CN116090679A - Power distribution network load prediction method - Google Patents
Power distribution network load prediction method Download PDFInfo
- Publication number
- CN116090679A CN116090679A CN202310383283.1A CN202310383283A CN116090679A CN 116090679 A CN116090679 A CN 116090679A CN 202310383283 A CN202310383283 A CN 202310383283A CN 116090679 A CN116090679 A CN 116090679A
- Authority
- CN
- China
- Prior art keywords
- load
- power distribution
- distribution network
- value
- electricity consumption
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a power distribution network load prediction method, which comprises the steps that firstly, a flow monitoring subsystem predicts the instantaneous population number of a segment according to the access behavior of a resident network; then, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area; and finally, the load prediction subsystem predicts the maximum risk load value of the unit time of the region according to the instantaneous population estimated value and the load experience model. The method of the invention is used for realizing the maximum risk load value estimation in unit time under a small time scale, and the invention establishes a relation model between relation quantities through historical prior information, thereby providing quantitative basis for the load prediction of the small time scale of the area, effectively improving the accuracy and timeliness of the load prediction of the area and providing a timely and effective monitoring mechanism for the electricity safety precaution.
Description
Technical Field
The invention relates to the field of power distribution network load prediction, in particular to a power distribution network load prediction method.
Background
In recent years, with the rapid development of economy, the requirements of various layers of society on power supply become wider and wider, and obviously, power supply enterprises as important basic industries in China become important supporting forces of national economy and become key factors for promoting the healthy development of various industries.
The power supply firstly needs to consider the balance of supply and demand, and only can ensure the power demand and waste as little as possible, so that the power generation cost can be effectively controlled, and low-cost power supply is provided for a power consumer.
Therefore, how to accurately predict the load change of the power distribution network is a foundation for improving the efficiency and the electricity safety of the power grid. The prediction of the load of the power distribution network in the prior art is usually performed based on a large time scale, for example, prediction and adjustment are performed according to a quarter, after the prediction of the large time scale, a more abundant power supply guarantee is provided, the overload in the period is avoided, the whole power distribution network is not overloaded, the efficiency of the whole power distribution network is too low, in order to improve the efficiency of the power distribution network, a power distribution network load prediction method based on a small time scale is required to be provided, and only the power distribution network prediction accuracy of the small time scale is improved, the power distribution network supply balance can be effectively optimized, the power distribution network efficiency is improved, and the power supply safety is ensured. Therefore, providing a power distribution network load prediction method with a small time scale is a problem to be solved in the industry.
Disclosure of Invention
The invention aims to solve the technical problems that: the power distribution network load prediction method effectively improves the accuracy and timeliness of regional load prediction.
The technical scheme for solving the technical problems is as follows: a method for predicting load of a power distribution network, comprising the steps of:
step 1, a flow monitoring subsystem predicts the instantaneous population number of a segment according to the access behavior of a resident network;
step 2, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area;
and 3, predicting the maximum risk load value of the unit time of the region by the load prediction subsystem according to the instantaneous population estimated value and the load experience model.
Preferably, in the step 1, the method for estimating the instantaneous population number of the segment according to the resident network access behavior comprises the following steps: the flow monitoring subsystem monitors the IP number accessed by the broadband network of each household in unit time, wherein the IP number is the estimated population number of the household, and then the estimated population number sum of each household in the area is counted to obtain the instantaneous population number of the area, and the unit time is completed through configuration.
Further, the unit time is configured to be 1 second.
Preferably, in the step 1, the method for estimating the instantaneous population number of the segment according to the resident network access behavior comprises the following steps: the flow monitoring subsystem monitors the total flow of the broadband network of each household in unit time, the total flow divided by the experience value of the average flow is the population number of the household, then the estimated population number sum of each household in the residential area is counted to obtain the instantaneous population number of the residential area, and the experience value of the average flow is completed through configuration.
Further, the average flow experience value is configured to be 3.68Mbps.
More preferably, in the step 2, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area, and the load experience model at least comprises an experience model of the number of people in the area and the load, and an experience model of the maximum peak-to-average ratio of the load.
More preferably, in the step 2, the empirical model generating method of the population and the load of the zone is as follows:
and 2.1A, selecting data matched with weather characteristics and time characteristics of a current required prediction period from historical data by the electricity consumption behavior analysis subsystem to form screened historical data, wherein the weather characteristics at least comprise air temperature, and the period characteristics refer to a period corresponding to the required prediction period in one day.
Step 2.2A, the electricity consumption behavior analysis subsystem calculates the average unit duration load according to the screened historical data:
wherein Num (m, n) is the estimated number of people in the subinterval, load (m, n) is the total Load of the subinterval, and T (m, n) is the subinterval duration;
where M is one of M samples formed from the screened historical data, N m The number of subintervals included in sample m;
step 2.3A, an empirical model for determining the number X of the regional people and the unit time load Y of the regional by the electricity behavior analysis subsystem is as follows: y=x×avgcoad.
More preferably, in the step 2, the empirical model generating method of the maximum peak-to-average ratio of the load is as follows:
step 2.1B, the electricity consumption behavior analysis subsystem selects data matched with weather characteristics and time characteristics of a current required prediction period from historical data to form screened historical data, wherein the weather characteristics at least comprise air temperature, and the period characteristics refer to periods corresponding to the required prediction period in one day;
step 2.2B, the electricity behavior analysis subsystem calculates the maximum load value MaxLoad of each subinterval unit duration of each sample according to the screened historical data,
wherein Num (m, n) is the estimated number of people in the subinterval, load (m, n) is the total Load of the subinterval, and T (m, n) is the subinterval duration;
where M is one of M samples formed from the screened historical data, N m The number of subintervals included in sample m;
in the formula (2)
To solve the problems that M is more than or equal to 1 and less than or equal to M, N is more than or equal to 1 and less than or equal to N is less than or equal to 1 and less than or equal to N m In (a)
Maximum value of (2); />
Step 2.3B, the electricity consumption behavior analysis subsystem calculates
And obtaining the maximum peak-to-average ratio of the load.
More preferably, in the step 3, the load prediction subsystem predicts a maximum risk load value predictmaxload=x×avgcoad×parkvalue×threshold of the unit time of the area according to the instantaneous population estimation value X and the load experience model, where threshold is a correction coefficient.
Further, threshold=1.2.
The beneficial effects of the invention are as follows:
compared with the prior art, the invention has the following advantages and beneficial effects: by adopting the method, the population quantity is estimated dynamically in real time based on the resident network access behavior, then the load experience model modeling is completed according to the historical electricity consumption data, and the maximum risk load value estimation per unit time under the small time scale is realized based on the estimated population quantity and the load experience model.
Drawings
FIG. 1 is a flow chart of a method for predicting load of a power distribution network;
fig. 2 is a schematic diagram of a power distribution network load prediction system.
Detailed Description
For the purpose of making the technical solutions and advantages of the present invention more apparent, the present invention will be described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the load prediction method of the power distribution network specifically comprises the following steps:
step 1, a flow monitoring subsystem predicts the instantaneous population number of a segment according to the access behavior of a resident network;
step 2, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area;
and 3, predicting the maximum risk load value of the unit time of the region by the load prediction subsystem according to the instantaneous population estimated value and the load experience model.
In the step 1, the instantaneous population number of the segment is estimated according to the network access behavior of the resident, and the specific method is as follows:
IP monitoring party: the flow monitoring subsystem monitors the IP number accessed by the broadband network of each household in unit time, wherein the IP number is the estimated population number of the household, and then the estimated population number sum of each household in the area is counted to obtain the instantaneous population number of the area, and the unit time is completed through configuration, preferably, the typical configuration is 1 second;
or alternatively, the process may be performed,
flow monitoring method: the flow monitoring subsystem monitors the total flow of the broadband network of each household in unit time, the total flow divided by the experience value of the average flow is the population number of the household, and then the estimated population number sum of each household in the residential area is counted to obtain the instantaneous population number of the residential area, wherein the experience value of the average flow is completed through configuration, and is preferably configured to be 3.68Mbps typically;
in the step 2, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area, wherein the load experience model at least comprises an experience model of the number of people in the area and the load, and an experience model of the maximum peak-to-average ratio of the load.
In the step 2, the empirical model of the number of people and the load of the area is obtained by the following method:
step 2.1A, the electricity behavior analysis subsystem selects data matched with weather characteristics and time characteristics of a current required prediction period from historical data to form screened historical data, wherein the weather characteristics at least comprise air temperature, and the period characteristics refer to periods of one day corresponding to the required prediction period, such as: period 18:00-24:00;
step 2.2A, the electricity consumption behavior analysis subsystem calculates the average unit time length load of people according to the screened historical data, wherein the screened historical data comprises M samples, and the sample M comprises N m The sample m subperiod n comprises a predicted number Num (m, n) of people in the subperiod, a total Load (m, n) of the subperiod and a subperiod duration T (m, n), wherein the calculation method of the average person unit duration Load avgLoad is shown as a formula (1);
step 2.3A, an empirical model for determining the number X of the regional people and the unit time load Y of the regional by the electricity behavior analysis subsystem is as follows: y=x avgcoad;
in the step 2, the empirical model of the maximum peak-to-average ratio of the load is obtained by the following method:
step 2.1B, the electricity consumption behavior analysis subsystem selects data matched with weather characteristics and time characteristics of a current required prediction period from historical data to form screened historical data, wherein the weather characteristics at least comprise air temperature, and the period characteristics refer to periods corresponding to the required prediction period in one day;
step 2.2B, power consumption behavior AnalyzerThe system calculates the maximum load value MaxLoad of each sub-period unit time length of each sample according to the screened historical data, wherein the screened historical data comprises M samples, and N is as follows m The sample m comprises N subintervals, the subinterval N of the sample m comprises the number of estimated people Num (m, N) in the subinterval, the total Load (m, N) of the subinterval and the subinterval duration T (m, N), wherein the calculating method of the maximum Load MaxLoad of unit duration is shown as a formula (2), and the calculating method of the maximum Load MaxLoad of unit duration is shown as a formula (2)
To solve the problem that M is not less than 1 and not more than M, n is not less than 1 and not more than n is not more than +.>
Middle->
Maximum value of (2);
step 2.3B, the electricity consumption behavior analysis subsystem calculates
And obtaining the maximum peak-to-average ratio of the load.
In the step 3, the method of predicting the maximum risk load value PredictMaxLoad of the unit time of the area by the load prediction subsystem according to the instantaneous population estimation value X and the load experience model refers to the formula (3), and the threshold is a correction coefficient, and is configured, preferably, typically configured to be 1.2.
PredictMaxLoad=X*AvgLoad*ParValue*threshold （3）
In the embodiment, fig. 2 is taken as an example to illustrate a load prediction system for a power distribution network according to the present invention.
As shown in fig. 2, a power distribution network load prediction system includes: the system comprises a flow monitoring subsystem, an electricity behavior analysis subsystem and a load prediction subsystem, wherein the functions of each subsystem are described as follows:
the flow monitoring subsystem predicts instantaneous population distribution of the segment according to the access behavior of the resident network;
the power consumption behavior analysis subsystem forms a load experience model according to the historical power consumption data of the area;
and the load prediction subsystem predicts a maximum risk load value of the region according to the instantaneous population estimated value and the load experience model.
A specific implementation of a power distribution network load prediction system is described below with specific examples:
examples: the working process of the power distribution network load prediction system is described by predicting the power distribution network load of a cell.
Firstly, according to step 1, the flow monitoring subsystem predicts the instantaneous population number of the cell according to the access behavior of the resident network, the embodiment adopts a flow monitoring method, the experience value of the average flow is configured to be 3.68Mbps, the flow monitoring subsystem monitors the total flow number of the broadband network of each resident of a certain cell in unit time to be Stream (k) at a certain moment, wherein 1<k<K, K is the number of the living units of the cell, and then the population Count (K) of each resident is obtained by calculating the Stream (K)/3.68 Mbps, and finally the population Count (K) of each resident is obtained by calculating
Obtaining the total population number of the cell, and assuming the calculation result of the embodiment, the prediction result of the total population number X is equal to 200;
and then, according to the step 2, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area, wherein the load experience model at least comprises an experience model of the number of people in the area and the load, and an experience model of the maximum peak-to-average ratio of the load.
The empirical model of the number of people and the load of the area is obtained by the following method:
according to the step 2.1A, the electricity consumption behavior analysis subsystem selects data matched with the climate characteristics and the time period characteristics of the current required prediction period from the historical data to form screened historical data, and assuming that the embodiment predicts the load of the power distribution network for the period 18:00-24:00, and the current air temperature is 20-25 ℃, the electricity consumption behavior analysis subsystem selects the historical data of the period 18:00-24:00 from the historical data, and the air temperature is 20-25 ℃ to form the screened historical data, and the screened historical data is shown in the table 1 in detail;
according to step 2.2A, the electricity behavior analysis subsystem calculates the average unit time length load according to the screened historical data, wherein the screened historical data is shown in Table 1 and comprises M samples (3 samples in the embodiment, so that the M value is equal to 3), and the sample M comprises
Subinterval (wherein->
=2、/>
=4、/>
=3), the sample m subperiod n includes the number of pre-estimated people Num (m, n) in the subperiod, the total Load (m, n) in the subperiod, and the subperiod duration T (m, n), where specific data are shown in table 1, and the average unit duration Load avgcoad result is 1.9756 according to formula (1), and the calculation process is as follows:
=((Load(1,1)/(Num(1,1)*T(1,1))+Load(1,2)/(Num(1,2)*T(1,2)))/2+(Load(2,1)/(Num(2,1)*T(2,1))+Load(2,2)/(Num(2,2)*T(2,2))+Load(2,3)/(Num(2,3)*T(2,3))+Load(2,4)/(Num(2,4)*T(2,4)))/4+(Load(3,1)/(Num(3,1)*T(3,1))+Load(3,2)/(Num(3,2)*T(3,2))+Load(3,3)/(Num(3,3)*T(3,3)))/3)/3
=((48000/(100*240)+15000/(80*120))/2+(4200/(70*60)+50000/(120*180)+16000/(90*60)+5000/(60*60))/4+(16000/(90*120)+75000/(130*180)+6000/(50*60))/3)/3
=1.9756
TABLE 1 historical data representation after screening
According to the step 2.3A, the electricity behavior analysis subsystem determines that the empirical model of the number X of the regional population and the unit time load Y of the regional population is as follows: y=x×avgcoad=x× 1.9756;
then, an empirical model of the maximum peak-to-average ratio of the load is calculated according to the following steps:
2.1B, selecting data matched with weather characteristics and time characteristics of a current required prediction period from historical data by the electricity consumption behavior analysis subsystem to form screened historical data, wherein the weather characteristics at least comprise air temperature, and the period characteristics refer to a period corresponding to the required prediction period in one day;
according to the step 2.2B, the electricity behavior analysis subsystem calculates the maximum load value MaxLoad of each sub-period unit duration of each sample according to the screened historical data, wherein the screened historical data comprises M samples, and the sample M comprises
And each subperiod, wherein the sample m subperiod n comprises the number of estimated persons Num (m, n) in the subperiod, the total Load (m, n) in the subperiod and the time duration T (m, n) in the subperiod, each item of data is as shown in table 1, then the maximum Load MaxLoad in unit time duration is calculated according to the formula (2) to be equal to 3.2, and the calculation process is shown in table 2 in detail.
TABLE 2 maximum load calculation procedure schematic for unit duration
According to step 2.3B, the electricity behavior analysis subsystem calculates
Obtaining a maximum peak-to-average load ratio ParValue=3.2/1.9756 =1.62;
next, according to step 3, a maximum risk load value per unit time PredictMaxLoad is calculated according to formula (3), and in this embodiment, the threshold value is 1.2, where predictmaxload=200×1.9756×1.62×1.2=768.
Thus, the prediction of the maximum risk load is completed, and as can be seen from the embodiment, the method of the invention is adopted to dynamically predict population quantity in real time based on resident network access behaviors, then complete load experience model modeling according to historical electricity consumption data, and realize maximum risk load value estimation per unit time under a small time scale based on the predicted population quantity and the load experience model.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and the related workers can make various changes and modifications without departing from the scope of the technical idea of the present invention. The technical scope of the present invention is not limited to the description, but includes all equivalent changes and modifications in shape, construction, characteristics and spirit according to the scope of the claims.
Claims (10)
1. The power distribution network load prediction method is characterized by comprising the following steps of:
step 1, a flow monitoring subsystem predicts the instantaneous population number of a segment according to the access behavior of a resident network;
step 2, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area;
and 3, predicting the maximum risk load value of the unit time of the region by the load prediction subsystem according to the instantaneous population estimated value and the load experience model.
2. A method of predicting load on a power distribution network as recited in claim 1, wherein:
in the step 1, the method for predicting the instantaneous population number of the segment according to the resident network access behavior comprises the following steps:
the flow monitoring subsystem monitors the IP number accessed by the broadband network of each household in unit time, wherein the IP number is the estimated population number of the household, and then the estimated population number sum of each household in the area is counted to obtain the instantaneous population number of the area, and the unit time is completed through configuration.
3. A method of predicting load on a power distribution network as claimed in claim 2, wherein:
the unit time is configured to be 1 second.
4. A method of predicting load on a power distribution network as recited in claim 1, wherein:
in the step 1, the method for predicting the instantaneous population number of the segment according to the resident network access behavior comprises the following steps:
the flow monitoring subsystem monitors the total flow of the broadband network of each household in unit time, the total flow divided by the experience value of the average flow is the population number of the household, then the estimated population number sum of each household in the residential area is counted to obtain the instantaneous population number of the residential area, and the experience value of the average flow is completed through configuration.
5. The method for predicting load of power distribution network as set forth in claim 4, wherein:
the per capita flow experience value is configured to be 3.68Mbps.
6. A method of predicting load on a power distribution network as recited in claim 1, wherein:
in the step 2, the electricity consumption behavior analysis subsystem forms a load experience model according to the historical electricity consumption data of the area, wherein the load experience model at least comprises an experience model of the number of people in the area and the load, and an experience model of the maximum peak-to-average ratio of the load.
7. The power distribution network load prediction method according to claim 6, wherein:
in the step 2, the empirical model generation method of the number of people and the load of the zone is as follows:
2.1A, selecting data matched with weather characteristics and time characteristics of a current required prediction period from historical data by an electricity behavior analysis subsystem to form screened historical data, wherein the weather characteristics at least comprise air temperature, and the period characteristics refer to periods corresponding to the required prediction period in one day;
step 2.2A, the electricity consumption behavior analysis subsystem calculates the average unit duration load according to the screened historical data:
wherein Num (m, n) is the estimated number of people in the subinterval, load (m, n) is the total Load of the subinterval, and T (m, n) is the subinterval duration;
where M is one of M samples formed from the screened historical data, N m The number of subintervals included in sample m;
step 2.3A, an empirical model for determining the number X of the regional people and the unit time load Y of the regional by the electricity behavior analysis subsystem is as follows: y=x×avgcoad.
8. The power distribution network load prediction method according to claim 6, wherein:
in the step 2, the empirical model generating method of the maximum peak-to-average ratio of the load is as follows:
step 2.1B, the electricity consumption behavior analysis subsystem selects data matched with weather characteristics and time characteristics of a current required prediction period from historical data to form screened historical data, wherein the weather characteristics at least comprise air temperature, and the period characteristics refer to periods corresponding to the required prediction period in one day;
step 2.2B, the electricity behavior analysis subsystem calculates the maximum load value MaxLoad of each subinterval unit duration of each sample according to the screened historical data,
wherein Num (m, n) is the estimated number of people in the subinterval, load (m, n) is the total Load of the subinterval, and T (m, n) is the subinterval duration;
where M is one of M samples formed from the screened historical data, N m The number of subintervals included in sample m;
in the formula (2)
To solve the problems that M is more than or equal to 1 and less than or equal to M, N is more than or equal to 1 and less than or equal to N is less than or equal to 1 and less than or equal to N m Middle->
Maximum value of (2);
step 2.3B, the electricity consumption behavior analysis subsystem calculates
And obtaining the maximum peak-to-average ratio of the load.
9. A method of predicting load on a power distribution network as recited in claim 1, wherein:
in the step 3, the load prediction subsystem predicts a maximum risk load value predictmaxload=x×avgcoad×park×threshold of the unit time of the region according to the instantaneous population estimation value X and the load experience model, where the threshold is a correction coefficient.
10. A method of predicting load in a power distribution network as claimed in claim 9, wherein:
threshold=1.2。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310383283.1A CN116090679B (en) | 2023-04-12 | 2023-04-12 | Power distribution network load prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310383283.1A CN116090679B (en) | 2023-04-12 | 2023-04-12 | Power distribution network load prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116090679A true CN116090679A (en) | 2023-05-09 |
| CN116090679B CN116090679B (en) | 2023-07-07 |
Family
ID=86199606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310383283.1A Active CN116090679B (en) | 2023-04-12 | 2023-04-12 | Power distribution network load prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116090679B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102723785A (en) * | 2012-07-03 | 2012-10-10 | 广东电网公司电力科学研究院 | Electric power load prediction method and electric power load prediction system based on collection of larger user intelligent terminal |
| JP2015122826A (en) * | 2013-12-20 | 2015-07-02 | 三菱電機株式会社 | Load prediction device for distribution system, and load prediction method for distribution system |
| CN105760963A (en) * | 2016-03-14 | 2016-07-13 | 中国能源建设集团江苏省电力设计院有限公司 | Tourist area resident household electricity prediction method |
| CN106532686A (en) * | 2016-11-09 | 2017-03-22 | 国网山东省电力公司济南供电公司 | Area power distribution network load prediction method based on electric automobile charging apparatus |
| CN111126663A (en) * | 2019-11-25 | 2020-05-08 | 黑龙江电力调度实业有限公司 | Short-term power load prediction method |
| CN113570246A (en) * | 2021-07-27 | 2021-10-29 | 广东电网有限责任公司 | Regional power grid dispatching control system and control method |
| CN113869616A (en) * | 2021-12-06 | 2021-12-31 | 国网湖北省电力有限公司经济技术研究院 | Self-adaptive residential user load prediction method |
| CN113989952A (en) * | 2021-10-22 | 2022-01-28 | 国网山东省电力公司利津县供电公司 | Power equipment inspection system based on distributed power supply network points |
| CN114118593A (en) * | 2021-11-30 | 2022-03-01 | 国网湖南省电力有限公司 | Population mobility prediction method and power grid load prediction method thereof |
-
2023
- 2023-04-12 CN CN202310383283.1A patent/CN116090679B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102723785A (en) * | 2012-07-03 | 2012-10-10 | 广东电网公司电力科学研究院 | Electric power load prediction method and electric power load prediction system based on collection of larger user intelligent terminal |
| JP2015122826A (en) * | 2013-12-20 | 2015-07-02 | 三菱電機株式会社 | Load prediction device for distribution system, and load prediction method for distribution system |
| CN105760963A (en) * | 2016-03-14 | 2016-07-13 | 中国能源建设集团江苏省电力设计院有限公司 | Tourist area resident household electricity prediction method |
| CN106532686A (en) * | 2016-11-09 | 2017-03-22 | 国网山东省电力公司济南供电公司 | Area power distribution network load prediction method based on electric automobile charging apparatus |
| CN111126663A (en) * | 2019-11-25 | 2020-05-08 | 黑龙江电力调度实业有限公司 | Short-term power load prediction method |
| CN113570246A (en) * | 2021-07-27 | 2021-10-29 | 广东电网有限责任公司 | Regional power grid dispatching control system and control method |
| CN113989952A (en) * | 2021-10-22 | 2022-01-28 | 国网山东省电力公司利津县供电公司 | Power equipment inspection system based on distributed power supply network points |
| CN114118593A (en) * | 2021-11-30 | 2022-03-01 | 国网湖南省电力有限公司 | Population mobility prediction method and power grid load prediction method thereof |
| CN113869616A (en) * | 2021-12-06 | 2021-12-31 | 国网湖北省电力有限公司经济技术研究院 | Self-adaptive residential user load prediction method |
Non-Patent Citations (3)
| Title |
|---|
| MD. RASHIDUL ISLAM 等: "LSTM-Based Electrical Load Forecasting for Chattogram City of Bangladesh", 《 2020 INTERNATIONAL CONFERENCE ON EMERGING SMART COMPUTING AND INFORMATICS (ESCI)》, pages 188 - 192 * |
| 向翰丞: "基于电力大数据的居民电量预测和可视化平台设计", 《中国优秀硕士学位论文全文数据库》, pages 042 - 557 * |
| 彭玉芹;: "配电网空间负荷预测方法的应用研究", 电力需求侧管理, no. 05, pages 27 - 30 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116090679B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Energy consumption and emission mitigation prediction based on data center traffic and PUE for global data centers | |
| CN115796393B (en) | Energy management optimization method, system and storage medium based on multi-energy interaction | |
| CN112178756A (en) | Intelligent heat supply management system and working method thereof | |
| CN109670694B (en) | Load prediction method for multi-energy supply system | |
| CN111144654A (en) | Park energy management configuration method and device based on Internet of things | |
| KR20150026230A (en) | Self running building energy management system using bim data | |
| CN115983430A (en) | Method and system for managing and optimizing comprehensive energy system | |
| CN102819770A (en) | Method for forecasting short-term load of distribution network based on human body comfort index | |
| CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
| CN115481918A (en) | Active sensing and predictive analysis system for unit state based on source network load storage | |
| Chuang et al. | Research on user electricity consumption behavior and energy consumption modeling in big data environment | |
| CN109858668B (en) | Coordination prediction method for power load region in thunder and lightning climate | |
| CN112987617A (en) | Near-zero energy consumption building digital management system and energy efficiency monitoring method | |
| CN114254838A (en) | Method for determining short-term power load prediction influence factor | |
| CN116090679B (en) | Power distribution network load prediction method | |
| CN112307675A (en) | Neural network-based temperature-sensitive load separation identification method and system | |
| CN116485036A (en) | Multi-energy-flow carbon emission short-term prediction method based on multi-task learning mechanism | |
| CN112465215A (en) | Distributed energy user side cold and heat power short-term load prediction method and system | |
| CN114662333A (en) | Intelligent power grid line loss detection system based on Internet of things | |
| CN116911583B (en) | Planning method, system and medium for electric vehicle charging station equipment | |
| CN116523148B (en) | Distribution network distribution transformer overload early warning method, device and equipment | |
| Afolabi et al. | Prediction of power consumption utilization in a cloud computing data centre using kalman filter parameters with genetic algorithm | |
| CN117578534B (en) | Scheduling method, device, equipment and storage medium of photovoltaic energy storage system | |
| CN115204446A (en) | Short-term electric quantity load accurate prediction method based on random forest | |
| CN117646935A (en) | Multifunctional air source heat pump control method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |