price scenario of the target node pair includes:
superposing the error sample of the first target node and the predicted power price of the first target node in the financial power transmission right holding period to determine a power price scene of the first target node;
in the formula (I), the compound is shown in the specification,
for the electricity rate scenario of the first target node,
for the predicted price of electricity for the first target node during the period of possession of the financial power transfer right,
is an error sample of the first target node,
the sampling times are;
superposing the error sample of the second target node with the predicted power price of the second target node in the financial power transmission right holding period to determine a power price scene of the second target node;
in the formula (I), the compound is shown in the specification,
for the electricity rate scenario of the second target node,
transferring power to finance for second target nodeThe predicted electricity prices during the holding period,
is an error sample for the second target node,
the sampling times are;
and determining the electricity price scene of the target node pair according to the electricity price scene of the first target node and the electricity price scene of the second target node.
Optionally, the step of determining the type of the financial power transmission right of the target node pair, and predicting the financial power transmission right price of the target node pair in the financial power transmission right holding period according to the power price scenario includes:
if the obligation type financial power transmission right of the power price scene is used, the calculation formula of the target node on the predicted price of the financial power transmission right in the financial power transmission right holding period is as follows:
if the obligation type financial power transmission right of the power price scene is used, the calculation formula of the target node on the predicted price of the financial power transmission right in the financial power transmission right holding period is as follows:
in the formula (I), the compound is shown in the specification,
the price is predicted for the financial power right,
in order to finance the target capacity of the power transmission right,
in order to maintain the period of financial power transmission rights,
in order to be able to count the number of samples,
is the maximum number of samples.
A second aspect of an embodiment of the present invention provides an implant safe area generating device, including:
the data acquisition module is used for acquiring historical electricity price data of the target node pair and pre-estimated market power load data of the target node pair;
the data construction module is used for constructing a prediction input characteristic according to the historical electricity price data and the pre-estimated market power load data;
the power price prediction module is used for inputting the prediction input characteristics into a power price prediction model obtained by pre-training and outputting the prediction power price of the target node pair in the financial power transmission right holding period;
the sampling module is used for obtaining the joint probability distribution of the electricity price prediction error and sampling the joint probability distribution to obtain an error sample;
the data processing module is used for superposing the predicted electricity price and the error sample and determining an electricity price scene of the target node pair;
and the financial power transmission right prediction module is used for determining the financial power transmission right type of the target node pair and predicting the financial power transmission right price of the target node pair in the financial power transmission right holding period according to the power price scene.
Optionally, the electricity price prediction module comprises:
the first power price prediction submodule is used for inputting the first prediction input characteristic into the first target node power price prediction model and outputting the power price to obtain the predicted power price of the first target node in the financial power transmission right holding period;
and the second power price prediction submodule is used for inputting the second prediction input characteristic into the second target node power price prediction model and outputting the power price to obtain the predicted power price of the second target node in the financial power transmission right holding period.
The embodiment of the invention has the following advantages: obtaining historical power price data of a target node pair and estimated market power load data of the target node pair, constructing a prediction input feature according to the historical power price data and the estimated market power load data, inputting the prediction input feature into a power price prediction model obtained through pre-training, outputting the prediction power price of the target node pair in a financial power transmission right holding period, obtaining joint probability distribution of power price prediction errors of the target node pair, sampling the joint probability distribution, obtaining an error sample, superposing the prediction power price and the error sample, determining a power price scene of the target node pair, determining a financial power transmission right type of the target node pair, and predicting the financial power transmission right price of the target node pair in the financial power transmission right holding period according to the power price scene. The invention fully utilizes market load information, and uses the random forest model to predict the electricity price, thereby obtaining higher precision. In addition, the price of the financial power transmission right is predicted by using the multivariate Gaussian distribution and scene sampling method, the prices of different types of financial power transmission rights of the target node pair can be predicted, the method is suitable for different actual demands, and based on the predicted financial power transmission right price, the trading behavior of a market main body in the financial power transmission right market can be guided, so that the economic benefit of power market participants can be improved, and the method has important practical significance and good application prospect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating the steps of a method for forecasting the price of a financial power right according to an embodiment of the present invention;
fig. 2 is a block diagram of an apparatus for predicting a price of a financial power right according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Interpretation of terms:
1) random forest regression model training technology: and constructing input features and output results of the model based on certain historical data, and obtaining a group of better random forest models through training and cross validation so as to fit the relationship between the input features and the output.
2) Maximum likelihood estimation techniques: the technology can estimate the parameters of potential distribution from historical observed values, and particularly in the invention, the maximum likelihood estimation technology is used for estimating the parameters of multivariate Gaussian distribution from the prediction error of the electricity price point to realize the modeling of joint probability prediction.
In the related art, although there is a method of predicting the electricity rate in a short period of time in a specific area, there is no method of predicting the financial power transmission right between areas.
Based on this, the inventor proposes the inventive concept of the present invention: and determining the predicted price of the inter-area financial power transmission right by combining market load information according to the medium-term and long-term predicted power price between the financial power transmission right areas to be predicted.
In a possible embodiment, first, the electricity price prediction model of the present invention is obtained by training the following steps:
step S100-1: obtaining sample historical power rate data and sample historical market power load data of a first target node and sample historical power rate data and sample historical market power load data of a second target node.
Step S100-2: and respectively carrying out normalization processing on the sample historical power price data and the sample historical market power load data of the first target node, and the sample historical power price data and the sample historical market power load data of the second target node according to the sample financial power transmission right holding period to obtain a first prediction input characteristic sample of the first target node and a second prediction input characteristic sample of the second target node.
Step S100-3: training a preset first random forest model according to the first prediction input feature sample to obtain a first target node electricity price prediction model and a historical electricity price prediction sequence of the first target node electricity price prediction model;
step S100-4: and training a preset second random forest model according to the second prediction input characteristic sample to obtain a second target node electricity price prediction model and a historical electricity price prediction sequence of the second target node electricity price prediction model.
In the embodiments of steps S100-1 to S100-4, to create the power rate prediction models of the first target node and the second target node, sample historical power rate data and sample historical market power load data of the first target node and the second target node need to be obtained, where the sample historical load data is used as a sample
And (4) showing. With sample financial transmission entitlement periods equal to
For example, the sample historical electricity price data and the sample historical market power load data are normalized and averaged according to the sample financial transmission right holding time, and a predicted input characteristic sample is constructed. The historical electricity price data samples and the historical market power load data samples are according to
The regular average treatment is carried out for one day, the treatment process is shown in formulas 1 to 4, and the treated data are as follows:
for the first target node
To say, it is the first
The vector for input characteristics of each time interval unit is shown in formula 5:
namely, it is
A feature sample is input for the first prediction. Similarly, for the second target node
To say, it is the first
The vector for the input features of each time interval unit is shown in equation 6:
namely, it is
The feature samples are input for the second prediction.
As an example, consider a sample financial power transfer rightThe holding time of (1) is x years and 6 months, and the holding time of the sample is
，
In one month, when the current time is at the beginning of 6 months in x years, acquiring input historical electricity price data corresponding to a first target node and a second target node, and forming a training data set through regular averaging for constructing a financial power transmission right price prediction model between the first target node and the second target node in 6 months in x years. The training data set comprises power price average values and input feature vectors of a plurality of historical time period units, for example, the input feature vector of the time period unit corresponding to the x 5 months of the year comprises the power price average values of the x 4 months, the 3 months, the 2 months, the 1 month and the x-1 year 12 months, namely historical power price data of a total of 5 time periods, and historical market power load data of the first target node and the second target node at the x 5 months of the year; the input feature vector of the corresponding time interval unit of the x-year 4-month comprises the average value of the electricity prices of the x-year 3-month, 2-month, 1-month, x-1-year 12-month and 11-month, and the historical market power load data of the first target node and the second target node of the x-year 4-month. In the invention, the number of the selected historical electricity price data is not limited, but the greater the number of the selected historical electricity price data is, the more the data used as a sample in the training process is, and the higher the accuracy of the model is generally.
Training and cross-verifying the random forest model by using the normalized historical electricity price data of the first target node sample and the sample historical market power load data to obtain a first target node electricity price prediction model and a historical electricity price prediction sequence of the first target node electricity price prediction model predicted based on the first target node electricity price prediction model. Namely, the electricity rate prediction sequence of the first target node for each history period unit. Similarly, training and cross-verifying the random forest model by using the normalized second target node historical electricity price data samples and historical market power load data samples to obtain a second target node electricity price prediction model and a historical electricity price prediction sequence of the second target node electricity price prediction model predicted based on the second target node electricity price prediction model. Namely, the electricity rate prediction sequence of the second target node for each history period unit.
In one possible embodiment, the step of obtaining a joint probability distribution of the electricity price prediction error comprises:
calculating a historical electricity price prediction error sequence of the first target node according to the historical electricity price prediction sequence of the first target node electricity price prediction model and the sample historical electricity price data of the first target node;
calculating a historical electricity price prediction error sequence of the second target node according to the historical electricity price prediction sequence of the electricity price prediction model of the second target node and the sample historical electricity price data of the second target node;
and modeling the historical electricity price prediction error sequence of the first target node and the historical electricity price prediction error sequence of the second target node based on the multivariate Gaussian distribution to obtain the joint probability distribution of the electricity price prediction errors.
In this embodiment, continuing with the data in the above embodiment as an example, when the historical power rate prediction sequence of the power rate prediction model of the first target node is obtained, it is compared with the actual power rate sequence of the first target node, for example, after the power rate prediction sequence of the first target node in x year and 5 months predicted by the power rate prediction model of the first target node is obtained, it is compared with the actual power rate sequence of the first target node in x year and 5 months. Similarly, when the historical electricity price prediction sequence of the second target node electricity price prediction model is obtained, the historical electricity price prediction sequence is compared with the actual electricity price sequence, for example, after the electricity price prediction sequence of the second target node in x year and 5 month predicted by the second target node electricity price prediction model is obtained, the historical electricity price prediction sequence is compared with the actual electricity price sequence of the second target node in x year and 5 month. Namely the electricity price prediction sequence of the first target node
And a power rate prediction sequence of a second target node
Electricity price real sequence with first target node respectively
And the electricity price real sequence of the second target node of the sequence
And performing difference calculation to obtain a historical electricity price prediction error sequence of the first target node and the second target node, wherein the calculation is shown in formulas 7 to 8:
modeling the probability distribution of two groups of error sequences by using multivariate Gaussian distribution, and estimating the position parameters of the multivariate Gaussian distribution by using a maximum likelihood method
Sum covariance matrix
I.e. using a multivariate Gaussian distribution
To characterize the joint probability distribution of the errors.
After a power price prediction model is trained and joint probability distribution of errors is determined, the embodiment of the invention provides a method for predicting a financial power right price, and referring to fig. 1, fig. 1 shows a flow chart of steps of the method for predicting the financial power right price, and the method comprises the following steps:
step S101: and obtaining historical electricity price data of the target node pair and pre-estimated market power load data of the target node pair.
When a user determines his needs forecast based on his specific application requirementsWhen the target finance power transmission right is met, the node pair to be predicted is determined
And
and (6) finally. The term of the financial power transmission right refers to the prediction node
To the node
When the financial power transmission right is predicted, the time length of days held by the user is also the time length for predicting the price of the financial power transmission right. The estimated power load data refers to estimated data of the usage amount of the electric energy of each time period of each day, which is issued by the relevant power departments, namely load prediction data. Setting the financial power transmission right to be predicted as a node
To the node
Capacity of
MW（
>0) The financial transmission right holding period is
Tian (A)
Is an integer, typically 30 or 90). Given acquirable historical electricity price data
Day (suppose)
Is that
Integer multiple of) and assume 24 periods per day. To be provided with
，…, 
Representing nodes
In history
Electricity price at each time of day
,…,
Representing nodes
In history
Electricity prices at various times of day, wherein
The number of the day is the number of the day,
=1,…, 
corresponding to the number of days in the history,
=
+1,…, 
+ 
corresponding to the financial transmission right holding period to be predicted. For load prediction data
And (4) showing. As an example, if the user needs to predict the financial power transmission right with capacity of 1000MW and 30-day holding period from Sichuan to Guangdong, the node is
Is Sichuan node
And if the number is the Guangdong, acquiring the electricity price data of each sub-period of each day in 30 days of Sichuan and the electricity price data of each sub-period of each day in 30 days of the Guangdong, and acquiring the estimated power load data of the Sichuan and the Guangdong within 30 days in the future. The historical electricity price data in 30 days refers to electricity price data 30 days before the current time, the financial power transmission right holding period of 30 days refers to 30 days after the current time, and the estimated power load data in 30 days in the future refers to power load data 30 days after the current time.
Step S102: and constructing a prediction input characteristic according to the historical electricity price data and the pre-estimated market power load data.
Continuing the above embodiment
Is Sichuan node
For example, the Guangdong. When acquiring the node
And node
After the respective historical electricity price data and the estimated market power load data are obtained, because various adopted time units are different, corresponding data processing needs to be carried out on the historical electricity price data and the estimated market power load data, and nodes are constructed on the basis of the processed data
And node
The respective predicted input features.
Step S103: and inputting the predicted input characteristics into a power price prediction model obtained by pre-training, and outputting to obtain the predicted power price of the target node in the financial power transmission right holding period.
After the input characteristics of the node pairs are constructed, the predicted electricity price of the target node pairs in the financial transmission right holding period needs to be determined according to the input characteristics, so that the constructed predicted input characteristics are input into a pre-trained electricity price prediction model, and the predicted electricity price of the target node pairs in the financial transmission right holding period is obtained, wherein the predicted electricity price is a medium-long predicted electricity price.
Step S104: and obtaining the joint probability distribution of the electricity price prediction error, and sampling the joint probability distribution to obtain an error sample.
Joint probability distribution for electricity price prediction error
And sampling is carried out, so that error samples of multiple times of sampling are obtained.
Step S105: and superposing the predicted electricity price and the error sample, and determining the electricity price scene of the target node pair.
Step S106: and determining the financial power transmission right type of the target node pair, and predicting the financial power transmission right price of the target node pair in the financial power transmission right holding period according to the power price scene.
And after the financial power transmission right type of the target node pair is determined, calculating a financial power transmission right price prediction result based on the node pair power price scene. In the embodiment, a financial power transmission right price prediction method based on a random forest and multivariate Gaussian distribution is established for the financial power transmission right price prediction problem, compared with the existing method, the method makes full use of market load information, uses a random forest model to predict the electricity price, can obtain higher precision, and uses the multivariate Gaussian distribution and scene sampling method to predict the price of the financial power transmission right, so that the practical problem of prediction of different types of financial power transmission right prices can be solved, and the method is suitable for different actual demands. By applying the method, different types of financial transmission right prices of the target node pair can be predicted, the trading behavior of the market main body in the financial transmission right market can be guided, the economic benefit of the power market participant can be improved, and therefore the method has important practical significance and good application prospect.
In one possible embodiment, the step of constructing the prediction input feature according to the historical electricity price data and the estimated market power load data specifically comprises the following steps:
step S102-1: according to the financial power transmission right holding period, the historical power price data and the estimated market power load data of the first target node are normalized, and a first prediction input characteristic is constructed;
in the present embodiment, the historical power rate data of the first target node is averaged for each financial power transmission right holding period. The specific process is shown as a formula 9;
in the formula (I), the compound is shown in the specification,
the historical electricity price data of the first target node after the regularization processing,
is a first one of the target nodes, and,
is the period number.
The historical electricity price data of the first target node which is not subjected to the regulation processing,
is numbered by day, and the financial transmission right holding period is
The acquired historical electricity price data of the first target node are shared
And (5) day.
=1,2,…, 
；
。
And carrying out average processing on the estimated market power load data of the first target node according to the financial power transmission right holding period. The specific process is shown as a formula 10;
in the formula (I), the compound is shown in the specification,
the estimated market power load data of the first target node after the regularization processing,
is a first one of the target nodes, and,
is the period number.
The estimated market power load data for the first target node that has not been subjected to the regularization process,
is numbered by day, and the financial transmission right holding period is
The acquired historical electricity price data of the first target node are shared
And (5) day.
=1,2,…, 
；
。
After the historical electricity price data and the estimated market power load data of the first target node are normalized, the time interval can be set to be
+1 is the first prediction input characteristic as shown in equation 11.
In the formula (I), the compound is shown in the specification,
is a period of time
A first predictive input feature of +1,
the time period after the normalization treatment is
+1 historical electricity price data for the first target node,
the time period after the normalization treatment is
+1 estimated market power load data for the first target node,
is a period of time
+1 of the number of first destination nodes,
numbering the historical electricity price data according to the regular time intervals of the financial transmission right holding period, namely
。
Step S102-2: and according to the financial power transmission right holding period, the historical power price data and the estimated market power load data of the second target node are normalized, and a second prediction input characteristic is constructed.
In the present embodiment, the historical power rate data of the second target node is averaged in accordance with the financial power transmission right holding period. The specific process is shown as formula 12;
in the formula (I), the compound is shown in the specification,
the historical electricity price data of the second target node after the regularization processing,
is the second target node of the network, and is,
is the period number.
The historical electricity price data of the second target node which is not subjected to the regulation processing,
is numbered by day, and the financial transmission right holding period is
The acquired historical electricity price data of the first target node are shared
And (5) day.
=1,2,…, 
；
。
And averagely processing the estimated market power load data of the second target node according to the financial power transmission right holding period. The specific process is shown as formula 13;
in the formula (I), the compound is shown in the specification,
the estimated market power load data of the second target node after the regularization processing,
is the second target node of the network, and is,
is the period number.
The estimated market power load data for the second target node that has not been subjected to the regularization process,
is numbered by day, and the financial transmission right holding period is
The acquired historical electricity price data of the first target node are shared
And (5) day.
=1,2,…, 
；
。
After the historical electricity price data and the estimated market power load data of the second target node are normalized, the time interval can be set as
+1 is the second prediction input characteristic as shown in equation 14.
In the formula (I), the compound is shown in the specification,
for the purpose of the second prediction of the input features,
the time period after the normalization treatment is
+1 historical electricity price data for the second target node,
the time period after the normalization treatment is
+1 estimated market power load data for the second target node,
for a time period that is the second target node,
numbering the historical electricity price data according to the regular time intervals of the financial transmission right holding period, namely
。
In a feasible implementation mode, inputting the predicted input features into a power price prediction model obtained by pre-training, and outputting to obtain the predicted power price of the target node in the financial power transmission right holding period specifically comprises the following steps:
step S103-1: inputting the first prediction input characteristic into a first target node electricity price prediction model, and outputting to obtain the predicted electricity price of the first target node in the financial transmission right holding period;
step S103-2: and inputting the second prediction input characteristic into a second target node electricity price prediction model, and outputting to obtain the predicted electricity price of the second target node in the financial power transmission right holding period.
In an embodiment of steps S103-1 to S103-2, the first predicted input feature is
And a second predictive input feature
Respectively inputting the power rates into a first target node power rate prediction model and a second target node power rate prediction model which are trained in advance to obtain a first target node
Forecasting electricity prices during financial transmission rights holding periods
And a second target node
Forecasting electricity prices during financial transmission rights holding periods
。
In one possible embodiment, the step of sampling the joint probability distribution to obtain error samples comprises:
step S104-1: determining the sampling times of error sampling;
step S104-2: and sampling the joint probability distribution based on the sampling times to obtain an error sample of the first target node and an error sample of the second target node.
In the embodiment of steps S104-1 to S104-2, the maximum number of sampling times of the error sample is acquired
Number of samples of error samples
The larger the error, the higher the accuracy of the sampling for the error, and in an embodiment, the larger the error is
If the power price is not less than 1000, then 1000 times of error sampling is carried out, and the joint probability distribution of the power price prediction error is obtained
Sampling to obtain
=1000 sets of error samples, record
。
Is an error sample of the first target node,
is an error sample for the second target node.
In a possible implementation, the step of superimposing the predicted electricity price and the error sample, and determining the electricity price scenario of the target node pair specifically includes the following steps:
step S105-1: and overlapping the error sample of the first target node with the predicted power price of the first target node in the financial power transmission right holding period to determine the power price scene of the first target node.
Step S105-2: and superposing the error sample of the second target node with the predicted power price of the second target node in the financial power transmission right holding period to determine the power price scene of the second target node.
Step S105-3: and determining the electricity price scene of the target node pair according to the electricity price scene of the first target node and the electricity price scene of the second target node.
In the embodiment of steps S105-1 to S105-3, the predicted power rate of the first target node in the financial power transmission right holding period and the predicted power rate of the second target node in the financial power transmission right holding period are superimposed with the error sample to obtain a node-to-node power rate scenario, which is calculated as shown in the following formulas 15 to 16:
in the formula (I), the compound is shown in the specification,
for the electricity rate scenario of the first target node,
for the predicted price of electricity for the first target node during the period of possession of the financial power transfer right,
is an error sample for the first target node.
For the electricity rate scenario of the second target node,
for the predicted price of electricity for the second target node during the period of possession of the financial power transfer right,
is an error sample for the second target node. Then
For a node to the electricity price scenario,
=1,2,…,
。
in a possible implementation manner, determining the type of the financial power transmission right of the target node pair, and predicting the predicted price of the financial power transmission right of the target node pair in the financial power transmission right holding period according to the power price scenario specifically includes the steps of:
step S106-1: if the obligation type financial power transmission right of the power price scene is used, the calculation formula of the target node on the predicted price of the financial power transmission right in the financial power transmission right holding period is as follows:
step S106-2: if the obligation type financial power transmission right of the power price scene is used, the calculation formula of the target node on the predicted price of the financial power transmission right in the financial power transmission right holding period is as follows:
in the embodiment of steps S106-1 to S106-2, the type of the financial power right is a basic attribute of the financial power right, and is divided into an obligation-type financial power right and an option-type financial power right. In the formula (I), the compound is shown in the specification,
the price is predicted for the financial power right,
in order to be able to count the number of samples,
is the maximum number of samples.
For financial lossThe target capacity of the electricity right is,
is a financial transmission right holding period.
The embodiment of the invention also provides a financial power transmission right price prediction device, and referring to fig. 2, a functional module diagram of the financial power transmission right price prediction device of the invention is shown, and the device can comprise the following modules:
the data acquisition module 201 is configured to acquire historical electricity price data of the target node pair and pre-estimated market power load data of the target node pair;
the data construction module 202 is used for constructing a prediction input characteristic according to the historical electricity price data and the pre-estimated market power load data;
the electricity price prediction module 203 is used for inputting the prediction input characteristics into a pre-trained electricity price prediction model and outputting the prediction input characteristics to obtain the predicted electricity price of the target node in the financial power transmission right holding period;
the sampling module 204 is configured to obtain a joint probability distribution of the electricity price prediction error, and sample the joint probability distribution to obtain an error sample;
the data processing module 205 is used for superposing the predicted electricity price and the error sample and determining an electricity price scene of the target node pair;
and the financial power transmission right prediction module 206 is configured to determine a financial power transmission right type of the target node pair, and predict a financial power transmission right price of the target node pair in a financial power transmission right holding period according to the power price scenario.
In one possible implementation, the data construction module 202 includes:
the first construction submodule is used for conducting normalization processing on historical power price data of the first target node and estimated market power load data according to the financial power transmission right holding period and constructing a first prediction input characteristic;
in the formula (I), the compound is shown in the specification,
for the first predicted input feature(s),
the historical electricity price data of the first target node after the regularization processing,
the estimated market power load data of the first target node after the regularization processing,
is a first one of the target nodes, and,
numbering the historical electricity price data according to the time intervals after the financial transmission right holding period is regular;
the second construction submodule is used for performing normalization processing on the historical power price data of the second target node and the estimated market power load data according to the financial power transmission right holding period and constructing a second prediction input characteristic;
in the formula (I), the compound is shown in the specification,
for the purpose of the second prediction of the input features,
the historical electricity price data of the second target node after the regularization processing,
the estimated market power load data of the second target node after the regularization processing,
is the second target node of the network, and is,
and numbering the historical electricity price data according to the time intervals after the financial transmission right holding period is regulated.
In one possible embodiment, the electricity price prediction module 203 includes:
the first power price prediction submodule is used for inputting the first prediction input characteristic into the first target node power price prediction model and outputting the power price to obtain the predicted power price of the first target node in the financial power transmission right holding period;
and the second power price prediction submodule is used for inputting the second prediction input characteristic into the second target node power price prediction model and outputting the power price to obtain the predicted power price of the second target node in the financial power transmission right holding period.
In one possible implementation, the sampling module 204 includes:
a determination submodule for determining the number of sampling times of the error samples;
and the sampling submodule is used for sampling the joint probability distribution of the electricity price prediction error based on the sampling times to obtain an error sample of the first target node and an error sample of the second target node.
In one possible implementation, the data processing module 205 includes:
the first calculation submodule is used for superposing the error sample of the first target node and the predicted power price of the first target node in the financial power transmission right holding period to determine the power price scene of the first target node;
in the formula (I), the compound is shown in the specification,
for the electricity rate scenario of the first target node,
is the first orderThe forecast price of the bidding node in the financial transmission right holding period,
is an error sample of the first target node,
the sampling times are;
the second calculation submodule is used for superposing the error sample of the second target node and the predicted power price of the second target node in the financial power transmission right holding period to determine the power price scene of the second target node;
in the formula (I), the compound is shown in the specification,
for the electricity rate scenario of the second target node,
for the predicted price of electricity for the second target node during the period of possession of the financial power transfer right,
is an error sample for the second target node,
the sampling times are;
and the third calculation submodule is used for determining the electricity price scene of the target node pair according to the electricity price scene of the first target node and the electricity price scene of the second target node.
In one possible implementation, financial power right prediction module 206 includes:
the first prediction submodule is used for calculating the predicted price of the financial power transmission right in the financial power transmission right holding period by the target node if the obligation type financial power transmission right of the power price scene is as follows:
the second prediction submodule is used for calculating the predicted price of the financial power transmission right of the target node in the financial power transmission right holding period according to the following formula if the obligation type financial power transmission right of the power price scene is:
in the formula (I), the compound is shown in the specification,
the price is predicted for the financial power right,
in order to finance the target capacity of the power transmission right,
in order to maintain the period of financial power transmission rights,
in order to be able to count the number of samples,
is the maximum number of samples.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. "and/or" means that either or both of them can be selected. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method and the device for predicting the price of the financial power transmission right provided by the invention are described in detail, a specific example is applied in the method to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for predicting a financial power right price, the method comprising:
obtaining historical electricity price data of a target node pair and pre-estimated market power load data of the target node pair;
constructing a prediction input characteristic according to the historical electricity price data and the pre-estimated market power load data;
inputting the prediction input characteristics into a power price prediction model obtained by pre-training, and outputting to obtain the predicted power price of the target node in the financial power transmission right holding period;
obtaining a joint probability distribution of the electricity price prediction error, and sampling the joint probability distribution to obtain an error sample;
superposing the predicted electricity price and the error sample to determine an electricity price scene of the target node pair;
and determining the financial power transmission right type of the target node pair, and predicting the financial power transmission right price of the target node pair in the financial power transmission right holding period according to the power price scene.
2. The method of claim 1, wherein the target node pair comprises a first target node and a second target node, and wherein the electricity price prediction model comprises a first target node electricity price prediction model and a second target node electricity price prediction model, and wherein the electricity price prediction model is trained by:
obtaining sample historical power price data and sample historical market power load data of the first target node and sample historical power price data and sample historical market power load data of the second target node;
the sample historical power price data and the sample historical market power load data of the first target node, and the sample historical power price data and the sample historical market power load data of the second target node are respectively structured according to a sample financial power transmission right holding period to obtain a first prediction input characteristic sample of the first target node and a second prediction input characteristic sample of the second target node;
training a preset first random forest model according to the first prediction input feature sample to obtain a first target node electricity price prediction model and a historical electricity price prediction sequence of the first target node electricity price prediction model;
and training a preset second random forest model according to the second prediction input feature sample to obtain a second target node electricity price prediction model and a historical electricity price prediction sequence of the second target node electricity price prediction model.
3. The method of claim 2, wherein the step of obtaining a joint probability distribution of electricity price prediction errors comprises:
calculating a historical electricity price prediction error sequence of the first target node according to the historical electricity price prediction sequence of the first target node electricity price prediction model and the sample historical electricity price data of the first target node;
calculating a historical electricity price prediction error sequence of a second target node according to the historical electricity price prediction sequence of the second target node electricity price prediction model and the sample historical electricity price data of the second target node;
and modeling the historical electricity price prediction error sequence of the first target node and the historical electricity price prediction error sequence of the second target node based on multivariate Gaussian distribution to obtain joint probability distribution of the electricity price prediction errors.
4. The method of claim 3, wherein the step of constructing a predictive input signature based on the historical electricity price data and the projected market power load data comprises:
according to the financial power transmission right holding period, conducting normalization processing on historical power price data and estimated market power load data of the first target node, and constructing a first prediction input characteristic;
in the formula (I), the compound is shown in the specification,
for the first predicted input feature(s),
the historical electricity price data of the first target node after the regularization processing,
the estimated market power load data of the first target node after the regularization processing,
in the form of a first node of interest being a first node of interest,
date regulation for historical electricity price data according to financial transmission power rightNumbering the whole time period;
according to the financial power transmission right holding period, conducting normalization processing on the historical power price data and the estimated market power load data of the second target node, and constructing a second prediction input characteristic;
in the formula (I), the compound is shown in the specification,
for the purpose of the second prediction of the input features,
the historical electricity price data of the second target node after the regularization processing,
the estimated market power load data of the second target node after the regularization processing,
in the form of said second target node,
and numbering the historical electricity price data according to the time intervals after the financial transmission right holding period is regulated.
5. The method of claim 4, wherein the step of inputting the predicted input features into a pre-trained power rate prediction model and outputting the predicted power rates of the target node pairs in the financial power transmission right holding period comprises:
inputting the first prediction input characteristic into the first target node electricity price prediction model, and outputting to obtain the predicted electricity price of the first target node in the financial transmission right holding period;
and inputting the second prediction input characteristic into the second target node electricity price prediction model, and outputting to obtain the predicted electricity price of the second target node in the financial transmission right holding period.
6. The method of claim 4, wherein the step of sampling the joint probability distribution to obtain error samples comprises:
determining the sampling times of error sampling;
and sampling the joint probability distribution based on the sampling times to obtain an error sample of the first target node and an error sample of the second target node.
7. The method of claim 6, wherein superimposing the predicted electricity prices with the error samples, the step of determining an electricity price scenario for a target node pair comprises:
superposing the error sample of the first target node with the predicted power price of the first target node in the financial power transmission right holding period to determine a power price scene of the first target node;
in the formula (I), the compound is shown in the specification,
for the electricity rate scenario of the first target node,
for the predicted price of electricity for the first target node during the period of the financial power transfer right holding,
is an error sample of the first target node,
the sampling times are;
superposing the error sample of the second target node with the predicted power price of the second target node in the financial power transmission right holding period to determine a power price scene of the second target node;
in the formula (I), the compound is shown in the specification,
for the electricity rate scenario of the second target node,
for a predicted price of electricity for a second target node during the financial power transfer right holding period,
is an error sample for the second target node,
the sampling times are;
and determining the electricity price scene of the target node pair according to the electricity price scene of the first target node and the electricity price scene of the second target node.
8. The method of claim 7, wherein the types of financial power rights include obligation-type financial power rights and option-type financial power rights, and wherein the step of determining the type of financial power right for the target node pair, and predicting the price of the financial power right for the target node pair during the period of holding the financial power right according to the power price scenario comprises:
if the obligation type financial power transmission right of the electricity price scene is used, the calculation formula of the target node on the predicted price of the financial power transmission right in the financial power transmission right holding period is as follows:
if the obligation type financial power transmission right of the electricity price scene is used, the calculation formula of the target node on the predicted price of the financial power transmission right in the financial power transmission right holding period is as follows:
in the formula (I), the compound is shown in the specification,
the price is predicted for the financial power right,
in order to finance the target capacity of the power transmission right,
in order to maintain the period of financial power transmission rights,
in order to be able to count the number of samples,
is the maximum number of samples.
9. An apparatus for predicting a financial power right price, the apparatus comprising:
the data acquisition module is used for acquiring historical electricity price data of a target node pair and pre-estimated market power load data of the target node pair;
the data construction module is used for constructing a prediction input characteristic according to the historical electricity price data and the pre-estimated market power load data;
the electricity price prediction module is used for inputting the prediction input characteristics into a pre-trained electricity price prediction model and outputting the prediction electricity price of the target node pair in the financial transmission right holding period;
the sampling module is used for obtaining the joint probability distribution of the electricity price prediction error and sampling the joint probability distribution to obtain an error sample;
the data processing module is used for superposing the predicted electricity price and the error sample and determining an electricity price scene of the target node pair;
and the financial power transmission right prediction module is used for determining the financial power transmission right type of the target node pair and predicting the financial power transmission right price of the target node pair in the financial power transmission right holding period according to the power price scene.
10. The apparatus of claim 9, wherein the electricity price prediction module comprises:
the first power price prediction submodule is used for inputting the first prediction input characteristic into the first target node power price prediction model and outputting the power price to obtain the predicted power price of the first target node in the financial power transmission right holding period;
and the second power price prediction submodule is used for inputting the second prediction input characteristic into the second target node power price prediction model and outputting the power price to obtain the predicted power price of the second target node in the financial power transmission right holding period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297952.9A CN114399345A (en) | 2022-03-25 | 2022-03-25 | Financial power transmission right price prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297952.9A CN114399345A (en) | 2022-03-25 | 2022-03-25 | Financial power transmission right price prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114399345A true CN114399345A (en) | 2022-04-26 |
Family
ID=81234856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210297952.9A Pending CN114399345A (en) | 2022-03-25 | 2022-03-25 | Financial power transmission right price prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114399345A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545790A (en) * | 2022-10-20 | 2022-12-30 | 北京宽客进化科技有限公司 | Price data prediction method and device, electronic equipment and storage medium |
-
2022
- 2022-03-25 CN CN202210297952.9A patent/CN114399345A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545790A (en) * | 2022-10-20 | 2022-12-30 | 北京宽客进化科技有限公司 | Price data prediction method and device, electronic equipment and storage medium |
| CN115545790B (en) * | 2022-10-20 | 2023-06-09 | 北京宽客进化科技有限公司 | Price data prediction method, price data prediction device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| He et al. | Joint operation mechanism of distributed photovoltaic power generation market and carbon market based on cross-chain trading technology | |
| Yassine et al. | Double auction mechanisms for dynamic autonomous electric vehicles energy trading | |
| CN112333251B (en) | Block chain consensus distributed power transaction proxy node selection method and system | |
| Anders et al. | Cost related reliability measures for power system equipment | |
| CN114399345A (en) | Financial power transmission right price prediction method and device | |
| CN113837812A (en) | Joint probability prediction method and device for node electricity price | |
| CN115334106A (en) | Microgrid transaction consensus method and system based on Q method and power grid detection and evaluation | |
| Lin et al. | Currency exchange rates prediction based on linear regression analysis using cloud computing | |
| CN109617071A (en) | Analysis method and device for power supply capacity of power distribution network and storage medium | |
| Thakur et al. | Cost analysis of blockchains-based peer to peer energy trade | |
| CN112734238A (en) | Weak-centralized production and consumption user electric quantity coordination method and system based on block chain | |
| CN107705200A (en) | Current account is layered the methods of figuring interest and device, computer equipment and storage medium | |
| Mestre et al. | The arithmetic of stepwise offer curves | |
| Fabiani et al. | Personalized incentives as feedback design in generalized Nash equilibrium problems | |
| CN116976927A (en) | Short-term electricity price prediction method, system, computer and storage medium based on deep learning | |
| CN115907194A (en) | Photovoltaic power generation power prediction method, system and product | |
| CN116049678A (en) | Feature contribution degree evaluation method, device, electronic equipment and storage medium | |
| Hakam | Market power modelling in electricity market: A critical review | |
| Wu et al. | Unveiling bidding uncertainties in electricity markets: A Bayesian deep learning framework based on accurate variational inference | |
| CN115423519A (en) | Blocking surplus allocation method and device based on Shapley value and computer equipment | |
| Tesser et al. | An oligopoly model for medium-term power planning in a liberalized electricity market | |
| CN113159926A (en) | Loan transaction repayment date determination method and device | |
| CN112633942A (en) | Park electric power system contract deviation charge calculation method, medium and equipment | |
| Leow | Pricing of swing options: A Monte Carlo simulation approach | |
| Kargarian et al. | Artificial intelligence–based loss allocation algorithm in open access environments |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220426 |
|
| RJ01 | Rejection of invention patent application after publication |