CN110796314A - Monthly total power consumption prediction method considering temperature gradient change - Google Patents
Monthly total power consumption prediction method considering temperature gradient change Download PDFInfo
- Publication number
- CN110796314A CN110796314A CN201911063382.1A CN201911063382A CN110796314A CN 110796314 A CN110796314 A CN 110796314A CN 201911063382 A CN201911063382 A CN 201911063382A CN 110796314 A CN110796314 A CN 110796314A
- Authority
- CN
- China
- Prior art keywords
- month
- daily
- temperature
- power consumption
- total
- 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
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
- 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
Abstract
The invention provides a monthly general power consumption prediction method considering temperature gradient change, which comprises the following steps: s1, sorting the data of the ith month of the previous 1 year, sorting to form a daily average temperature and daily general electricity consumption data unit, and then dividing two data groups of working days and holidays; s2, performing ascending arrangement on the data units according to daily average temperature, and performing linear regression on the ordered data unit sequence by using a least square method to obtain an i-month working daily gradient temperature electric quantity model; s3, averaging the daily average temperature of the working day I-1 of the month, and taking the average as the base air temperature of the working day of the next month; and (4) calculating the average value of the daily total call electricity consumption of the working day of the month as the basic electricity consumption of the working day of the next month, and predicting the basic air temperature and the basic electricity consumption of the holidays of the month. The method fully considers the influence of temperature factors on the prediction of the total power consumption, can effectively reduce prediction errors especially in months with severe temperature changes in summer and winter, and is beneficial to the short-term power prediction method.
Description
Technical Field
The invention relates to the technical field of power grid systems, in particular to a monthly total power consumption prediction method considering temperature gradient change.
Background
The prediction of the power consumption is daily important work of related departments of a power system, the prediction of the power demand has important significance on the work of the power departments and related economic and energy departments, the overall power consumption is one of important indexes of the prediction of the power demand, the accurate prediction of the power consumption is beneficial to arrangement of a power production plan, and meanwhile, a basis can be provided for planning and designing a power grid.
The general electricity consumption refers to the electricity consumption used by users accessing the power grid. Different from users directly powered by local small power plants, the system has large-scale electricity consumption and wide related users, can basically represent the overall electricity consumption condition of a region, and is generally released by provincial power grid companies periodically according to the monthly degree. The prediction of monthly total dispatching power consumption is a starting point and a basis for making a specific next-month production plan, and has great significance for the organization of a power dispatching department to arrange the output of a total dispatching power plant and maintain load balance and power grid stability. Along with the improvement of the living standard of residents, the cooling and heating loads are rapidly increased, and the influence of the temperature on the total power consumption is larger and larger, so that the monthly total power consumption prediction method considering the temperature gradient change is provided. The method fully considers the influence of temperature factors on the prediction of the total power consumption, can effectively reduce prediction errors especially in months with severe temperature changes in summer and winter, and is beneficial to the short-term power prediction method.
The Chinese patent with the application number of 201210147746.6 discloses an intelligent power consumption prediction system and a method, wherein the system comprises an intelligent power consumption terminal (1), an electric energy acquisition module (2) which is respectively connected with the intelligent power consumption terminal (1) and used for managing real-time data acquisition, a local storage management module (3), a predicted value analysis and calculation module (4) of a predicted point, and a GPRS communication control module (5) which is responsible for data communication transmission control; the core prediction processing algorithm of the predictive value analysis and calculation module (4) adopts a BP neural network. The invention can lead the user to know the electricity utilization condition in advance, and provides effective electricity utilization optimization suggestion for the user by combining with the electricity utilization optimization algorithm, thereby improving the electricity utilization habit of the user, avoiding unnecessary electricity fee expenditure of the electric appliance of the user and saving the electricity fee for the user economically; the power grid fluctuation caused by the electricity consumption of the peak of the user can be reduced, so that the power grid is more stable, more stable power transmission is provided, the quality of the electricity consumption of residents is improved, and the production of the power users of enterprises such as production and manufacturing is stable.
The chinese patent with application number 201310474089.0 provides a method for predicting user monthly electricity consumption based on seasonal index method, which comprises the following steps: 1) acquiring historical electricity consumption data from an electricity consumption historical database by using an electricity consumption historical data acquisition unit, and storing the historical electricity consumption data in an electricity consumption historical data storage unit; 2) the seasonal index calculation unit calculates a seasonal index according to historical data of the power consumption; and 3) the power consumption prediction model construction unit constructs a power consumption prediction model by utilizing the seasonal index.
But does not take into account the effects of temperature gradient changes.
Disclosure of Invention
In view of the above, the present invention provides a monthly total power consumption prediction method capable of considering temperature gradient changes, which fully considers the influence of temperature factors on the total power consumption prediction, and particularly in months with severe temperature changes in summer and winter, can effectively reduce prediction errors, and is a beneficial supplement to the short-term power consumption prediction method.
In order to solve the technical problem, the invention provides a monthly total electricity consumption prediction method considering temperature gradient change, which comprises the following steps:
s1, arranging the data of the ith month of the previous 1 year, firstly arranging the data to form a daily average temperature and daily general electricity consumption data unit, and then dividing the data into two data groups of working days and holidays;
s2, performing ascending arrangement on the data units according to daily average temperature, and performing linear regression on the ordered data unit sequence by using a least square method to obtain an i-month working daily gradient temperature electric quantity model;
s3, averaging the daily average temperature of working days I-1 of this month to obtain the basic temperature T of working days of next monthI,W(ii) a The average value of the daily total power consumption of the working day of the month is used as the basic power consumption of the working day of the next monthEI,WSimilarly, the basic air temperature T of the month, day and holiday is predictedI,HAnd a basic electric quantity EI,H。
And S4, according to the daily prediction of the temperature in the month I by the meteorological department, superposing the newly added electric quantity generated due to the temperature factor on the basic electric quantity, and distinguishing working days and holidays to respectively complete the prediction of the total electricity consumption in the month I.
Further, in step S2, the i-month working day gradient temperature electric quantity model is:
Ei,w=ki,w*Ti,w+Ci,w
wherein, i month is a prediction month and takes values of 1, 2, 3 … 12, Ei,w、Ti,w、Ci,wRespectively the daily total electricity consumption, daily average temperature, constant term, k of the last year i month working dayi,wThe physical meaning of the gradient temperature coefficient of the working day of the last year in the month i is that the electric quantity of the daily total regulation of the working day of the month i is increased by k every time the temperature is increased by 1 DEG Ci,wHundred million kilowatt hours, and the same principle, the gradient temperature coefficient k of holidays of i month in the last yeari,h。
Further, in step S4, the calculation formula of the daily electricity consumption for the I-th month work is as follows:
wherein the content of the first and second substances,and respectively representing the daily total electricity consumption and the daily average temperature predicted value of the J-th working day of the month I.
Further, in step S4, the formula for calculating the total electricity consumption for holidays in the I-th month is as follows:
wherein the content of the first and second substances,respectively represent the J th of month IDaily total electricity consumption of holidays and daily average temperature predicted values.
Further, in step S4, the predicted value of the total daily schedule power consumption for the working day and holiday is accumulated to obtain the predicted value of the total daily schedule power consumption for the first month
The prediction of monthly total dispatching power consumption is a starting point and a basis for making a specific next-month production plan, and has great significance for the organization of a power dispatching department to arrange the output of a total dispatching power plant and maintain load balance and power grid stability.
The method fully considers the influence of temperature factors on the prediction of the total power consumption, can effectively reduce prediction errors especially in months with severe temperature changes in summer and winter, and is beneficial to the short-term power prediction method.
Drawings
Fig. 1 is a schematic diagram of a monthly total electricity consumption prediction method that can consider a temperature gradient change.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to fig. 1 of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.
The first embodiment of the invention provides a monthly total power consumption prediction method considering temperature gradient change, which comprises the following steps:
s1, arranging the data of the ith month of the previous 1 year, firstly arranging the data to form a daily average temperature and daily general electricity consumption data unit, and then dividing the data into two data groups of working days and holidays;
s2, performing ascending arrangement on the data units according to daily average temperature, and performing linear regression on the ordered data unit sequence by using a least square method to obtain an i-month working daily gradient temperature electric quantity model;
s3, averaging the daily average temperature of working days I-1 of this month to obtain the basic temperature T of working days of next monthI,W(ii) a The average value of the daily total power consumption of the working day of the month is used as the basic power E of the working day of the next monthI,WSimilarly, the basic air temperature T of the month, day and holiday is predictedI,HAnd a basic electric quantity EI,H。
And S4, according to the daily prediction of the temperature in the month I by the meteorological department, superposing the newly added electric quantity generated due to the temperature factor on the basic electric quantity, and distinguishing working days and holidays to respectively complete the prediction of the total electricity consumption in the month I.
Further, in step S2, the i-month working day gradient temperature electric quantity model is:
Ei,w=ki,w*Ti,w+Ci,w
wherein, i month is a prediction month and takes values of 1, 2, 3 … 12, Ei,w、Ti,w、Ci,wRespectively the daily total electricity consumption, daily average temperature, constant term, k of the last year i month working dayi,wThe physical meaning of the gradient temperature coefficient of the working day of the last year in the month i is that the electric quantity of the daily total regulation of the working day of the month i is increased by k every time the temperature is increased by 1 DEG Ci,wHundred million kilowatt hours, and the same principle, the gradient temperature coefficient k of holidays of i month in the last yeari,h。
Further, in step S4, the calculation formula of the daily electricity consumption for the I-th month work is as follows:
wherein the content of the first and second substances,and respectively representing the daily total electricity consumption and the daily average temperature predicted value of the J-th working day of the month I.
Further, in step S4, the formula for calculating the total electricity consumption for holidays in the I-th month is as follows:
Example two
It differs from the first embodiment in that:
in step S4, the predicted value of the total daily electricity consumption for weekdays and holidays is accumulated to obtain the predicted value of the total daily electricity consumption for monthly
The prediction of monthly total dispatching power consumption is a starting point and a basis for making a specific next-month production plan, and has great significance for the organization of a power dispatching department to arrange the output of a total dispatching power plant and maintain load balance and power grid stability.
The method fully considers the influence of temperature factors on the prediction of the total power consumption, can effectively reduce prediction errors especially in months with severe temperature changes in summer and winter, and is beneficial to the short-term power prediction method.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (5)
1. A monthly total power consumption prediction method considering temperature gradient change is characterized by comprising the following steps:
s1, arranging the data of the ith month of the previous 1 year, firstly arranging the data to form a daily average temperature and daily general electricity consumption data unit, and then dividing the data into two data groups of working days and holidays;
s2, performing ascending arrangement on the data units according to daily average temperature, and performing linear regression on the ordered data unit sequence by using a least square method to obtain an i-month working daily gradient temperature electric quantity model;
s3, averaging the daily average temperature of working days I-1 of this month to obtain the basic temperature T of working days of next monthI,W(ii) a The average value of the daily total power consumption of the working day of the month is used as the basic power E of the working day of the next monthI,WSimilarly, the basic air temperature T of the month, day and holiday is predictedI,HAnd a basic electric quantity EI,H。
And S4, according to the daily prediction of the temperature in the month I by the meteorological department, superposing the newly added electric quantity generated due to the temperature factor on the basic electric quantity, and distinguishing working days and holidays to respectively complete the prediction of the total electricity consumption in the month I.
2. The throttling system for improving grid efficiency according to claim 1, wherein the i-month working day gradient temperature electric quantity model in step S2 is:
Ei,w=ki,w*Ti,w+Ci,w
wherein, i month is a prediction month and takes values of 1, 2, 3 … 12, Ei,w、Ti,w、Ci,wRespectively the daily total electricity consumption, daily average temperature, constant term, k of the last year i month working dayi,wThe physical meaning of the gradient temperature coefficient of the working day of the last year in the month i is that the electric quantity of the daily total regulation of the working day of the month i is increased by k every time the temperature is increased by 1 DEG Ci,wHundred million kilowatt hours, and the same principle, the gradient temperature coefficient k of holidays of i month in the last yeari,h。
3. The throttling system for improving grid efficiency according to claim 1, wherein in step S4, the calculation formula of the I-th month operating daily total power consumption is as follows:
4. The throttling system for improving grid efficiency according to claim 3, wherein in step S4, the formula for calculating the total power consumption for holidays in month I is as follows:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911063382.1A CN110796314A (en) | 2019-10-31 | 2019-10-31 | Monthly total power consumption prediction method considering temperature gradient change |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911063382.1A CN110796314A (en) | 2019-10-31 | 2019-10-31 | Monthly total power consumption prediction method considering temperature gradient change |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110796314A true CN110796314A (en) | 2020-02-14 |
Family
ID=69442490
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911063382.1A Pending CN110796314A (en) | 2019-10-31 | 2019-10-31 | Monthly total power consumption prediction method considering temperature gradient change |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110796314A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112713616A (en) * | 2020-12-31 | 2021-04-27 | 南方电网科学研究院有限责任公司 | Control method, device, equipment and medium for generating side unit of power system |
CN112803492A (en) * | 2020-12-31 | 2021-05-14 | 南方电网科学研究院有限责任公司 | Control method, device, equipment and medium for generating side unit of power system |
-
2019
- 2019-10-31 CN CN201911063382.1A patent/CN110796314A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112713616A (en) * | 2020-12-31 | 2021-04-27 | 南方电网科学研究院有限责任公司 | Control method, device, equipment and medium for generating side unit of power system |
CN112803492A (en) * | 2020-12-31 | 2021-05-14 | 南方电网科学研究院有限责任公司 | Control method, device, equipment and medium for generating side unit of power system |
CN112713616B (en) * | 2020-12-31 | 2022-10-28 | 南方电网科学研究院有限责任公司 | Control method, device, equipment and medium for generating side unit of power system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107370170B (en) | Energy storage system capacity configuration method considering capacity electricity price and load prediction error | |
CN102694391B (en) | Day-ahead optimal scheduling method for wind-solar storage integrated power generation system | |
Mu et al. | Short-term load forecasting using improved similar days method | |
Biel et al. | Flow shop scheduling with grid-integrated onsite wind power using stochastic MILP | |
CN109886567B (en) | Short-term load prediction method considering somatosensory temperature and radiation intensity | |
CN110729764A (en) | Optimal scheduling method for photovoltaic power generation system | |
CN110796314A (en) | Monthly total power consumption prediction method considering temperature gradient change | |
CN110866658A (en) | Method for predicting medium and long term load of urban power grid | |
CN111639819B (en) | Multi-stage optimization control method for comprehensive energy park | |
CN110909958A (en) | Short-term load prediction method considering photovoltaic grid-connected power | |
CN104134102B (en) | Long-term electricity needs distribution forecasting method in power network based on LEAP models | |
CN112288130A (en) | New energy consumption calculation method based on two-stage multi-objective optimization | |
CN110991750A (en) | Short-term power load prediction method based on neural network | |
CN115511541A (en) | Time-period electricity price calculation method based on supply and demand situations and system cost | |
CN111626509B (en) | Method and system for evaluating effective supply capacity of regional new energy | |
CN113626763A (en) | Short-term whole-network maximum power load prediction method and system | |
Zhang et al. | The research on smart power consumption technology based on big data | |
CN111079966B (en) | Generalized load space prediction method and system | |
CN109840614B (en) | Transformer optimal equipment utilization rate control method based on life cycle cost | |
CN107749646B (en) | Power plant sequencing coefficient calculation method for monthly electric quantity regulation | |
Deng et al. | Analysis of Renewable Energy Accommodation Capability of Shanxi Power Grid Based on Operation Simulation Method | |
CN110991748A (en) | Short-term load prediction method for urban power grid | |
Wang et al. | Research on the characteristics of flexible control load of rural distribution network and flexibility evaluation | |
CN116632935B (en) | Balance unit-based power system balance optimization method | |
CN109657877A (en) | A kind of electric power Mid-long term load forecasting method based on the double-deck regression model |
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: 20200214 |
|
RJ01 | Rejection of invention patent application after publication |