CN115358476A - Demand response potential prediction method, demand response potential prediction device, computer equipment and storage medium - Google Patents

Demand response potential prediction method, demand response potential prediction device, computer equipment and storage medium Download PDF

Info

Publication number
CN115358476A
CN115358476A CN202211042308.3A CN202211042308A CN115358476A CN 115358476 A CN115358476 A CN 115358476A CN 202211042308 A CN202211042308 A CN 202211042308A CN 115358476 A CN115358476 A CN 115358476A
Authority
CN
China
Prior art keywords
coefficient
power consumption
electricity
predicted
time period
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
Application number
CN202211042308.3A
Other languages
Chinese (zh)
Inventor
周晓
刘志文
肖天颖
董楠
邵冲
黄豫
梁宇
曹毅
卓越
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.)
Energy Development Research Institute of China Southern Power Grid Co Ltd
Original Assignee
Energy Development Research Institute of China Southern 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 Energy Development Research Institute of China Southern Power Grid Co Ltd filed Critical Energy Development Research Institute of China Southern Power Grid Co Ltd
Priority to CN202211042308.3A priority Critical patent/CN115358476A/en
Publication of CN115358476A publication Critical patent/CN115358476A/en
Pending legal-status Critical Current

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2282—Tablespace storage structures; Management thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Databases & Information Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Educational Administration (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Computational Linguistics (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The application relates to a demand response potential prediction method, a demand response potential prediction device, a computer device, a storage medium and a computer program product. The method comprises the steps of obtaining a unit-degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient of an object to be predicted from an electric power database by detecting a demand response potential prediction request, inquiring a preset rule table according to grades corresponding to the coefficients respectively, determining an elasticity coefficient matrix according to the obtained self elasticity coefficient and mutual elasticity coefficient, and determining a new electricity demand of the object to be predicted, which is in response to an updated electricity demand in a preset time period, according to the elasticity coefficient matrix, the original electricity demand, the original electricity cost, the updated electricity cost and the number of electricity periods of the object to be predicted in the preset time period. Compared with the traditional prediction method through a physical modeling mode, the method has the advantages that the demand response potential is predicted based on the unit-degree electricity generation value, the peak-valley load coefficient, the load interruptible coefficient and the elastic coefficient matrix, and the prediction complexity is reduced.

Description

Demand response potential prediction method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of power technologies, and in particular, to a demand response potential prediction method, apparatus, computer device, storage medium, and computer program product.
Background
With the continuous improvement of the power generation proportion of renewable energy sources in the power system, the power grid faces the problem of insufficient time-interval peak regulation capacity, the peak regulation potential needs to be further mined, the regulation capacity of the system is improved, and the balance of supply and demand of power is promoted. Demand response is an efficient load management means in the power industry, and the aim of peak clipping and valley filling is achieved by properly increasing the electricity price during the peak period of electricity utilization or giving incentive rewards to users and reducing the electricity price during the valley period of electricity utilization in a mode of guiding the users to use electricity by peak clipping and valley filling. By the demand response method, the power load reduction and transfer in the peak period can be realized, the distributed power generation is effectively consumed, and the operation cost of a power grid is reduced. The assessment of the demand response potential is a basis for scientifically formulating a demand-side management means and assessing demand response benefits, and can help power enterprises and load managers to determine the expected scale and source of demand response resources, so that the goal and strategy of demand response development are facilitated. The current way to predict demand response potential is typically to evaluate demand response potential after physical modeling of different electrical devices. However, forecasting the demand response potential through physical modeling can result in increased forecasting complexity due to the complexity of the modeling process.
Therefore, the current demand response potential prediction method has the defect of high complexity.
Disclosure of Invention
In view of the above, there is a need to provide a demand response potential prediction method, apparatus, computer device, computer readable storage medium and computer program product capable of reducing prediction complexity.
In a first aspect, the present application provides a demand response potential prediction method, including:
responding to a demand response potential prediction request, and inquiring and acquiring a unit degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient corresponding to an object to be predicted from a power database; the unit degree electricity generation value represents the influence of electricity cost on the electricity consumption of the object to be predicted; the load peak-valley distribution coefficient represents the electricity consumption time interval distribution characteristic of the electricity consumption of the object to be predicted; the load interruptible coefficient represents the influence degree of the interrupted power consumption on the production of the object to be predicted;
inquiring a preset rule table according to the grade corresponding to the unit degree electricity generation value, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient to obtain a corresponding self-elasticity coefficient and a corresponding mutual elasticity coefficient; the preset rule table comprises corresponding relations among the grade corresponding to the unit degree electric power value, the grade corresponding to the load peak-valley distribution coefficient, the grade corresponding to the load interruptible coefficient, the self-elasticity coefficient and the mutual elasticity coefficient; the self-elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity cost variation of the current time period; the mutual elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variation of other time periods;
determining an elasticity coefficient matrix according to the self elasticity coefficient and the mutual elasticity coefficient, and determining a new power consumption demand of the object to be predicted in response to the updated power consumption cost in a preset time period according to the elasticity coefficient matrix, the original power consumption demand of the object to be predicted in a preset time period, the original power consumption cost of the object to be predicted in the preset time period, the corresponding updated power consumption cost of the object to be predicted in the preset time period and the number of power consumption time periods;
and determining the demand response potential of the object to be predicted according to the difference value of the new power demand and the original power demand.
In one embodiment, the obtaining of the unit-degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient corresponding to the object to be predicted includes:
acquiring an annual output value increment and an annual power consumption of an object to be predicted in a historical time period, and acquiring a total power consumption of the object to be predicted in a preset time period, wherein the preset time period comprises a power consumption peak time period, a power consumption valley time period and a power consumption level middle time period;
determining the unit-degree electricity generation value of the object to be predicted according to the annual value increment and the annual electricity consumption in the historical time period;
acquiring first electric quantity at a power consumption peak period, second electric quantity at a power consumption valley period and power consumption data points at the power consumption peak period, the power consumption valley period and the power consumption level period in the total power consumption in the preset period, and acquiring a load peak-valley distribution coefficient according to the first electric quantity, the second electric quantity and the power consumption data points;
and determining a load interruptible coefficient corresponding to the object to be predicted according to the power utilization behavior of the object to be predicted.
In one embodiment, before the obtaining the first electricity quantity in the electricity consumption peak period, the second electricity quantity in the electricity consumption valley period, and the number of electricity consumption data points in the electricity consumption peak period, the electricity consumption valley period, and the electricity consumption level period in the total electricity consumption in the preset time period, the method further includes:
obtaining the region where the object to be predicted is located, and determining the division strategy of the electricity consumption peak time period, the electricity consumption valley time period and the electricity consumption normal time period in the preset time period according to the electricity consumption cost strategy corresponding to the region;
and determining the electricity consumption peak time period, the electricity consumption valley time period and the electricity consumption level time period in the preset time period according to the division strategy.
In one embodiment, the determining, according to the electricity cost policy corresponding to the region, a dividing policy of an electricity peak period, an electricity valley period, and an electricity level middle period in the preset time period includes:
if the power cost strategy is a time-of-use power price strategy, determining a division strategy of a power consumption peak time period, a power consumption valley time period and a power consumption normal time period in the preset time period according to the time-of-use power price strategy;
and if the power consumption cost strategy is not a time-of-use power price strategy, determining a division strategy of a power consumption peak period, a power consumption valley period and a power consumption level period in the preset time period according to a typical daily power consumption curve.
In one embodiment, the querying a preset rule table according to the level corresponding to the unit degree power generation value, the level corresponding to the load peak-valley distribution coefficient, and the level corresponding to the load interruptible coefficient to obtain the corresponding self-elastic coefficient and mutual elastic coefficient includes:
inputting the unit degree electric power values into a first membership function to obtain a plurality of first probabilities of a plurality of unit degree electric power value grades corresponding to the unit degree electric power values output by the first membership function;
inputting the load peak-valley distribution coefficient into a second membership function to obtain a plurality of second probabilities of a plurality of load peak-valley distribution coefficient grades corresponding to the load peak-valley distribution coefficient output by the second membership function;
inputting the load interruptible coefficients into a third membership function to obtain a plurality of third probabilities of a plurality of load interruptible coefficient levels corresponding to the load interruptible coefficients output by the third membership function;
inquiring a preset rule table according to the plurality of unit degree electric power generation value grades and the corresponding plurality of first probabilities, the plurality of load peak-valley distribution coefficient grades and the corresponding plurality of second probabilities, the plurality of load interruptible coefficient grades and the corresponding plurality of third probabilities to obtain a plurality of fourth probabilities and a plurality of fifth probabilities of the plurality of self-elastic coefficient grades and the plurality of mutual elastic coefficient grades under the conditions of each group of unit degree electric power generation value grades, load peak-valley distribution coefficient grades and load interruptible coefficient grades;
performing logical AND operation on the fourth probabilities and the fifth probabilities respectively, determining at least one target self-elastic coefficient grade corresponding to at least one target fourth probability with the maximum probability corresponding to the object to be predicted, and determining at least one target mutual elastic coefficient grade corresponding to at least one target fifth probability with the maximum probability corresponding to the object to be predicted;
and respectively defuzzifying the at least one target self-elasticity coefficient grade and the at least one target mutual elasticity coefficient grade according to a gravity center method to obtain the self-elasticity coefficient and the mutual elasticity coefficient of the object to be predicted.
In one embodiment, the determining an elasticity coefficient matrix according to the self-elasticity coefficient and the mutual elasticity coefficient, and determining a new electricity demand of the object to be predicted in response to the updated electricity cost in a preset time period according to the elasticity coefficient matrix, the original electricity demand of the object to be predicted in the preset time period, the original electricity cost of the object to be predicted in the preset time period, the corresponding updated electricity cost of the object to be predicted in the preset time period, and the number of electricity consumption time periods includes:
determining a first coefficient between a power consumption valley period and a power consumption valley period, a second coefficient between a power consumption level period and a power consumption level period, and a third coefficient between a power consumption peak period and a power consumption peak period in the preset time period according to the self-elasticity coefficient;
according to the mutual elasticity coefficient, determining a fourth coefficient between a power consumption peak period and a power consumption valley period, a fifth coefficient between the power consumption peak period and the power consumption level period, and a sixth coefficient between the power consumption level period and the power consumption valley period in the preset time period;
obtaining the elastic coefficient matrix according to the first coefficient, the second coefficient, the third coefficient, the fourth coefficient, the fifth coefficient and the sixth coefficient;
and obtaining a product of the elastic coefficient matrix, the original power consumption demand, and a ratio of the power consumption cost variation obtained by the difference between the original power consumption cost and the updated power consumption cost to the original power consumption cost, determining a new power consumption load variation of the object to be predicted in response to the updated power consumption cost in a preset time period according to the ratio of the product to the power consumption time period number, and adding the load variation to the original power consumption demand to obtain the updated power consumption demand.
In a second aspect, the present application provides a demand response potential prediction apparatus, comprising:
the response module is used for responding to the demand response potential prediction request, and inquiring and acquiring a unit degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient corresponding to the object to be predicted from the power database; the unit degree electricity generation value represents the influence of electricity cost on the electricity consumption of the object to be predicted; the load peak-valley distribution coefficient represents the electricity consumption time interval distribution characteristic of the electricity consumption of the object to be predicted; the load interruptible coefficient represents the influence degree of the interrupted power consumption on the production of the object to be predicted;
the query module is used for querying a preset rule table according to the grade corresponding to the unit-degree electricity generation value, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient to obtain a corresponding self-elastic coefficient and a corresponding mutual elastic coefficient; the preset rule table comprises corresponding relations among the grade corresponding to the unit degree electricity value, the grade corresponding to the load peak-valley distribution coefficient, the grade corresponding to the load interruptible coefficient, the self-elasticity coefficient and the mutual elasticity coefficient; the self-elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variation of the current time period; the mutual elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variation of other time periods;
a determining module, configured to determine an elastic coefficient matrix according to the self-elastic coefficient and the mutual-elastic coefficient, and determine a new power consumption demand of the object to be predicted, which is in response to the updated power consumption cost within a preset time period, according to the elastic coefficient matrix, an original power consumption demand of the object to be predicted within the preset time period, an original power consumption cost of the object to be predicted within the preset time period, a corresponding updated power consumption cost of the object to be predicted within the preset time period, and a number of power consumption time periods;
and the prediction module is used for determining the demand response potential of the object to be predicted according to the difference value between the new power demand and the original power demand.
In a third aspect, the present application provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method described above.
In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method described above.
According to the demand response potential prediction method, the demand response potential prediction device, the computer equipment, the storage medium and the computer program product, when a demand response potential prediction request is detected, a unit-degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient of an object to be predicted are obtained from the power database, a preset rule table is inquired according to a grade corresponding to the unit-degree electricity generation value, a grade corresponding to the load peak-valley distribution coefficient and a grade corresponding to the load interruptible coefficient, a corresponding self-elasticity coefficient and a corresponding mutual elasticity coefficient are obtained, an elasticity coefficient matrix is determined according to the self-elasticity coefficient and the mutual elasticity coefficient, and a new electricity demand of the object to be predicted, which is in response to the updated electricity demand in a preset time period, is determined according to the elasticity coefficient matrix, the original electricity demand of the object to be predicted in the preset time period, the original electricity cost of the object to be predicted in the preset time period, the updated electricity cost of the object to be predicted in the preset time period and the electricity quantity in the time period. Compared with the traditional prediction method through a physical modeling mode, the method has the advantages that the demand response potential is predicted based on the unit-degree electricity generation value, the peak-valley load coefficient, the load interruptible coefficient and the elastic coefficient matrix, and the prediction complexity is reduced.
Drawings
FIG. 1 is a diagram of an exemplary application environment for a demand response potential prediction method;
FIG. 2 is a schematic flow chart diagram illustrating a method for demand response potential prediction in one embodiment;
FIG. 3 is a schematic flow chart diagram illustrating a demand response potential prediction method according to another embodiment;
FIG. 4 is a schematic interface diagram of the demand response potential prediction step in one embodiment;
FIG. 5 is a schematic interface diagram of the demand response potential prediction step in one embodiment;
FIG. 6 is a block diagram of a demand response potential prediction apparatus in one embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The demand response potential prediction method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server. The terminal 102 may obtain the unit-degree electricity generation value, the load peak-valley distribution coefficient, and the load interruptible coefficient corresponding to the object with prediction from the database of the server 104 when receiving the demand response potential prediction request, so that the terminal 102 may determine the corresponding elastic coefficient matrix based on these coefficients, and further obtain the demand response potential of the object with prediction. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, a demand response potential prediction method is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:
step S202, responding to a demand response potential prediction request, and inquiring and acquiring a unit degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient corresponding to an object to be predicted from a power database; the unit degree electricity generation value represents the influence of electricity cost on electricity consumption of an object to be predicted; the load peak-valley distribution coefficient represents the influence of electricity consumption time period distribution on electricity consumption of an object to be predicted; the load interruptible coefficient represents the degree of influence of the interrupting power consumption on the production of the object to be predicted.
The demand response is short for power demand response, and means that after receiving a direct compensation notification of an inductive load reduction or a power consumption cost increase signal sent by a power supplier, a power consumer changes its inherent conventional power consumption mode to achieve a short-term behavior of reducing or pushing a certain period of power consumption load. Demand response potential refers to the ability of a user to participate in a demand response program to adjust load, including both load increase and load decrease adjustment directions. The object to be predicted may be an object for which demand response potential prediction is required, such as industrial users of metal manufacturing plants and textile plants. The terminal can predict the demand response potential of the object to be predicted. The prediction can be carried out through instruction triggering, and the terminal can inquire and acquire a unit-degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient corresponding to an object to be predicted from the power database when a demand response potential prediction request triggered by a user is detected; the unit degree electricity generation value represents the influence of electricity cost on the electricity consumption of the object to be predicted; the load peak-valley distribution coefficient represents the influence of electricity consumption time interval distribution on electricity consumption of an object to be predicted; the load interruptible coefficient represents the influence degree of the interruption power consumption on the object to be predicted. The unit degree electricity generation value can be obtained by calculation according to the annual output value increment and the annual electricity consumption of the object to be predicted; the load peak-valley distribution coefficient can be obtained according to the power consumption of the object to be predicted in the peak-valley period; the load interruptible coefficient may be obtained according to the power consumption behavior of the object to be predicted.
Specifically, a start button for demand response potential prediction may be set in the display device of the terminal, and a user may click the start button in the display device of the terminal, so that the terminal may receive a demand response potential prediction request, query the power database, and obtain information corresponding to an object to be predicted. Price-based demand response refers to that power consumers adjust power consumption behaviors and demands along with dynamic changes of power prices so as to achieve the effect of reducing power consumption. The price type demand response mainly includes time of use electricity prices and peak electricity prices. The time-of-use electricity price scheme is that 24 hours a day are divided into a plurality of time intervals according to the running condition of a system, and electricity charges are charged according to different charging standards in each time interval to change the electricity consumption behavior of a user.
Step S204, inquiring a preset rule table according to the grade corresponding to the unit degree electricity generation value, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient to obtain a corresponding self-elasticity coefficient and a corresponding mutual elasticity coefficient; the preset rule table comprises corresponding relations among grades corresponding to unit-degree electricity generation values, grades corresponding to load peak-valley distribution coefficients and grades corresponding to load interruptible coefficients, self-elasticity coefficients and mutual elasticity coefficients; the self-elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variable quantity of the current time period; and the mutual elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variable quantity of other time periods.
After the terminal obtains the unit-degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient, the terminal can respectively obtain the unit-degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient, and obtain the grade corresponding to the unit-degree electricity generation value, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient. The above-mentioned grades can have multiple grades, take the unit degree electric production value as an example, its correspondent grade can be low, medium, high three grades; each grade can be determined based on the probability value belonging to each grade output by the membership function after the unit-degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient are respectively input into the corresponding membership function. After the terminal obtains the grade corresponding to the unit-degree electricity generation value, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient, a preset rule table can be inquired based on each grade to obtain the corresponding self-elasticity coefficient and mutual elasticity coefficient. The preset rule table comprises corresponding relations between a grade corresponding to a unit degree electricity value, a grade corresponding to a load peak-valley distribution coefficient, a grade corresponding to a load interruptible coefficient, a self-elastic coefficient and a mutual elastic coefficient. The self-elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity cost variation of the current time period; the mutual elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variation of other time periods.
Specifically, the terminal may combine the multiple levels corresponding to the unit degree electrical output value, the multiple levels corresponding to the load peak-valley distribution coefficient, and the multiple levels corresponding to the load interruptible coefficient to obtain multiple level conditions, where each level condition includes a level corresponding to one unit degree electrical output value, a level corresponding to the load peak-valley distribution coefficient, and a level corresponding to the load interruptible coefficient, and determines a self-elastic coefficient level and a mutual-elastic coefficient level corresponding to each level condition to form a preset rule table. Therefore, the terminal can form grade conditions through the grade corresponding to the unit degree electricity value of the object to be predicted, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient, a preset rule table is inquired to obtain the corresponding self-elasticity coefficient grade and mutual elasticity coefficient grade, and the terminal can convert the self-elasticity coefficient grade and the mutual elasticity coefficient grade through a gravity center method to obtain the self-elasticity coefficient and the mutual elasticity coefficient corresponding to the object to be predicted.
Step S206, an elasticity coefficient matrix is determined according to the self elasticity coefficient and the mutual elasticity coefficient, and a new electricity demand of the object to be predicted responding to the updated electricity cost in the preset time period is determined according to the elasticity coefficient matrix, the original electricity demand of the object to be predicted in the preset time period, the original electricity cost of the object to be predicted in the preset time period, the corresponding updated electricity cost of the object to be predicted in the preset time period and the number of the electricity consumption time periods.
After the terminal acquires the self-elasticity coefficient and the mutual elasticity coefficient, an elasticity coefficient matrix can be determined according to the self-elasticity coefficient and the mutual elasticity coefficient. The self-elasticity coefficient and the mutual elasticity coefficient represent the influence of the price variation of the electricity utilization time interval on the electricity utilization demand, and the influence of the price variation of the electricity utilization time interval on the electricity utilization demand of the time interval and the influence of the price variation of the electricity utilization on the electricity utilization demand of other time intervals are included. The terminal can determine the comparison value of each period in the elastic coefficient matrix according to the self elastic coefficient and the mutual elastic coefficient, including the comparison among the power consumption valley period, the power consumption level period and the power consumption peak period, so as to form the elastic coefficient matrix.
After the terminal obtains the elastic coefficient matrix, the terminal can determine the new power demand of the object to be predicted in response to the updated power cost in the preset time period according to the elastic coefficient matrix, the original power demand of the object to be predicted in the preset time period, the original power cost of the object to be predicted in the preset time period, the corresponding updated power cost of the object to be predicted in the preset time period and the number of the power consumption time periods. For example, the terminal determines an electricity consumption curve of the object to be predicted in a preset time period based on the original electricity consumption cost, and determines an electricity consumption curve of a new electricity consumption of the object to be predicted, which responds to the updated electricity consumption cost in the preset time period, based on the updated electricity consumption cost and the number of the electricity consumption time periods of the object to be predicted. The original power consumption cost may be a power consumption cost when the time-of-use power price calculation is not adopted at a certain time, and the updated power consumption cost may be a power consumption cost when the time-of-use power price calculation is adopted at a certain time. The electricity consumption period number may be the number of the time period required to adjust the electricity price included in one day after the time-of-use electricity price is adopted. The original power demand may be a load amount when the target to be predicted adjusts the power consumption in response to a change in the power consumption cost. The new electricity demand may be a load amount when the electricity consumption is adjusted in response to a change in electricity consumption cost of the object to be predicted.
And step S208, determining the demand response potential of the object to be predicted according to the difference value between the new power consumption demand and the original power consumption demand.
The preset time period can be a 24-hour time period, the new power demand can include new power demand at each time in a day, the original power demand can include original power demand at each time in a day, the terminal can respectively form an original power curve and a new power curve according to the original power demand at each time and the new power demand at each time, and the terminal can determine demand response potential of the object to be predicted according to a difference value between the new power demand and the original power demand. For example, the terminal may determine a difference in power demand by comparing the original power usage curve and the new power usage curve, and determine a demand response potential of the object to be predicted based on the difference in power demand. For example, when the difference value of the power consumption demand quantity is larger, the demand response potential of the object to be predicted is larger. The terminal can also carry out potential prediction on demand resources of the object to be predicted through a potential prediction model of price type demand response. The potential prediction model of the price type demand response is constructed according to the elastic coefficient matrix, the original power consumption demand of the object to be predicted in the preset time period, the original power consumption cost of the object to be predicted in the preset time period, the corresponding updated power consumption cost of the object to be predicted in the preset time period and the number of the power consumption time periods. Therefore, the terminal can obtain the demand response potential of the object to be predicted based on the electricity consumption cost change.
According to the demand response potential prediction method, when a demand response potential prediction request is detected, a unit degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient of an object to be predicted are obtained from an electricity database, a preset rule table is inquired according to a grade corresponding to the unit degree electricity generation value, a grade corresponding to the load peak-valley distribution coefficient and a grade corresponding to the load interruptible coefficient, a corresponding self-elasticity coefficient and a corresponding mutual elasticity coefficient are obtained, an elasticity coefficient matrix is determined according to the self-elasticity coefficient and the mutual elasticity coefficient, and a new electricity demand of the object to be predicted, which is in response to the updated electricity demand in a preset time period, is determined according to the elasticity coefficient matrix, the original electricity cost of the object to be predicted in the preset time period, the updated electricity cost of the object to be predicted in the preset time period and the number of the electricity periods. Compared with the traditional prediction method through a physical modeling mode, the method has the advantage that the prediction complexity is reduced by predicting the demand response potential based on the unit-degree electricity production value, the peak-valley load coefficient, the load interruptible coefficient and the elastic coefficient matrix.
In one embodiment, obtaining the unit degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient corresponding to the object to be predicted comprises: acquiring annual output value increment and annual power consumption of an object to be predicted in a historical time period; acquiring total power consumption of an object to be predicted within a preset time period, wherein the preset time period comprises a power consumption peak time period, a power consumption valley time period and a power consumption middle time period; determining the unit-degree electricity generation value of the object to be predicted according to the annual output value increment and the annual electricity consumption of the historical time period; acquiring first electric quantity at a power consumption peak period, second electric quantity at a power consumption valley period and power consumption data points at the power consumption peak period, the power consumption valley period and the power consumption level period in total electric quantity in a preset time period, and acquiring a load peak-valley distribution coefficient according to the first electric quantity, the second electric quantity and the power consumption data points; and determining a load interruptible coefficient corresponding to the object to be predicted according to the electricity utilization behavior of the object to be predicted.
In this embodiment, the terminal may obtain the unit-degree electricity generation value, the load peak-valley distribution coefficient, and the load interruptible coefficient of the object to be predicted in different calculation manners. For the unit-degree electricity generation value, the terminal can acquire the annual generation value increment and the annual electricity consumption in the historical time period of the object to be predicted. Wherein, include power consumption peak period, power consumption valley period and power consumption level period in the preset time quantum, the division tactics of power consumption peak period, power consumption valley period and power consumption level period can be different based on the difference of power consumption cost tactics, for example, in an embodiment, obtain the first electric quantity of power consumption peak period in the total power consumption in the preset time quantum, before the second electric quantity of power consumption valley period and the power consumption data point number of power consumption peak period, power consumption valley period and power consumption level period, still include: the method comprises the steps of obtaining an area where an object to be predicted is located, and determining a power utilization peak period, a power utilization valley period and a power utilization middle period division strategy in a preset time period according to a power utilization cost strategy corresponding to the area; and determining a power consumption peak time period, a power consumption valley time period and a power consumption level time period in a preset time period according to a dividing strategy. In this embodiment, the terminal may detect a region where an object to be predicted is located, and obtain an electricity cost policy corresponding to the region, where the electricity cost may be an electricity price, and the terminal may determine, according to the electricity cost policy of the region, a partitioning policy of an electricity peak period, an electricity valley period, and an electricity level period in a preset time period, and determine, according to the partitioning policy, a partitioning policy of the electricity peak period, the electricity valley period, and the electricity level period in the preset time period.
The judgment of the electricity cost strategy can be specifically the judgment of whether the terminal has the time-of-use electricity price strategy in the region. For example, in one embodiment, determining a dividing policy of a power consumption peak period, a power consumption valley period, and a power consumption middle period in a preset time period according to a power consumption cost policy corresponding to a region includes: if the electricity cost strategy is a time-of-use electricity price strategy, determining a division strategy of an electricity peak time period, an electricity valley time period and an electricity middle time period in a preset time period according to the time-of-use electricity price strategy; and if the electricity cost strategy is not the time-of-use electricity price strategy, determining a division strategy of an electricity peak period, an electricity valley period and an electricity level period in a preset time period according to a typical daily electricity quantity curve. In this embodiment, the terminal may determine whether the area where the object to be predicted is located has a time-of-use electricity price policy, and if the electricity price policy of the area where the object to be predicted is located is the time-of-use electricity price policy, the terminal may determine, according to the time-of-use electricity price policy, a division policy of a peak electricity utilization period, a valley electricity utilization period, and a middle electricity utilization period in a preset time period, where the division policy is related to a time-of-use manner of the time-of-use electricity price policy; if the electricity cost strategy is not a time-of-use electricity price strategy, the terminal can determine the division strategies of the electricity peak time period, the electricity valley time period and the electricity utilization level time period in the preset time period according to the typical daily electricity quantity curve of the power industry, namely the division strategies are related to the electricity consumption change of the typical day.
The terminal can obtain the annual output value increment and the annual power consumption of the target original object to be predicted in the historical time period; and acquiring the total power consumption of the object to be predicted in a preset time period, wherein the preset time period comprises a power consumption peak time period, a power consumption valley time period, a power consumption normal time period and the distribution condition of each time period.
When the terminal acquires the output value increment and the total power consumption of the object to be predicted within the preset time period, the object to be predicted needs to be determined first. For example, in one embodiment, obtaining the output value increase amount and the total power consumption amount of the object to be predicted in the preset time period includes: acquiring a plurality of original objects to be predicted, and acquiring an original output value increment and an original total power consumption of each original object to be predicted in a preset time period; and performing descending sorting on the plurality of original objects to be predicted according to the original total power consumption, acquiring a target original object to be predicted with the ranking smaller than a preset ranking threshold value as the object to be predicted, and acquiring an original output value increment and an original total power consumption corresponding to the target original object to be predicted as the output value increment and the total power consumption of the object to be predicted. In this embodiment, the terminal may determine the object to be predicted by a conditional screening method, the terminal may obtain a plurality of original objects to be predicted, and obtain an original output value increment and an original total power consumption of each original object to be predicted in a preset time period, and the terminal may perform descending order sorting on the plurality of original objects to be predicted based on the original total power consumption, and obtain a target original object to be predicted whose rank is smaller than a preset rank threshold, as the object to be predicted that participates in demand response potential prediction. The terminal can obtain the original output value increment and the original total power consumption corresponding to the target original object to be predicted as the output value increment and the total power consumption of the object to be predicted.
Specifically, the terminal can classify according to the industries of the power consumers, collect power load data of the maximum load day of each industry in a preset area, and represent the power load data by 96 points, that is, one point is taken every 15 minutes in one day, wherein the time interval for acquiring the data can be determined according to actual needs. And the terminal can also obtain annual load data and relevant economic statistical data of each industry, and the terminal can also obtain the measuring and calculating ranges of price elastic coefficient matrixes in different regions.
After the terminal acquires the annual output value increment and the annual power consumption of the historical time period of the object to be predicted, the unit-degree power generation value of the object to be predicted can be determined according to the annual output value increment and the total power consumption. Specifically, the above formula for calculating the unit electricity consumption value may be as follows:
Figure BDA0003821333810000111
wherein alpha is a unit degree electric power value, P gdp For annual yield increase, Q, in historical time periods of the object to be predicted l The annual power consumption of the object to be predicted in the historical time period is used. The unit degree electricity production value alpha is used for judging the sensitivity degree of the industry production to electricity consumption cost, when the unit degree electricity production value alpha of the industry is low, the sensitivity of the industry electricity price is considered to be high, namely the fluctuation of the electricity price has great influence on the cost and the income of the industry, the electricity consumption mode of the industry is further influenced, and the demand response potential of the industry is large. When the specific electric production value alpha of the industry is higher, the price sensitivity of the industry is considered to be lower, and the demand response potential of the industry is smaller.
For the load peak-valley distribution coefficient, the terminal can acquire the first electric quantity in the electricity consumption peak period, the second electric quantity in the electricity consumption valley period and the electricity consumption data points in the peak period and the valley period in the preset time period, and determine the load peak-valley distribution coefficient according to the first electric quantity, the second electric quantity and the electricity consumption data points. The number of the power consumption data points may be a time point set according to a preset time interval in the preset time period, specifically, the preset time period may be a time of a day, the terminal may set one power consumption data point for every fifteen minutes, and the terminal may include 96 power consumption data points in a day, and the power consumption peak time period, the power consumption valley time period, and the power consumption time period have corresponding power consumption data points. The object to be predicted can be in a preset area, and the terminal can adopt a time-of-use electricity price scheme to the preset area. The terminal can divide the time in a preset time period, for example, a day into three time periods, namely, a power utilization peak time period, a power utilization valley time period and a power utilization middle time period according to the time-of-use electricity price scheme or the load distribution condition of the maximum load day in a preset area, wherein the high electricity price time period corresponds to the power utilization peak time period, the power utilization valley time period corresponds to the power utilization middle time period, and the low electricity price time period corresponds to the power utilization valley time period. The above formula for calculating the load peak-to-valley distribution coefficient can be as follows:
Figure BDA0003821333810000112
wherein beta is a load peak-to-valley distribution coefficient,
Figure BDA0003821333810000113
as the total load of the peak period of electricity usage,
Figure BDA0003821333810000114
for the total load of the electricity consumption peak period, m is the number of electricity consumption peak periods, also referred to as electricity consumption data points of the electricity consumption peak period, and n is the number of electricity consumption valley periods, also referred to as electricity consumption data points of the electricity consumption valley period.
The terminal can judge the willingness and degree of the industry to participate in price type demand response based on the load peak-valley distribution coefficient beta, when the load peak-valley distribution coefficient beta is larger than 1, the unit load capacity of the industry in the peak time period is larger than that of the valley time period, the industry has strong load reduction and load transfer potentials, and the higher the load peak-valley distribution coefficient beta of the industry is, the greater the load reduction and transfer potentials of the industry are. When the peak-to-valley load correlation coefficient beta is less than 1, the unit load capacity of the industry in the valley period is larger than that of the peak period, and the load reduction or transfer potential of the industry is considered to be low.
For the load interruptible coefficient, the terminal can determine the load interruptible coefficient corresponding to the object to be predicted according to the power utilization behavior of the object to be predicted. The electricity consumption behavior can be a related behavior of how electricity is used for production when the object to be predicted produces electricity, and the electricity consumption behavior represents the dependency of the production behavior of the object to be predicted on the electricity. Specifically, the terminal can determine the load interruptible coefficient theta by analyzing the electricity utilization characteristics of the industry to which the object to be predicted belongs and the electricity utilization logic of the industry, specifically, the load electricity utilization law, the electricity utilization mode and the industry characteristics of the industry are obtained through collection, research and analysis of related data. For example, in the chemical material production industry, the main electrical loads come from processing furnaces and production lines, the interruption of load or low-load operation has a great safety risk, the difficulty in stopping the furnaces and recovering the production is great, potential safety hazards are easily formed, and the whole set of production system and personal safety accidents can be caused. Due to this electrical property of the chemical material production industry, the industry is considered to have a low capacity for load shifting and load interruption. Defining the load interruptible coefficient theta to be 0 when the industry has no load transfer capability at all, and the load interruptible coefficient theta to be 1 when the industry has strong load transfer capability. Wherein, the capacity of load transfer represents the capacity of the object to be predicted whether to produce through other energy sources when the power is cut off.
Through the embodiment, the terminal can respectively determine the unit-degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient corresponding to the object to be predicted based on various modes, so that the terminal can predict the demand response potential of the object to be predicted based on the unit-degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient, and the complexity of the demand response potential prediction is reduced.
In one embodiment, querying a preset rule table according to a grade corresponding to a unit degree electric power value, a grade corresponding to a load peak-valley distribution coefficient and a grade corresponding to a load interruptible coefficient to obtain a corresponding self-elastic coefficient and a corresponding mutual elastic coefficient includes: inputting the unit degree electric power values into a first membership function to obtain a plurality of first probabilities of a plurality of unit degree electric power value grades corresponding to the unit degree electric power values output by the first membership function; inputting the load peak-valley distribution coefficient into a second membership function to obtain a plurality of second probabilities of a plurality of load peak-valley distribution coefficient grades corresponding to the load peak-valley distribution coefficient output by the second membership function; inputting the load interruptible coefficients into a third membership function to obtain a plurality of third probabilities of a plurality of load interruptible coefficient levels corresponding to the load interruptible coefficients output by the third membership function; inquiring a preset rule table according to the multiple unit-degree electric power value grades, the corresponding multiple first probabilities, the multiple load peak-valley distribution coefficient grades, the corresponding multiple second probabilities, the multiple load interruptible coefficient grades and the corresponding multiple third probabilities to obtain multiple fourth probabilities and multiple fifth probabilities of the multiple self-elastic coefficient grades and the multiple mutual elastic coefficient grades under the conditions of each group of unit-degree electric power value grades, each group of load peak-valley distribution coefficient grades and each group of load interruptible coefficient grades; respectively carrying out logical AND operation on the plurality of fourth probabilities and the plurality of fifth probabilities, determining at least one target self-elasticity coefficient grade corresponding to at least one target fourth probability with the maximum probability corresponding to the object to be predicted, and determining at least one target mutual elasticity coefficient grade corresponding to at least one target fifth probability with the maximum probability corresponding to the object to be predicted; and performing defuzzification on at least one target self-elasticity coefficient grade and at least one target mutual elasticity coefficient grade respectively according to a gravity center method to obtain the self-elasticity coefficient and the mutual elasticity coefficient of the object to be predicted.
In this embodiment, the unit-degree power generation value, the load peak-valley distribution coefficient, and the load interruptible coefficient may have corresponding levels. The terminal can determine the grade of each parameter through the corresponding membership function. The terminal can input the unit degree electric production value into the first membership function to obtain a plurality of first probabilities of a plurality of unit degree electric production value grades corresponding to the unit degree electric production value output by the first membership function, namely the unit degree electric production value grades can be multiple, and the terminal can obtain the first probabilities that the unit degree electric production values belong to the levels respectively based on the first membership function to obtain the first probabilities. The terminal may further input the load peak-valley distribution coefficient into a second membership function to obtain a plurality of second probabilities of a plurality of load peak-valley distribution coefficient levels corresponding to the load peak-valley distribution coefficient output by the second membership function, that is, there may be a plurality of load peak-valley distribution coefficient levels, and the terminal may obtain, based on the second membership function, second probabilities that the load peak-valley distribution coefficients respectively belong to the respective levels, to obtain a plurality of second probabilities. The terminal may further input the load interruptible coefficients into a third membership function to obtain a plurality of third probabilities of a plurality of load interruptible coefficient levels corresponding to the load interruptible coefficients output by the third membership function, that is, there may be a plurality of load interruptible coefficient levels, and the terminal may obtain, based on the third membership function, third probabilities that the load interruptible coefficients respectively belong to the respective levels, to obtain a plurality of third probabilities. The determination of the above-mentioned levels may be a blurring process. The terminal can form a group of judgment conditions by one unit degree electricity value grade, one load peak-valley distribution coefficient grade and one load interruptible coefficient grade. The terminal can query a preset rule table according to the unit degree electric power value grades, the corresponding first probabilities, the load peak-valley distribution coefficient grades, the corresponding second probabilities, the load interruptible coefficient grades and the corresponding third probabilities to obtain a plurality of fourth probabilities and a plurality of fifth probabilities of the self-elastic coefficient grades and the mutual elastic coefficient grades under the conditions of each group of unit degree electric power value grades, load peak-valley distribution coefficient grades, load interruptible coefficient grades and the corresponding third probabilities. Therefore, the terminal can respectively carry out logical AND operation on the fourth probabilities and the fifth probabilities, determine at least one target self-elasticity coefficient grade corresponding to at least one target fourth probability with the maximum probability corresponding to the object to be predicted, and determine at least one target mutual elasticity coefficient grade corresponding to at least one target fifth probability with the maximum probability corresponding to the object to be predicted. After the terminal determines at least one target self-elastic coefficient grade and at least one target mutual elastic coefficient grade with the highest probability, defuzzification can be respectively carried out on the at least one target self-elastic coefficient grade and the at least one target mutual elastic coefficient grade according to a gravity center method, and the self-elastic coefficient and the mutual elastic coefficient of the object to be predicted are obtained.
Specifically, the process of obtaining the level may be a process of fuzzification, and for an accurate input value, the process of finding the corresponding language variable value, i.e. the fuzzy variable value, and then describing the language variable value in the form of natural language is referred to as fuzzification. According to the proper natural language value, the corresponding membership degree is obtained, and the natural language variable becomes a fuzzy subset. The terminal can be provided with a fuzzy controller, and the terminal can input the unit-degree electricity production value alpha, the load peak-valley distribution coefficient beta and the load interruptible coefficient theta into the fuzzy controller, and respectively use three fuzzy sets for description, and the grade description of each parameter can be as follows: unit degree electricity generation value: low (SA), medium (MA) and high (LA); load peak-to-valley distribution coefficient: low (SB), medium (MB) and high (LB); load interruptible coefficient: low (SC), medium (MC) and high (LC). For coefficient of self-elasticity e 1 And coefficient of mutual elasticity e 2 The terminal can determine the coefficient of self-elasticity e by the following description 1 Grade and coefficient of mutual elasticity e 2 Grade (2): coefficient of self-elasticity e 1 : very low (VS 1), low (S1), medium (M1), high (L1), very high (VL 1); coefficient of mutual elasticity e 2 : very low (VS 2), low (S2), medium (M2), high (L2), very high (VL 2). The terminal can obtain the probability that each parameter belongs to each grade respectively, and takes a unit degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient as a group of judgment conditions, determines the elastic coefficient and the probability thereof under each group of conditions, and forms a preset rule table. The table may be as follows:
Figure BDA0003821333810000141
wherein, in the above table, 27 fuzzy rules are described, and for the first rule: "If α is SA, β is SB AND θ is SC, THEN e 1 is M1 AND e 2 is VS2", i.e." if the electrical power value α per degree is small, the load peak-to-valley distribution coefficient β is low, and the load interruptible coefficient θ is small, the self-elastic coefficient e 1 Is (1) in (1); coefficient of mutual elasticity e 2 Is very low. When the terminal determines the target self-elastic coefficient and the target mutual elastic coefficient, the terminal may first substitute the three coefficient indexes of the object to be predicted into corresponding membership functions, and then calculate membership degrees corresponding to the input indexes. And then searching matched fuzzy rules in a fuzzy rule base through the membership degree, namely determining the grade corresponding to the coefficient and the probability of the grade. The terminal can perform rule premise reasoning: within each rule, the antecedents of the rules can be deduced through the AND relation. For example, the rules are IF X is PA and Y is NA the Z is VS. Then, the membership degree of the precondition is obtained by taking a small operation, and the membership degree of the precondition of the rule is min (mu) PA(X) ，μ NA(Y) )μ PA(X) The expression X is the degree of membership of PA, which may also be referred to as probability. The terminal can also collect all membership degrees of the same type of rule premises to obtain the total membership degree output of the fuzzy system, and the terminal can obtain at least one target self-elasticity coefficient grade and at least one target mutual elasticity coefficient grade with the maximum membership degree, namely the maximum probability value, from the total membership degree output. After the terminal obtains at least one target self-elastic coefficient grade and at least one target mutual elastic coefficient grade, defuzzification can be carried out on the at least one target self-elastic coefficient grade and the at least one target mutual elastic coefficient grade based on an area gravity center method, and the self-elastic coefficient and the mutual elastic coefficient of the object to be predicted are obtained. And the terminal can obtain a price elastic coefficient matrix E based on the self elastic coefficient and the mutual elastic coefficient.
Through the embodiment, the terminal can determine the grade of each parameter corresponding to the object to be predicted based on the membership function, and determine the self-elasticity coefficient and the mutual elasticity coefficient based on the grade and the preset rule table, so that the terminal can construct an elasticity coefficient matrix based on the self-elasticity coefficient and the mutual elasticity coefficient, predict the demand response potential of the object to be predicted, and reduce the prediction complexity.
In one embodiment, determining an elasticity coefficient matrix according to the self-elasticity coefficient and the mutual elasticity coefficient, and determining a new electricity demand of the object to be predicted in response to the updated electricity cost in the preset time period according to the elasticity coefficient matrix, the original electricity demand of the object to be predicted in the preset time period, the original electricity cost of the object to be predicted in the preset time period, the corresponding updated electricity cost of the object to be predicted in the preset time period, and the number of electricity consumption time periods, includes: determining a first coefficient between a power consumption valley period and a power consumption valley period, a second coefficient between a power consumption level period and a third coefficient between a power consumption peak period and a power consumption peak period in a preset time period according to the self-elasticity coefficient; determining a fourth coefficient between a power consumption peak period and a power consumption valley period, a fifth coefficient between the power consumption peak period and the power consumption level period and a sixth coefficient between the power consumption level period and the power consumption valley period in a preset time period according to the mutual elasticity coefficient; obtaining an elastic coefficient matrix according to the first coefficient, the second coefficient, the third coefficient, the fourth coefficient, the fifth coefficient and the sixth coefficient; the method comprises the steps of obtaining a product of a ratio of power consumption cost variation obtained by a difference value of an elasticity coefficient matrix, original power consumption demand, original power consumption cost and updated power consumption cost and a ratio of the original power consumption cost, determining a new power consumption load variation of an object to be predicted, which is in response to the updated power consumption cost in a preset time period, according to the product and the ratio of the number of power consumption time periods, and obtaining the updated power consumption demand according to the sum of the new power consumption load variation and the original power consumption demand.
In this embodiment, after obtaining the self-elastic coefficient and the mutual-elastic coefficient of the object to be predicted, the terminal may determine, according to the self-elastic coefficient, a first coefficient between the power consumption valley period and the power consumption valley period, a second coefficient between the power consumption level period and the power consumption level period, and a third coefficient between the power consumption peak period and the power consumption peak period within the preset time period, and determine, according to the mutual-elastic coefficient, a fourth coefficient between the power consumption peak period and the power consumption valley period, a fifth coefficient between the power consumption peak period and the power consumption level period, and a sixth coefficient between the power consumption level period and the power consumption valley period within the preset time period, that is, each elastic coefficient represents an influence relationship between different power consumption periods. The terminal may obtain an elastic coefficient matrix according to the first coefficient, the second coefficient, the third coefficient, the fourth coefficient, the fifth coefficient, and the sixth coefficient. After the terminal obtains the elastic coefficient matrix, the product of the elastic coefficient matrix, the original power consumption demand, the power consumption cost variation obtained by the difference value of the original power consumption cost and the updated power consumption cost and the ratio of the original power consumption cost can be obtained, the new power consumption load variation of the object to be predicted, which is in response to the updated power consumption cost in the preset time period, is determined according to the ratio of the product and the power consumption time period number, and the updated power consumption demand can be obtained by adding the original power consumption demand to the load variation.
Specifically, the elastic coefficient matrix E may be as follows:
Figure BDA0003821333810000161
wherein epsilon is a demand elasticity coefficient, also called e, which is related to the price change of the time interval and the price change of other time intervals, and the terminals can respectively use the demand elasticity coefficient epsilon ii And cross elastic coefficient epsilon ij Representing the portion relating to price changes for this time period and the portion relating to price changes for other time periods. Epsilon ii The influence of the electricity price change in the period i on the requirement in the period i is represented, and the value of the change is usually negative; epsilon ij Indicating the effect of the change in electricity prices during the j time period on the demand during the i time period, which is typically positive in value. After the terminal obtains the elastic coefficient matrix, the terminal can determine the new power demand based on the following formula:
Figure BDA0003821333810000162
wherein Q is the original power demand corresponding to a certain time, and Q' is the demand response corresponding to a certain timeThe latter power demand; p is the original electricity cost corresponding to a certain moment, and delta P is the variable quantity of the electricity cost corresponding to the demand response at a certain moment; e is a price elastic coefficient matrix; n is the number of divided periods per day.
Through the embodiment, the terminal can determine the new electricity demand after the response electricity price corresponding to the object to be predicted is updated based on the elasticity coefficient matrix determined by the self elasticity coefficient and the mutual elasticity coefficient, and the terminal can predict the demand response of the object to be predicted based on the new electricity demand and the original electricity demand, so that the prediction complexity is reduced.
In this embodiment, after the terminal determines that the object to be predicted responds to the new power consumption demand with the changed power consumption cost, the terminal may obtain a difference between the new power consumption demand and the original power consumption demand. The new power demand and the original power demand both can include demands of multiple time points, and the terminal can construct a power utilization curve according to the demands of the multiple time points and determine the demand response potential of the object to be predicted based on the difference of the power utilization curves.
Through the embodiment, the terminal can determine the demand response potential of the object to be predicted based on the difference value between the new power demand and the original power demand, and the prediction complexity is reduced.
In one embodiment, determining the demand response potential of the object to be predicted according to the difference between the new power demand and the original power demand comprises: if the difference value between the new power consumption demand and the original power consumption demand is larger than a preset power consumption demand threshold, determining that the demand response potential of the object to be predicted under the current power consumption cost is a first level; if the difference value between the new power consumption demand and the original power consumption demand is smaller than or equal to a preset power consumption demand threshold, determining that the demand response potential of the object to be predicted under the current power consumption cost is in a second level; wherein the first level is greater than the second level.
In this embodiment, after the terminal determines that the object to be predicted responds to the new power consumption demand with the changed power consumption cost, the terminal may obtain a difference between the new power consumption demand and the original power consumption demand, and if the terminal detects that the difference between the new power consumption demand and the original power consumption demand is greater than a preset power consumption demand threshold, the terminal may determine that the demand response potential of the object to be predicted at the current power consumption cost is of a first level. If the terminal detects that the difference value between the new power consumption demand and the original power consumption demand is smaller than or equal to the preset power consumption demand threshold, the terminal can determine that the demand response potential of the object to be predicted is in a second level at the current power consumption cost; the first grade is larger than the second grade, the demand response potential of the object to be predicted represented by the first grade is larger, and the demand response potential of the object to be predicted represented by the second grade is smaller. The new power demand and the original power demand both can include demands of multiple time points, and the terminal can construct a power utilization curve according to the demands of the multiple time points and determine the demand response potential of the object to be predicted based on the difference of the power utilization curves.
Through the embodiment, the terminal can determine the demand response potential of the object to be predicted based on the difference value between the new power demand and the original power demand, and the prediction complexity is reduced.
In one embodiment, as shown in fig. 3, fig. 3 is a flow chart of a demand response potential prediction method in another embodiment. In the embodiment, the terminal calculates 3 coefficient indexes including a unit-degree electricity generation value alpha, a peak-valley load correlation coefficient beta and a load interruptible coefficient theta by designing a set of index system, obtains a correlation coefficient index of a selected industry, obtains a mapping relation between the index system and an elastic coefficient matrix by establishing a fuzzy control model, further quantitatively analyzes to obtain a demand elastic matrix E, and finally measures and calculates the adjustable potential of demand-side resources based on time-of-use electricity prices through the new electricity demand formula. The method specifically comprises the following steps: the terminal collects 96 points of power load data of each row of maximum load day (one point is taken every 15 minutes in one day), industry annual load data and related economic statistical data in a certain area according to industry classification of power users in the whole society, and obtains measurement and calculation ranges of price elastic coefficient matrixes in different regions at home and abroad. The terminal can carry out primary screening on industries and carry out primary screening on the selected industries according to objects needing to be analyzed. The terminal can calculate the unit degree electricity generation value alpha through the formula, the unit degree electricity generation value alpha is used for judging the sensitivity degree of the industry production to electricity consumption cost, when the unit degree electricity generation value alpha of the industry is low, the industry electricity price sensitivity is considered to be high, namely the fluctuation of the electricity price has great influence on the cost and the income of the industry, the electricity consumption mode of the industry is further influenced, and the demand response potential of the industry is large. When the specific-degree electricity generation value alpha of the industry is higher, the electricity price sensitivity of the industry is considered to be lower, and the demand response potential of the industry is smaller. The terminal can also calculate a load peak-valley distribution coefficient beta, judges the willingness and degree of the industry to participate in the price type demand response through the load peak-valley distribution coefficient beta, and when the load peak-valley distribution coefficient beta is larger than 1, shows that the unit load capacity of the industry in a peak period is larger than that of a valley period, the industry has strong load reduction and load transfer potentials, and the higher the load peak-valley distribution coefficient beta of the industry is, the greater the load reduction and transfer potentials of the industry are. When the peak-to-valley load correlation coefficient beta is less than 1, the unit load capacity of the industry in the valley period is larger than that of the peak period, and the load reduction or transfer potential of the industry is considered to be low. The terminal can also calculate the load interruptible coefficient theta, and the load interruptible coefficient theta is determined by analyzing the power utilization characteristics of the industry and the power utilization logic of the industry, specifically, the load power utilization rule, the power utilization mode and the industry characteristics of the industry are obtained by collecting, researching and analyzing relevant data. For example, in the chemical material production industry, the main electrical loads are from a processing furnace and a production line, the interruption of load or low-load operation has a large safety risk, the difficulty in stopping the furnace and recovering the production is high, potential safety hazards are easily formed, and the whole set of production system and personal safety accidents can be caused. Due to this electrical property of the chemical material production industry, the industry is considered to have a low capacity for load shifting and load interruption. The load interruptible coefficient theta is defined as 0 when the industry has no load transfer capability at all, and as 1 when the industry has a strong load transfer capability.
The terminal can also describe the coefficients through a natural language, namely, the grade of each coefficient is determined through fuzzification processing, a fuzzy rule table, namely the preset rule table, is formulated, and the elastic coefficient matrix E is determined based on the preset rule table. Specifically, the terminal substitutes three coefficient indexes calculated by each industry into a membership function, and further calculates the membership degree corresponding to each input index. And then searching matched fuzzy rules in the fuzzy rule base through the membership degree. And carrying out rule premise reasoning, which comprises the following steps: within each rule, the antecedents of the rules can be deduced through the AND relation. For example, the rule is IF X is PA and Y is NA the Z is VS. Then, the membership degree of the premise is obtained by taking a small operation, and the membership degree of the premise of the rule is min (mu) PA(X) ，μ NA(Y) ). The terminal can collect all membership degrees of the same type of rule premise to obtain the total membership degree output of the fuzzy system. And performing defuzzification by adopting an area gravity center method to obtain a price elastic coefficient matrix E. The terminal can utilize the established potential measuring and calculating model of the price type demand response to carry out potential measuring and calculating on the demand side resource according to the demand elasticity coefficient matrix E obtained through quantitative analysis, for example, the new power demand of the object to be predicted is determined through the elasticity coefficient matrix E, and therefore the terminal can determine the demand response potential of the object to be predicted based on the new power demand and the original power demand.
Through the embodiment, the terminal predicts the demand response potential based on the unit-degree electricity generation value, the peak-valley load coefficient, the load interruptible coefficient and the elastic coefficient matrix, and the prediction complexity is reduced.
In addition, the application embodiment also provides an application embodiment, for example, the terminal can select the metal product industry and the textile industry as case analysis samples, and the adjustable potential of the industries is measured and calculated on the basis of load data in a preset time period. The important indexes of the key industries are calculated firstly, and the index calculation results are shown in the following table.
Figure BDA0003821333810000191
The terminal may determine three fuzzy sets, i.e., three levels, corresponding to each coefficient according to the setting of the level corresponding to each coefficient. The fuzzy subsets of the input and output of the fuzzy control system select triangular and trapezoidal membership functions. The fuzzy rule is set according to the fuzzy rule design table, namely the preset rule table. The terminal can match the fuzzy rule by using the fuzzy rule design table and the fuzzy membership function. For example, given specific values of three input variables, such as a unit degree electrical output value α of 10, a load peak-valley distribution coefficient β of 1, and a load interruptible coefficient θ of 0.25, the corresponding membership degrees are:
Figure BDA0003821333810000192
the terminal may substitute the specific value into the preset rule table to obtain the following table:
Figure BDA0003821333810000193
the terminal can obtain 8 fuzzy rules through the preset rule table and carry out rule precondition reasoning. Specifically, the terminal may obtain the conclusion of each fuzzy rule and the membership degree of each fuzzy rule premise through logical and operation within the same rule and between the premises, as shown in the following table:
Figure BDA0003821333810000201
the terminal can calculate the intersection of the two tables, and obtain the fuzzy output of each rule through logical AND operation. Wherein the self-elastic coefficient e of the fuzzy system 1 The overall membership results are: mu.s agg (e 1 )＝max{min(1/3，μ M1(e1) ),min(1/3，μ M1(e1) ),min(1/3，μ M1(e1) ),min(1/3，μ M1(e1) ),min(1/3，μ S1(e1) ),min(1/3，μ S1(e1) ),min(1/2，μ S1(e1) ),min(1/2，μ M1(e1) )}＝max{min(1/2，μ S1(e1) ),min(1/2，μ M1(e1) ) }. Coefficient of self-elasticity e of fuzzy system 2 The overall membership results were: mu.s agg(e2) ＝max{min(1/3，μ VS2(e2) ),min(1/3，μ S2(e2) ),min(1/3，μ S2(e2) ),min(1/3，μ M2(e2) ),min(1/3，μ VS2(e2) ),min(1/3，μ S2(e2) ),min(1/2，μ S2(e2) ),min(1/2，μ S2(e2) )}＝max{min(1/2，μ VS2(e2) ),min(1/2，μ S2(e2) ),min(1/3，μ M2(e2) ) }. The terminal can perform defuzzification by using a gravity center method, and the result of the elastic coefficient can be obtained as 1 ＝0.0942，e 2 =0.0668. The self-elasticity coefficient e of each object to be predicted 1 And e of mutual elastic coefficient 2 As follows:
Figure BDA0003821333810000202
wherein, the self-elastic coefficient is negative and the mutual elastic coefficient is positive in the elastic coefficient matrix. The terminal can calculate the coefficient of self-elasticity e according to the calculation result 1 The value multiplied by-1 is defined as the coefficient of the elastic coefficient matrix for the peak-to-peak period, and the coefficients for the flat-to-flat and valley-to-valley periods are defined as the self-elastic coefficient e 1 2/3 of (1); coefficient of mutual elasticity e 2 Defined as the coefficient of the peak-to-valley period, and the peak-to-average and average-to-valley periods as the coefficient of mutual elasticity e 2 1/2 of (1). The elastic coefficient matrix for the metal article industry can be as follows:
Figure BDA0003821333810000203
the textile industry elastic coefficient matrix can be shown as follows:
Figure BDA0003821333810000211
the terminal can enable the time-of-use electricity price scheme of the preset area to be divided into peak-to-valley electricity prices of 1.8: 1: 0.3 and 2: 1: 0.25, and the peak-to-valley electricity price ratio is 6:1 and 8:1 respectively. The terminal obtains the load curves before and after the electricity price type demand response of the metal product industry and the textile industry through modeling simulation analysis based on the proposed adjustable potential evaluation model and the current time-of-use electricity price as shown in fig. 4 and 5, and fig. 4 is an interface schematic diagram of a demand response potential prediction step in one embodiment. FIG. 5 is an interface diagram of the demand response potential prediction step in one embodiment. Fig. 4 and 5 include power consumption curves after various DRs (Demand Response). For example, in fig. 4, the current DR electricity usage curve 301, the electricity usage curve 302 when the electricity price ratio is 6; in fig. 5, the current DR power consumption curve 401, the power consumption curve 402 when the power consumption ratio is 6, and the power consumption curve 403 when the power consumption ratio is 8. As can be seen from fig. 4 and 5, when the electricity price of the object to be predicted changes, there is a change in the electricity demand amount in response to the change in the electricity price, and the demand response potential of the metal manufacturing industry is greater than that of the textile industry.
Through the embodiment, the terminal predicts the demand response potential based on the unit-degree electricity generation value, the peak-valley load coefficient, the load interruptible coefficient and the elastic coefficient matrix, and the prediction complexity is reduced.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a demand response potential prediction apparatus for implementing the demand response potential prediction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the demand response potential prediction device provided below can be referred to the limitations of the demand response potential prediction method in the foregoing, and details are not repeated herein.
In one embodiment, as shown in fig. 6, there is provided a demand response potential prediction apparatus, including: a response module 500, a query module 502, a determination module 505, and a prediction module 506, wherein:
the response module 500 is used for responding to the demand response potential prediction request, and inquiring and acquiring a unit-degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient corresponding to an object to be predicted from the power database; the unit degree electricity generation value represents the influence of electricity cost on the electricity consumption of the object to be predicted; the load peak-valley distribution coefficient represents the electricity consumption time interval distribution characteristic of the electricity consumption of the object to be predicted; the load interruptible coefficient represents the degree of influence of the interrupting power consumption on the production of the object to be predicted.
The query module 502 is configured to query a preset rule table according to a level corresponding to the unit degree electricity generation value, a level corresponding to the load peak-valley distribution coefficient, and a level corresponding to the load interruptible coefficient, so as to obtain a corresponding self-elastic coefficient and a corresponding mutual elastic coefficient; the preset rule table comprises corresponding relations among grades corresponding to unit-degree electric power values, grades corresponding to load peak-valley distribution coefficients and grades corresponding to load interruptible coefficients, self-elastic coefficients and mutual elastic coefficients; the self-elasticity coefficient represents the corresponding relation between the power consumption of each time period of the object to be predicted and the power consumption cost of the current time period; and the mutual elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity cost of other time periods.
The determining module 504 is configured to determine an elasticity coefficient matrix according to the self-elasticity coefficient and the mutual elasticity coefficient, and determine a new power demand of the object to be predicted, which is in response to the updated power cost within the preset time period, according to the elasticity coefficient matrix, the original power demand of the object to be predicted within the preset time period, the original power cost of the object to be predicted within the preset time period, the updated power cost of the object to be predicted within the preset time period, and the number of power consumption time periods.
And the predicting module 506 is configured to determine a demand response potential of the object to be predicted according to a difference between the new power demand and the original power demand.
In an embodiment, the response module 500 is specifically configured to obtain an annual output value increment and an annual power consumption amount in a historical time period of the object to be predicted, and obtain a total power consumption amount in a preset time period of the object to be predicted, where the preset time period includes a power consumption peak time period, a power consumption valley time period, and a power consumption level middle time period; determining the unit-degree electricity generation value of the object to be predicted according to the annual value increment and the annual electricity consumption in the historical time period; acquiring first electric quantity at a power consumption peak period, second electric quantity at a power consumption valley period and power consumption data points at the power consumption peak period, the power consumption valley period and the power consumption level period in the total power consumption in a preset time period, and acquiring a load peak-valley distribution coefficient according to the first electric quantity, the second electric quantity and the power consumption data points; and determining the load interruptible coefficient corresponding to the object to be predicted according to the power utilization behavior of the object to be predicted.
In one embodiment, the apparatus further comprises: the dividing module is used for acquiring the region where the object to be predicted is located, and determining the dividing strategies of the electricity utilization peak period, the electricity utilization valley period and the electricity utilization middle period in the preset time period according to the electricity utilization cost strategies corresponding to the region; and determining a power consumption peak time period, a power consumption valley time period and a power consumption level time period in a preset time period according to a dividing strategy.
In an embodiment, the dividing module is specifically configured to determine, according to the time-of-use electricity price policy, a dividing policy of a peak electricity consumption period, a valley electricity consumption period, and a middle electricity consumption period in a preset time period, if the electricity consumption policy is the time-of-use electricity price policy; and if the electricity cost strategy is not the time-of-use electricity price strategy, determining a division strategy of an electricity peak period, an electricity valley period and an electricity level period in a preset time period according to a typical daily electricity quantity curve.
In an embodiment, the query module 502 is specifically configured to input the unit degree electrical output value into the first membership function, so as to obtain a plurality of first probabilities of a plurality of unit degree electrical output value levels corresponding to the unit degree electrical output value output by the first membership function; inputting the load peak-valley distribution coefficient into a second membership function to obtain a plurality of second probabilities of a plurality of load peak-valley distribution coefficient grades corresponding to the load peak-valley distribution coefficient output by the second membership function; inputting the load interruptible coefficients into a third membership function to obtain a plurality of third probabilities of a plurality of load interruptible coefficient levels corresponding to the load interruptible coefficients output by the third membership function; inquiring a preset rule table according to the multiple unit-degree electric power value grades, the corresponding multiple first probabilities, the multiple load peak-valley distribution coefficient grades, the corresponding multiple second probabilities, the multiple load interruptible coefficient grades and the corresponding multiple third probabilities to obtain multiple fourth probabilities and multiple fifth probabilities of the multiple self-elastic coefficient grades and the multiple mutual elastic coefficient grades under the conditions of each group of unit-degree electric power value grades, each group of load peak-valley distribution coefficient grades and each group of load interruptible coefficient grades; respectively carrying out logical AND operation on the plurality of fourth probabilities and the plurality of fifth probabilities, determining at least one target self-elasticity coefficient grade corresponding to at least one target fourth probability with the maximum probability corresponding to the object to be predicted, and determining at least one target mutual elasticity coefficient grade corresponding to at least one target fifth probability with the maximum probability corresponding to the object to be predicted; and respectively carrying out defuzzification on at least one target self-elasticity coefficient grade and at least one target mutual elasticity coefficient grade according to a gravity center method to obtain the self-elasticity coefficient and the mutual elasticity coefficient of the object to be predicted.
In an embodiment, the determining module 504 is specifically configured to determine, according to the self-elastic coefficient, a first coefficient between a power consumption valley period and a power consumption valley period, a second coefficient between a power consumption level period and a power consumption level period, and a third coefficient between a power consumption peak period and a power consumption peak period within a preset time period; determining a fourth coefficient between a power consumption peak period and a power consumption valley period, a fifth coefficient between the power consumption peak period and the power consumption level period and a sixth coefficient between the power consumption level period and the power consumption valley period in a preset time period according to the mutual elasticity coefficient; obtaining an elastic coefficient matrix according to the first coefficient, the second coefficient, the third coefficient, the fourth coefficient, the fifth coefficient and the sixth coefficient; the method comprises the steps of obtaining a product of a ratio of power consumption cost variation obtained by a difference value of an elasticity coefficient matrix, original power consumption demand, original power consumption cost and updated power consumption cost and a ratio of the original power consumption cost, determining a new power consumption load variation of an object to be predicted, which is in response to the updated power consumption cost in a preset time period, according to the product and the ratio of the number of power consumption time periods, and obtaining the updated power consumption demand according to the sum of the new power consumption load variation and the original power consumption demand.
The various modules in the demand response potential prediction apparatus described above 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 of 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.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a demand response potential prediction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided that includes a memory having a computer program stored therein and a processor that when executed implements the demand response potential prediction method described above.
In one embodiment, a computer-readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, implements the demand response potential prediction method described above.
In one embodiment, a computer program product is provided comprising a computer program that when executed by a processor implements the demand response potential prediction method described above.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (10)

1. A demand response potential prediction method, the method comprising:
responding to a demand response potential prediction request, and inquiring and acquiring a unit degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient corresponding to an object to be predicted from an electric power database; the unit degree electricity generation value represents the influence of electricity cost on the electricity consumption of the object to be predicted; the load peak-valley distribution coefficient represents the electricity consumption time interval distribution characteristic of the electricity consumption of the object to be predicted; the load interruptible coefficient represents the influence degree of the interrupted power consumption on the production of the object to be predicted;
inquiring a preset rule table according to the grade corresponding to the unit degree electricity generation value, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient to obtain a corresponding self-elasticity coefficient and a corresponding mutual elasticity coefficient; the preset rule table comprises corresponding relations among the grade corresponding to the unit degree electricity value, the grade corresponding to the load peak-valley distribution coefficient, the grade corresponding to the load interruptible coefficient, the self-elasticity coefficient and the mutual elasticity coefficient; the self-elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variation of the current time period; the mutual elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity cost variation of other time periods;
determining an elasticity coefficient matrix according to the self elasticity coefficient and the mutual elasticity coefficient, and determining a new power consumption demand of the object to be predicted in response to the updated power consumption cost in a preset time period according to the elasticity coefficient matrix, the original power consumption demand of the object to be predicted in a preset time period, the original power consumption cost of the object to be predicted in the preset time period, the corresponding updated power consumption cost of the object to be predicted in the preset time period and the number of power consumption time periods;
and determining the demand response potential of the object to be predicted according to the difference value of the new power consumption demand and the original power consumption demand.
2. The method according to claim 1, wherein the obtaining of the unit degree electricity generation value, the load peak-valley distribution coefficient and the load interruptible coefficient corresponding to the object to be predicted comprises:
acquiring an annual output value increment and an annual power consumption of an object to be predicted in a historical time period, and acquiring a total power consumption of the object to be predicted in a preset time period, wherein the preset time period comprises a power consumption peak time period, a power consumption valley time period and a power consumption level middle time period;
determining the unit degree electricity generation value of the object to be predicted according to the annual output value increment and the annual electricity consumption in the historical time period;
acquiring first electric quantity at a power consumption peak period, second electric quantity at a power consumption valley period and power consumption data points at the power consumption peak period, the power consumption valley period and the power consumption level period in the total power consumption in the preset time period, and acquiring a load peak-valley distribution coefficient according to the first electric quantity, the second electric quantity and the power consumption data points;
and determining a load interruptible coefficient corresponding to the object to be predicted according to the power utilization behavior of the object to be predicted.
3. The method according to claim 2, wherein before the obtaining of the first electricity quantity in the electricity peak period, the second electricity quantity in the electricity valley period, and the number of electricity consumption data points in the electricity peak period, the electricity valley period, and the electricity level period in the total electricity consumption in the preset time period, further comprises:
obtaining the region where the object to be predicted is located, and determining the division strategy of the electricity consumption peak time period, the electricity consumption valley time period and the electricity consumption normal time period in the preset time period according to the electricity consumption cost strategy corresponding to the region;
and determining the electricity utilization peak time period, the electricity utilization valley time period and the electricity utilization level time period in the preset time period according to the division strategy.
4. The method according to claim 3, wherein the determining of the dividing strategy of the peak power utilization period, the valley power utilization period, the level power utilization period and the level power utilization period in the preset time period according to the power utilization cost strategy corresponding to the region comprises:
if the power cost strategy is a time-of-use power price strategy, determining a division strategy of a power consumption peak period, a power consumption valley period and a power consumption middle period in the preset time period according to the time-of-use power price strategy;
and if the power consumption cost strategy is not a time-of-use power price strategy, determining a division strategy of a power consumption peak period, a power consumption valley period and a power consumption level period in the preset time period according to a typical daily power consumption curve.
5. The method according to claim 1, wherein the querying a preset rule table according to the level corresponding to the unit degree electricity generation value, the level corresponding to the load peak-valley distribution coefficient and the level corresponding to the load interruptible coefficient to obtain the corresponding self-elastic coefficient and mutual elastic coefficient comprises:
inputting the unit degree electric power values into a first membership function to obtain a plurality of first probabilities of a plurality of unit degree electric power value grades corresponding to the unit degree electric power values output by the first membership function;
inputting the load peak-valley distribution coefficient into a second membership function to obtain a plurality of second probabilities of a plurality of load peak-valley distribution coefficient grades corresponding to the load peak-valley distribution coefficient output by the second membership function;
inputting the load interruptible coefficients into a third membership function to obtain a plurality of third probabilities of a plurality of load interruptible coefficient levels corresponding to the load interruptible coefficients output by the third membership function;
inquiring a preset rule table according to the plurality of unit degree electric power value grades and the corresponding plurality of first probabilities, the plurality of load peak-valley distribution coefficient grades and the corresponding plurality of second probabilities, the plurality of load interruptible coefficient grades and the corresponding plurality of third probabilities to obtain a plurality of fourth probabilities and a plurality of fifth probabilities of the plurality of self-elastic coefficient grades and the plurality of mutual elastic coefficient grades under the conditions of each group of unit degree electric power value grades, load peak-valley distribution coefficient grades and load interruptible coefficient grades;
performing logical AND operation on the fourth probabilities and the fifth probabilities respectively, determining at least one target self-elastic coefficient grade corresponding to at least one target fourth probability with the maximum probability corresponding to the object to be predicted, and determining at least one target mutual elastic coefficient grade corresponding to at least one target fifth probability with the maximum probability corresponding to the object to be predicted;
and respectively carrying out defuzzification on the at least one target self-elasticity coefficient grade and the at least one target mutual elasticity coefficient grade according to a gravity center method to obtain the self-elasticity coefficient and the mutual elasticity coefficient of the object to be predicted.
6. The method according to claim 1, wherein the determining an elasticity coefficient matrix according to the self-elasticity coefficient and the mutual elasticity coefficient, and determining a new electricity demand amount of the object to be predicted in response to the updated electricity cost in a preset time period according to the elasticity coefficient matrix, an original electricity demand amount of the object to be predicted in the preset time period, an original electricity cost of the object to be predicted in the preset time period, a corresponding updated electricity cost of the object to be predicted in the preset time period, and a number of electricity periods comprises:
determining a first coefficient between a power consumption valley period and a power consumption valley period, a second coefficient between a power consumption level period and a power consumption level period, and a third coefficient between a power consumption peak period and a power consumption peak period in the preset time period according to the self-elasticity coefficient;
determining a fourth coefficient between a power consumption peak period and a power consumption valley period, a fifth coefficient between the power consumption peak period and the power consumption level period and a sixth coefficient between the power consumption level period and the power consumption valley period in the preset time period according to the mutual elasticity coefficient;
obtaining the elastic coefficient matrix according to the first coefficient, the second coefficient, the third coefficient, the fourth coefficient, the fifth coefficient and the sixth coefficient;
and acquiring the elasticity coefficient matrix, the original power consumption demand, and a product of a power consumption cost variation obtained by a difference value between the original power consumption cost and the updated power consumption cost and a ratio of the original power consumption cost, determining a new power consumption load variation of the object to be predicted, which is in response to the updated power consumption cost in a preset time period, according to the product and the ratio of the power consumption time period number, and acquiring the updated power consumption demand according to the sum of the new power consumption load variation and the original power consumption demand.
7. A demand response potential prediction apparatus, the apparatus comprising:
the response module is used for responding to the demand response potential prediction request, and inquiring and acquiring a unit-degree electricity generation value, a load peak-valley distribution coefficient and a load interruptible coefficient corresponding to the object to be predicted from the power database; the unit degree electricity generation value represents the influence of electricity cost on the electricity consumption of the object to be predicted; the load peak-valley distribution coefficient represents the electricity consumption time interval distribution characteristic of the electricity consumption of the object to be predicted; the load interruptible coefficient represents the influence degree of interrupted power consumption on the production of the object to be predicted;
the query module is used for querying a preset rule table according to the grade corresponding to the unit-degree electricity generation value, the grade corresponding to the load peak-valley distribution coefficient and the grade corresponding to the load interruptible coefficient to obtain a corresponding self-elastic coefficient and a corresponding mutual elastic coefficient; the preset rule table comprises corresponding relations among the grade corresponding to the unit degree electricity value, the grade corresponding to the load peak-valley distribution coefficient, the grade corresponding to the load interruptible coefficient, the self-elasticity coefficient and the mutual elasticity coefficient; the self-elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variation of the current time period; the mutual elasticity coefficient represents the corresponding relation between the electricity consumption of each time period of the object to be predicted and the electricity consumption cost variation of other time periods;
the determining module is used for determining an elastic coefficient matrix according to the self-elastic coefficient and the mutual elastic coefficient, and determining a new power consumption demand of the object to be predicted in response to the updated power consumption cost in a preset time period according to the elastic coefficient matrix, the original power consumption demand of the object to be predicted in the preset time period, the original power consumption cost of the object to be predicted in the preset time period, the updated power consumption cost corresponding to the object to be predicted in the preset time period and the number of power consumption time periods;
and the prediction module is used for determining the demand response potential of the object to be predicted according to the difference value between the new power demand and the original power demand.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
CN202211042308.3A 2022-08-29 2022-08-29 Demand response potential prediction method, demand response potential prediction device, computer equipment and storage medium Pending CN115358476A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211042308.3A CN115358476A (en) 2022-08-29 2022-08-29 Demand response potential prediction method, demand response potential prediction device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211042308.3A CN115358476A (en) 2022-08-29 2022-08-29 Demand response potential prediction method, demand response potential prediction device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115358476A true CN115358476A (en) 2022-11-18

Family

ID=84004155

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211042308.3A Pending CN115358476A (en) 2022-08-29 2022-08-29 Demand response potential prediction method, demand response potential prediction device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115358476A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116914762A (en) * 2023-07-21 2023-10-20 南方电网科学研究院有限责任公司 Distributed demand side resource management method and device and computer equipment
CN117540932A (en) * 2023-12-07 2024-02-09 南方电网能源发展研究院有限责任公司 Industrial load demand response potential dynamic evaluation method and device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116914762A (en) * 2023-07-21 2023-10-20 南方电网科学研究院有限责任公司 Distributed demand side resource management method and device and computer equipment
CN117540932A (en) * 2023-12-07 2024-02-09 南方电网能源发展研究院有限责任公司 Industrial load demand response potential dynamic evaluation method and device

Similar Documents

Publication Publication Date Title
CN115358476A (en) Demand response potential prediction method, demand response potential prediction device, computer equipment and storage medium
CN108470233B (en) Demand response capability assessment method and computing device for smart power grid
CN102426674B (en) Power system load prediction method based on Markov chain
CN102509173B (en) A kind of based on markovian power system load Accurate Prediction method
CN111612275B (en) Method and device for predicting load of regional user
CN113255973A (en) Power load prediction method, power load prediction device, computer equipment and storage medium
CN110544123B (en) Power consumer classification method and device, computer equipment and storage medium
CN103745280A (en) Prediction method, device and processor for electricity consumption
CN114611845B (en) Method and device for predicting carbon emission, electronic device, and medium
CN112633762A (en) Building energy efficiency obtaining method and equipment
Zheng et al. An application of machine learning for a smart grid resource allocation problem
Li et al. Feature analysis of generalized load patterns considering active load response to real-time pricing
Sari et al. The effectiveness of hybrid backpropagation Neural Network model and TSK Fuzzy Inference System for inflation forecasting
CN115329907B (en) Electric load completion method and system based on DBSCAN clustering
CN112256735B (en) Power consumption monitoring method and device, computer equipment and storage medium
CN112214734A (en) Power load prediction method based on statistical physics and artificial intelligence
Lin et al. Load Data Analysis Based on Timestamp-Based Self-Adaptive Evolutionary Clustering
CN118170976B (en) Intelligent recommendation method and system based on power enterprise user image
Qian et al. Enhancing power utilization analysis: detecting aberrant patterns of electricity consumption
CN118411003B (en) Load control method, system, device and storage medium for multi-class power device
CN117540932A (en) Industrial load demand response potential dynamic evaluation method and device
Pawar et al. Electricity Forecasting Using Machine Learning: A Review
CN117933677A (en) Regional frequency modulation-based associated data prediction method and device for hydropower plant
Yu et al. Comparison of innovation diffusion models: A case study on the DRAM industry
Wang et al. Baseline Load Forecasting for Demand Response Taking Meteorological Factors into Account

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