CN113807593A - Data quantity and data quality prediction method and system based on power dispatching - Google Patents

Data quantity and data quality prediction method and system based on power dispatching Download PDF

Info

Publication number
CN113807593A
CN113807593A CN202111109538.2A CN202111109538A CN113807593A CN 113807593 A CN113807593 A CN 113807593A CN 202111109538 A CN202111109538 A CN 202111109538A CN 113807593 A CN113807593 A CN 113807593A
Authority
CN
China
Prior art keywords
data
power scheduling
prediction
data quality
requirement information
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.)
Granted
Application number
CN202111109538.2A
Other languages
Chinese (zh)
Other versions
CN113807593B (en
Inventor
刘之亮
陈东
崔竞时
吴辰晔
赵晨
张然
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Power Grid Co Ltd
Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Original Assignee
Guangdong Power Grid Co Ltd
Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Power Grid Co Ltd, Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd filed Critical Guangdong Power Grid Co Ltd
Priority to CN202111109538.2A priority Critical patent/CN113807593B/en
Publication of CN113807593A publication Critical patent/CN113807593A/en
Application granted granted Critical
Publication of CN113807593B publication Critical patent/CN113807593B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a data quantity and data quality prediction method and system based on power dispatching, and relates to the technical field of data analysis. The method comprises the following steps: acquiring preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data; inputting the preset data requirement information into a data relation mapping model to obtain mapping relation information; the mapping relation information comprises the target data quantity and the target data quality. The user only needs to input preset data requirement information, and the mapping relation information can be obtained through the data relation mapping model constructed in advance, so that the quantity and the quality of data to be purchased can be obtained under the condition that the accuracy of the result and the acceptable error range are clear.

Description

Data quantity and data quality prediction method and system based on power dispatching
Technical Field
The invention relates to the technical field of data analysis, in particular to a data quantity and data quality prediction method and system based on power dispatching.
Background
The power dispatching is a complex system covering power generation, power transmission, power transformation, power distribution and power utilization, and is different from general production dispatching, the production and supply of electric energy are completed instantly, namely how much power is generated and how much power is used, so that an important responsibility of the power dispatching is to keep the balance between power generation and power utilization (load) at any time. In addition, the power dispatching also needs to perform the work of monitoring the safe operation of the power grid, safety analysis (adopting the technology of real-time load flow calculation and the like), accident handling and the like so as to ensure the safe and stable operation of the power grid, reliable power supply to the outside and orderly operation of all production links. Available data sources for power dispatching mainly comprise basic data, real-time data, application data and environment data.
In the data-driven power market, the larger the data volume and the higher the data quality, the higher the data price cost to be paid by the user. Different users have different requirements on data, some users may only need a rough result, and some users have high requirements on the accuracy of the result. The user then cannot directly ascertain the amount and quality of data that should be purchased in order to obtain the target outcome, with an explicit accuracy of the outcome and an acceptable error margin.
Disclosure of Invention
The invention aims to provide a method and a system for predicting data quantity and data quality based on power scheduling, which solve the problem that the quantity and the data quality of data which are to be purchased for obtaining a target result cannot be directly determined when a user determines result accuracy and an acceptable error range.
In order to achieve the above object, the present invention provides a data quantity and data quality prediction method based on power scheduling, including:
acquiring preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data;
inputting the preset data requirement information into a data relation mapping model to obtain mapping relation information; the mapping relation information comprises the target data quantity and the target data quality.
Preferably, the method for constructing the data relationship mapping model includes:
inputting training sets with different data quantities into a prediction model of the effectiveness of an online power scheduling algorithm for fitting to obtain a relational expression of the data quantities and the prediction accuracy of the prediction model;
and constructing a mapping model between the target data quantity and the preset data requirement information according to the relational expression between the data quantity and the prediction accuracy of the prediction model.
Preferably, the method for constructing the data relationship mapping model further includes:
obtaining a relational expression between the data quality and the effectiveness of the online power scheduling algorithm according to the commitment parameter and the window length of the online power scheduling algorithm;
and constructing a mapping model between the target data quality and the preset data requirement information according to the relation between the data quality and the effectiveness of the online power scheduling algorithm.
Preferably, the inputs of the online power scheduling algorithm include a set of power demand, a set of renewable energy training, and a set of renewable energy testing; the output of the online power scheduling algorithm comprises a scheduling plan.
The invention also provides a data quantity and data quality prediction system based on power scheduling, which comprises:
the information acquisition module is used for acquiring preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data;
the mapping output module is used for inputting the preset data requirement information into a data relation mapping model to obtain mapping relation information; the mapping relation information comprises the target data quantity and the target data quality.
Preferably, the system for predicting data quantity and data quality based on power scheduling further includes a mapping model building module, configured to build the data relation mapping model, specifically:
inputting training sets with different data quantities into a prediction model of the effectiveness of an online power scheduling algorithm for fitting to obtain a relational expression of the data quantities and the prediction accuracy of the prediction model;
and constructing a mapping model between the target data quantity and the preset data requirement information according to the relational expression between the data quantity and the prediction accuracy of the prediction model.
Preferably, the system for predicting data quantity and data quality based on power scheduling further includes a mapping model building module, configured to build the data relation mapping model, specifically:
obtaining a relational expression between the data quality and the effectiveness of the online power scheduling algorithm according to the commitment parameter and the window length of the online power scheduling algorithm;
and constructing a mapping model between the target data quality and the preset data requirement information according to the relation between the data quality and the effectiveness of the online power scheduling algorithm.
Preferably, the inputs of the online power scheduling algorithm include a set of power demand, a set of renewable energy training, and a set of renewable energy testing; the output of the online power scheduling algorithm comprises a scheduling plan.
The embodiment of the invention also provides computer terminal equipment which comprises one or more processors and a memory. A memory coupled to the processor for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement a data quantity and data quality prediction method based on power scheduling as described in any of the embodiments above.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the data quantity and data quality prediction method based on power scheduling according to any of the above embodiments.
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a data quantity and data quality prediction method based on power dispatching, which comprises the following steps: acquiring preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data; inputting the preset data requirement information into a data relation mapping model to obtain mapping relation information; the mapping relation information comprises the target data quantity and the target data quality. The user only needs to input preset data requirement information, and the mapping relation information can be obtained through the data relation mapping model constructed in advance, so that the quantity and the quality of data to be purchased can be obtained under the condition that the accuracy of the result and the acceptable error range are clear.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of an online power dispatching framework in a microgrid;
FIG. 2 is a diagram illustrating a power law relationship satisfied between a prediction error of a power scheduling algorithm and a training set data size;
fig. 3 is a schematic flow chart of a data quantity and data quality prediction method based on power scheduling according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a data quantity and data quality prediction system based on power scheduling according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer terminal device 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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
It should be understood that the step numbers used herein are for convenience of description only and are not used as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
In the field of power system renewable energy prediction, research on the influence of data quality and quantity on online scheduling efficiency is lacking. In order to reduce the impact of uncertainty in line power scheduling, the classical approach is to improve prediction accuracy. However, how the improved accuracy affects the scheduling performance in practical application is an unsolved problem. Therefore, in the application, based on the online convex optimization theory, an optimization problem solving algorithm is customized for the online energy scheduling problem so as to check how the data quality affects the scheduling performance.
In a microgrid comprising renewable energy, in order to meet the power demand of users, microgrid operators schedule traditional power generation in the market in the day ahead, and the problem of unbalanced electric quantity caused by prediction errors is solved in the real-time market. The increasing popularity of renewable energy sources in power systems has prompted the development of power scheduling strategies. To better facilitate online system control, system-level forecasts and necessary data are critical to the overall performance of the power market. The training set size used for prediction is the data quantity, and the window size in the online scheduling problem is the data quality. The empirical power-law relationship between the amount of data and the prediction error is the key to understanding the role of data in online energy scheduling.
At time t, the total demand for electricity in the microgrid is dtThe actual renewable energy power generation amount is rt. Thus, the actual net load gtCan be expressed as: gt＝dt-rt。
Dividing the whole time period into T parts, and defining the traditional power generation obtained at the moment T, the commitment as v and the prediction window as w as gv,w,t. Cost function htThe representative meeting time t is the cost corresponding to meeting the total demand of power utilization, and comprises the cost of buying power in the market in the day ahead and the cost of processing market unbalance by the real-time market:
Figure BDA0003273638570000051
where a, b, c are parameters of the traditional power generation cost and λ is the cost of dealing with real-time market and day-ahead market imbalances. Combining the power generation capacity constraint and the climbing constraint, the offline power scheduling problem form in the micro-grid is as follows:
Figure BDA0003273638570000052
Figure BDA0003273638570000053
Figure BDA0003273638570000054
wherein g represents a lower bound of the power generation capacity,
Figure BDA0003273638570000055
representing an upper bound on the power generation capacity.
Referring to fig. 1, fig. 1 is a frame diagram of online power dispatching in a microgrid. Defining renewable energy power generation quantity when prediction training set is n
Figure BDA0003273638570000061
Predicted net load
Figure BDA0003273638570000062
The expression of (a) is:
Figure BDA0003273638570000063
the corresponding online scheduling cost function is represented as:
Figure BDA0003273638570000064
similarly, the online optimization problem of the power scheduling is correspondingly modified on the basis of the offline optimization problem.
In order to design a scheduling algorithm of power based on the existing online convex optimization problem algorithm, the online power scheduling problem can be rewritten into the following form by replacing a climbing constraint with a soft constraint:
Figure BDA0003273638570000065
wherein the electricity generation selection set G is defined as
Figure BDA0003273638570000066
Beta is a parameter connecting the electricity production cost and the climbing capacity. At the same time, htThe (DEG) is a convex function, so that an online power dispatching algorithm OED is designed by combining an algorithm of a smooth online convex optimization problem. Where m represents the test set data volume and j is the number of features required for prediction. Referring to table 1, table 1 is a calculation process table of the online power scheduling algorithm.
Figure BDA0003273638570000067
Figure BDA0003273638570000071
A method of calculating the effectiveness of an online power scheduling algorithm, comprising: defining cost (opt) as the optimal offline power dispatching cost, and cost (oed) as the cost obtained by the online power dispatching algorithm. Further, the effectiveness of the algorithm is represented by the difference cd (oed) between the two: cd (oed) -cost (opt).
Based on the expected value of the renewable energy prediction error being 0 and the independent same distribution, the effectiveness of the algorithm is expressed as:
Figure BDA0003273638570000072
wherein the content of the first and second substances,
Figure BDA0003273638570000073
and { e } is the prediction error with standard deviation σ.
To simplify the expression of the effectiveness of the algorithm, EB (OED) is expressed as:
Figure BDA0003273638570000074
wherein the tail distribution of the algorithm can be representedComprises the following steps:
Figure BDA0003273638570000075
similarly, for convenience of representation, the following is obtained by further simplification:
Figure BDA0003273638570000076
in a general machine learning prediction problem, the selection of the number of samples in the training set has a significant impact on the prediction accuracy. Intuitively, the accuracy improves as the number of samples increases. At the same time, although the problem of reduced accuracy caused by overfitting can be alleviated by appropriately selecting a portion of the data for training, machine learning algorithms are still often affected by overfitting and underfitting. Empirical studies are used to fit the relationship between data volume and prediction accuracy. Selecting LSTM as a prediction model, and representing prediction accuracy by two indexes of root mean square error RMSE and mean square error MSE, wherein a power rule is satisfied between the prediction error and the data volume of a training set shown in FIG. 2, wherein the root mean square error RMSE is represented by the index of the prediction accuracy in FIG. 2(a), and the mean square error MSE is represented by the index of the prediction accuracy in FIG. 2 (b).
Taking the root mean square error RMSE as an example, the relationship between the root mean square error RMSE and the number n of training set samples is:
Figure BDA0003273638570000081
wherein, θ and
Figure BDA0003273638570000082
is a positive parameter obtained from the empirical results.
And measuring the data quantity by using the number n of the samples of the prediction model training set. Under the assumption that the expected prediction error value is 0 and the prediction error values are independently and identically distributed, the relationship between the standard deviation sigma of the prediction error and the error metric RMSE can be obtained: σ ═ RMSE.
Based on the relationship, the influence of the obtained data quantity on the effectiveness of the online power dispatching algorithm is as follows:
Figure BDA0003273638570000083
Figure BDA0003273638570000084
the commitment parameter v and the window length w in the online power scheduling algorithm OED measure the data quality, are intuitively understood and represent the data information updating speed. The influence of the data quality on the effectiveness of the online power scheduling algorithm is as follows:
Figure BDA0003273638570000085
referring to fig. 3, based on the research on the influence of the data quantity on the effectiveness of the online power scheduling algorithm and the influence of the data quality on the effectiveness of the online power scheduling algorithm, an embodiment of the present invention provides a method for predicting the data quantity and the data quality based on power scheduling, including the following steps:
s110, acquiring preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data;
s120, inputting the preset data requirement information into a data relation mapping model to obtain mapping relation information; the mapping relation information comprises the target data quantity and the target data quality.
In one embodiment, the method for constructing the data relationship mapping model includes:
inputting training sets with different data quantities into a prediction model of the effectiveness of an online power scheduling algorithm for fitting to obtain a relational expression of the data quantities and the prediction accuracy of the prediction model;
and constructing a mapping model between the target data quantity and the preset data requirement information according to the relational expression between the data quantity and the prediction accuracy of the prediction model.
In a certain embodiment, the method for constructing the data relationship mapping model further includes:
obtaining a relational expression between the data quality and the effectiveness of the online power scheduling algorithm according to the commitment parameter and the window length of the online power scheduling algorithm;
and constructing a mapping model between the target data quality and the preset data requirement information according to the relation between the data quality and the effectiveness of the online power scheduling algorithm.
In a certain embodiment, the inputs to the online power scheduling algorithm include a set of power demand, a set of renewable energy training, and a set of renewable energy testing; the output of the online power scheduling algorithm comprises a scheduling plan.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a data quantity and data quality prediction system based on power scheduling according to an embodiment of the present invention. In this embodiment, the system for predicting data quantity and data quality based on power scheduling includes:
an information obtaining module 210, configured to obtain preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data;
a mapping output module 220, configured to input the preset data requirement information into a data relationship mapping model to obtain mapping relationship information; the mapping relation information comprises the target data quantity and the target data quality.
In a certain embodiment, the system for predicting data quantity and data quality based on power scheduling further includes a mapping model building module, configured to build the data relation mapping model, specifically:
inputting training sets with different data quantities into a prediction model of the effectiveness of an online power scheduling algorithm for fitting to obtain a relational expression of the data quantities and the prediction accuracy of the prediction model;
and constructing a mapping model between the target data quantity and the preset data requirement information according to the relational expression between the data quantity and the prediction accuracy of the prediction model.
In a certain embodiment, the system for predicting data quantity and data quality based on power scheduling further includes a mapping model building module, configured to build the data relation mapping model, specifically:
obtaining a relational expression between the data quality and the effectiveness of the online power scheduling algorithm according to the commitment parameter and the window length of the online power scheduling algorithm;
and constructing a mapping model between the target data quality and the preset data requirement information according to the relation between the data quality and the effectiveness of the online power scheduling algorithm.
In a certain embodiment, the inputs to the online power scheduling algorithm include a set of power demand, a set of renewable energy training, and a set of renewable energy testing; the output of the online power scheduling algorithm comprises a scheduling plan.
Specific limitations on the data quantity and data quality prediction system based on power scheduling can be referred to the limitations in the above, and are not described in detail here. The various modules in the above-described power scheduling-based data quantity and data quality prediction system may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Referring to fig. 5, an embodiment of the invention provides a computer terminal device, which includes one or more processors and a memory. A memory is coupled to the processor for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement a method of data quantity and data quality prediction based on power scheduling as in any one of the embodiments described above.
The processor is used for controlling the overall operation of the computer terminal equipment so as to complete all or part of the steps of the data quantity and data quality prediction method based on the power scheduling. The memory is used to store various types of data to support the operation at the computer terminal device, which data may include, for example, instructions for any application or method operating on the computer terminal device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
In an exemplary embodiment, the computer terminal Device may be implemented by one or more Application Specific 1 integrated circuits (AS 1C), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is configured to perform the above-mentioned power scheduling-based data quantity and data quality prediction methods, and achieve technical effects consistent with the above-mentioned methods.
In another exemplary embodiment, there is also provided a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the data quantity and data quality prediction method based on power scheduling in any one of the above embodiments. For example, the computer readable storage medium may be the above-mentioned memory including program instructions executable by a processor of a computer terminal device to perform the above-mentioned data quantity and data quality prediction method based on power scheduling, and to achieve the technical effects consistent with the above-mentioned method.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.

Claims (10)

1. A data quantity and data quality prediction method based on power scheduling is characterized by comprising the following steps:
acquiring preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data;
inputting the preset data requirement information into a data relation mapping model to obtain mapping relation information; the mapping relation information comprises the target data quantity and the target data quality.
2. The data quantity and data quality prediction method based on power scheduling of claim 1, wherein the construction method of the data relation mapping model comprises the following steps:
inputting training sets with different data quantities into a prediction model of the effectiveness of an online power scheduling algorithm for fitting to obtain a relational expression of the data quantities and the prediction accuracy of the prediction model;
and constructing a mapping model between the target data quantity and the preset data requirement information according to the relational expression between the data quantity and the prediction accuracy of the prediction model.
3. The data quantity and data quality prediction method based on power scheduling of claim 2, wherein the construction method of the data relation mapping model further comprises:
obtaining a relational expression between the data quality and the effectiveness of the online power scheduling algorithm according to the commitment parameter and the window length of the online power scheduling algorithm;
and constructing a mapping model between the target data quality and the preset data requirement information according to the relation between the data quality and the effectiveness of the online power scheduling algorithm.
4. The power scheduling based data quantity and data quality prediction method according to claim 2, wherein the inputs of the online power scheduling algorithm comprise a set of electricity demand, a set of renewable energy training and a set of renewable energy testing; the output of the online power scheduling algorithm comprises a scheduling plan.
5. A data quantity and data quality prediction system based on power scheduling, comprising:
the information acquisition module is used for acquiring preset data requirement information sent by a user; the preset data requirement information comprises an expected value of the accuracy of the power scheduling result or the cost of the power scheduling data;
the mapping output module is used for inputting the preset data requirement information into a data relation mapping model to obtain mapping relation information; the mapping relation information comprises the target data quantity and the target data quality.
6. The power scheduling based data quantity and data quality prediction system according to claim 5, further comprising a mapping model construction module for constructing the data relation mapping model, in particular:
inputting training sets with different data quantities into a prediction model of the effectiveness of an online power scheduling algorithm for fitting to obtain a relational expression of the data quantities and the prediction accuracy of the prediction model;
and constructing a mapping model between the target data quantity and the preset data requirement information according to the relational expression between the data quantity and the prediction accuracy of the prediction model.
7. The power scheduling based data quantity and data quality prediction system according to claim 5, further comprising a mapping model construction module for constructing the data relation mapping model, in particular:
obtaining a relational expression between the data quality and the effectiveness of the online power scheduling algorithm according to the commitment parameter and the window length of the online power scheduling algorithm;
and constructing a mapping model between the target data quality and the preset data requirement information according to the relation between the data quality and the effectiveness of the online power scheduling algorithm.
8. The power scheduling based data quantity and data quality prediction system of claim 6 wherein the inputs to the online power scheduling algorithm include a set of electricity demand, a set of renewable energy training, and a set of renewable energy testing; the output of the online power scheduling algorithm comprises a scheduling plan.
9. A computer terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of power scheduling based data quantity and data quality prediction as claimed in any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the data quantity and data quality prediction method based on power scheduling according to any one of claims 1 to 4.
CN202111109538.2A 2021-09-22 2021-09-22 Data quantity and data quality prediction method and system based on power scheduling Active CN113807593B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111109538.2A CN113807593B (en) 2021-09-22 2021-09-22 Data quantity and data quality prediction method and system based on power scheduling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111109538.2A CN113807593B (en) 2021-09-22 2021-09-22 Data quantity and data quality prediction method and system based on power scheduling

Publications (2)

Publication Number Publication Date
CN113807593A true CN113807593A (en) 2021-12-17
CN113807593B CN113807593B (en) 2024-01-23

Family

ID=78896181

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111109538.2A Active CN113807593B (en) 2021-09-22 2021-09-22 Data quantity and data quality prediction method and system based on power scheduling

Country Status (1)

Country Link
CN (1) CN113807593B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113408837A (en) * 2020-03-16 2021-09-17 图灵人工智能研究院（南京）有限公司 Energy consumption control strategy generation method, system, device, distribution and distribution system and medium
CN115018212A (en) * 2022-08-08 2022-09-06 水利部珠江水利委员会珠江水利综合技术中心 Power generation water consumption prediction analysis method and system and cloud platform

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110035071A1 (en) * 2010-07-02 2011-02-10 David Sun System tools for integrating individual load forecasts into a composite load forecast to present a comprehensive synchronized and harmonized load forecast
CN109149567A (en) * 2018-09-10 2019-01-04 华南理工大学 The Multiple Time Scales control method for coordinating of self micro-capacitance sensor containing hybrid energy-storing
JP2021018821A (en) * 2019-07-18 2021-02-15 ▲広▼州大学 Data intelligent prediction method, device, computer device, and storage medium
KR20210037264A (en) * 2019-09-27 2021-04-06 한국전력공사 Apparatus for auto-scheduling of energy storage system for charging and discharging method thereof
CN116542490A (en) * 2023-06-29 2023-08-04 国网智能电网研究院有限公司 Virtual power plant day-ahead dispatching encapsulation model and dispatching ex-definition model construction method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110035071A1 (en) * 2010-07-02 2011-02-10 David Sun System tools for integrating individual load forecasts into a composite load forecast to present a comprehensive synchronized and harmonized load forecast
CN109149567A (en) * 2018-09-10 2019-01-04 华南理工大学 The Multiple Time Scales control method for coordinating of self micro-capacitance sensor containing hybrid energy-storing
JP2021018821A (en) * 2019-07-18 2021-02-15 ▲広▼州大学 Data intelligent prediction method, device, computer device, and storage medium
KR20210037264A (en) * 2019-09-27 2021-04-06 한국전력공사 Apparatus for auto-scheduling of energy storage system for charging and discharging method thereof
CN116542490A (en) * 2023-06-29 2023-08-04 国网智能电网研究院有限公司 Virtual power plant day-ahead dispatching encapsulation model and dispatching ex-definition model construction method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
JINGSHI CUI等: "Quantity or Quality? Data Enabled Online Energy Dispatch", PROCEEDINGS OF THE 2021 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, pages 606 - 612 *
RICHARD D RILEY等: "Calculating the sample size required for developing a clinical prediction model", BMJ, pages 1 - 12 *
RLILYX: "数学基础-模型准确度影响因素", pages 1 - 7, Retrieved from the Internet <URL:https://blog.csdn.net/weixin_37801695/article/details/80590550> *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113408837A (en) * 2020-03-16 2021-09-17 图灵人工智能研究院（南京）有限公司 Energy consumption control strategy generation method, system, device, distribution and distribution system and medium
CN113408837B (en) * 2020-03-16 2023-09-26 图灵人工智能研究院（南京）有限公司 Energy utilization control strategy generation method, system, device, energy distribution system and medium
CN115018212A (en) * 2022-08-08 2022-09-06 水利部珠江水利委员会珠江水利综合技术中心 Power generation water consumption prediction analysis method and system and cloud platform

Also Published As

Publication number Publication date
CN113807593B (en) 2024-01-23

Similar Documents

Publication Publication Date Title
CN113807593B (en) Data quantity and data quality prediction method and system based on power scheduling
CN106529704A (en) Monthly maximum power load forecasting method and apparatus
CN111144025A (en) Simulation model parameterization integration system and method based on multi-level reconstruction
CN111198799A (en) Machine room power consumption early warning method, system, terminal and storage medium based on LSTM
KR20220100975A (en) Cable route planning methods, systems, media and electronic devices in wind farms
CN112200489B (en) Integrated optimization system, method and device for nonferrous metal smelting production and supply marketing
CN106408126B (en) A kind of three perfecting by stage methods concurrently gathered towards energy consumption data
CN106067077A (en) A kind of load forecasting method based on neutral net and device
CN115034519A (en) Method and device for predicting power load, electronic equipment and storage medium
CN115986728A (en) Power grid situation prediction method considering uncertainty factors and terminal
CN109359433B (en) Automation method for reactor core refueling design
CN113328467A (en) Probability voltage stability evaluation method, system, terminal device and medium
Rao et al. Software selection in manufacturing industries using a fuzzy multiple criteria decision making method, PROMETHEE
FAN et al. Research and application of project settlement overdue prediction based on xgboost intelligent algorithm
CN113991752B (en) Quasi-real-time intelligent control method and system for power grid
CN111784203A (en) Electric power spot market risk simulation analysis method suitable for generator set participation
Ali et al. Studying dynamic pricing in electrical power markets with distributed generation: Agent-based modeling and reinforcement-learning approach
CN108767854B (en) Electricity purchase scheme optimization method and device and electronic equipment
CN115879824A (en) Method, device, equipment and medium for assisting expert decision based on ensemble learning
Zadeh et al. Multi-thread security constraint economic dispatch with exact loss formulation
CN115528684A (en) Ultra-short-term load prediction method and device and electronic equipment
Liu et al. Deep reinforcement learning for real-time economic energy management of microgrid system considering uncertainties
Shendryk et al. Decision Support System for Efficient Energy Management of MicroGrid with Renewable Energy Sources
Wenbo et al. The model combination method of power system load forecasting based on freshness availability index
CN113723717B (en) Method, device, equipment and readable storage medium for predicting short-term load before system day

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
GR01 Patent grant
GR01 Patent grant