CN111178618A - Intelligent power grid load prediction method - Google Patents
Intelligent power grid load prediction method Download PDFInfo
- Publication number
- CN111178618A CN111178618A CN201911352796.6A CN201911352796A CN111178618A CN 111178618 A CN111178618 A CN 111178618A CN 201911352796 A CN201911352796 A CN 201911352796A CN 111178618 A CN111178618 A CN 111178618A
- Authority
- CN
- China
- Prior art keywords
- newton interpolation
- load
- adopting
- park
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000005611 electricity Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000010248 power generation Methods 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 3
- 238000009472 formulation Methods 0.000 abstract 1
- 239000000203 mixture Substances 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000000611 regression analysis Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a load prediction method of an intelligent power grid, which is technically characterized by comprising the following steps: collecting 12-month electricity load data of a park in one year, and observing the trend condition of the park; selecting proper training data for training and predicting a Newton interpolation model; predicting the power load data of the missing month by adopting a Newton interpolation method; correcting a Newton interpolation result by adopting a post error estimation method; and calculating the relative error between the final Newton interpolation result and the true value, thereby completing the load prediction of the intelligent power grid. The method is reasonable in design, can accurately predict the short-term electric load condition of the park, is simple and easy to realize, does not need to fit a specific function form, can predict and obtain a better prediction effect by only a few data points, and can provide a reference basis for power grid scheduling formulation and power generation and supply plans.
Description
Technical Field
The invention belongs to the technical field of smart power grids, and particularly relates to a load prediction method for a smart power grid.
Background
The forecasting of the electric load of the park is an important link in the planning of an electric power system, and the problem of balance of supply and demand of electric energy caused by the fact that the electric energy cannot be stored in a large scale is solved, so that the quality of power supply is guaranteed.
With the development of an electric power system EMS, short-term load prediction becomes one of necessary links of the EMS nowadays, support is provided for guaranteeing safe and economic operation of the electric power system, and the method is mainly used for optimizing unit start-stop, hydropower plan, water, fire and electricity coordination and power exchange plan. By accurately predicting the short-term power load, a reference basis can be provided for the power grid scheduling and making a power generation and supply plan, the balance of supply and demand of electric energy in the power grid is guaranteed, and data support can be provided for the production, transmission, distribution and sale of estimated electric energy, so that a power system can make a more economic and reasonable power generation and utilization scheme, and the aims of energy management and control, energy conservation and emission reduction are achieved.
At present, regression analysis is mostly adopted to establish a mathematical model for forecasting the power load of a park, so that the fitting precision is low due to irregular data points, and the accurate management and control requirements of the intelligent power grid are difficult to meet.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for predicting the load of an intelligent power grid, which has the advantages of reasonable design, accurate prediction result and high efficiency.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
a smart grid load prediction method comprises the following steps:
step 1, collecting power load data of a park in 12 months in one year, and observing the trend condition of the park;
2, selecting proper training data for training and predicting a Newton interpolation model;
step 3, predicting the power load data of the missing month by adopting a Newton interpolation method;
and 5, calculating the relative error between the final Newton interpolation result and the true value, thereby completing the load prediction of the intelligent power grid.
The newton interpolation method is calculated according to the following formula:
f(x)=f(x0)+(x-x0)f(x,x0)+…+(x-x0)…(x-xn-1)f(x,x0,…,xn-1)+(x-x0)…(x-xn-1)(x-xn)f(x,x0,…,xn)
in the formula, f (x) is the electricity consumption data of the missing month; f (x, x)0) Is a first order difference quotient, f (x, x)0,…,xn) Is the N-order difference quotient.
The quotient of each step of the Newton interpolation method is calculated by adopting the following formula:
f(x)=f(x0)+(x-x0)f(x,x0)
f(x,x0)=f(x,x1)+(x-x1)f(x,x0,x1)
f(x,x0,x1)=f(x0,x1,x2)+(x-x2)f(x,x0,x1,x2)
…
f(x,x0,…,xn-1)=f(x0,x1,…,xn)+(x-xn)f(x,x0,…,xn)
in the formula, y represents a modified Newton interpolation result; f (x)1) Representing the result of the first Newton interpolation; f (x)2) Representing the second Newton interpolation result; x is the number of1,x2,x3Here representing different months.
The step 5 adopts the following formula to calculate the relative error:
σ=(y-yture)/yture*100%
in the formula, y represents a modified Newton interpolation result; y istureRepresenting the true value.
The invention has the advantages and positive effects that:
1. according to the method, on the basis of the collected historical load data, the short-term load trend is predicted by modeling analysis of the load by adopting a Newton interpolation method, a specific function form does not need to be fitted, the problem that the fitting precision of a regression analysis method is low due to irregular data points is solved, and the prediction result is more accurate.
2. The method adopts a Newton interpolation method, does not need to predict the electric load data for a long time, can simply calculate by only needing a plurality of data points, and greatly simplifies the requirement of data quantity.
3. The method can predict the power load data at any time in a certain time period, and the power load has periodicity, so that the prediction result of the method is also effective in the next period, and a reference basis is provided for the dispatching and making of a power generation and supply plan of a power grid in a park.
4. The intelligent park energy efficiency management and control system is reasonable in design, plays an important role in realizing resource regulation and control, guaranteeing balance of power supply and demand and guaranteeing power quality through short-term load prediction, can provide reference basis for energy efficiency management and control of the intelligent park, effectively realizes optimal allocation of resources and load balancing, and improves management energy efficiency.
Drawings
FIG. 1 is a prediction flow diagram of the present invention;
figure 2 is a plot of the electrical load trend for a campus.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
A method for predicting the load of a smart grid is disclosed, as shown in FIG. 1, and comprises the following steps:
step 1, collecting the electricity load data of the park in 12 months in one year, and observing the trend condition of the park.
In this step, as can be seen from fig. 2, the change of the power consumption with time has no obvious trend, so that the prediction of the power load cannot be performed by a simple regression analysis method, and the newton interpolation rule is a good choice.
The electricity consumption data of the 12 months in the park are shown in table 1.
TABLE 1 campus electricity load data for 24 hours (kWh)
And 2, selecting proper training data for training and predicting the Newton interpolation model.
In this step, for error estimation and correction, three sets of data are selected for model calculation, corresponding to 1,3,4 and 1,3,5 in months, respectively. The data for months 1,3,4 and 1,3,5 are used to predict the power load for month 2.
And 3, predicting the missing monthly electric load data by adopting a Newton interpolation method.
In this step, the newton interpolation model is calculated according to the following formula:
f(x)=f(x0)+(x-x0)f(x,x0)+…+(x-x0)…(x-xn-1)f(x,x0,…,xn-1)+(x-x0)…(x-xn-1)(x-xn)f(x,x0,…,xn)
in the formula, f (x) is the electricity consumption data of the missing month; f (x, x)0) Is a first order difference quotient, like f (x, x)0,…,xn) Is the N-order difference quotient; the difference quotient f (x, x)0,…,xn) The calculation formula is as follows:
the difference quotient is calculated as follows:
f(x)=f(x0)+(x-x0)f(x,x0)
f(x,x0)=f(x,x1)+(x-x1)f(x,x0,x1)
f(x,x0,x1)=f(x0,x1,x2)+(x-x2)f(x,x0,x1,x2)
…
f(x,x0,…,xn-1)=f(x0,x1,…,xn)+(x-xn)f(x,x0,…,xn)
and calculating to obtain the difference quotient of each order shown in the tables 2 and 3 according to the calculation formula of the difference quotient and by combining the selected data.
TABLE 2.1,3,4 months power consumption difference quotient calculation results
TABLE 3.1,3,5 months power consumption difference quotient calculation results
If the result of the first Newton interpolation is recorded as f (2)1Then, according to table 2:
f(2)1=9000+(2-1)*(-500)+(2-1)*(2-3)*(-333.3)=8833.3
if the result of the second Newton interpolation is recorded as f (2)2Similarly, from table 3, we can obtain:
f(2)2=9000+(2-1)*(-500)+(2-1)*(2-3)*0=8500
and 4, step 4: and correcting the Newton interpolation result by adopting a post error estimation method, wherein the result corrected by the post error estimation method is as follows:
in the formula, y represents a modified Newton interpolation result; f (x)1) Representing the result of the first Newton interpolation; f (x)2) Representing the second Newton interpolation result; x is the number of1,x2,x3Here representing different months.
And 5: the relative error of the final newton interpolation result from the true value is calculated as follows:
σ=(y-yture)/yture*100%=(9499.9-10000)/10000*100%=-5.001%
in the formula, y represents a modified Newton interpolation result; y istureRepresenting the true value.
Through the steps, the electricity utilization load of the designated month can be predicted, and the relative error is low.
It should be emphasized that the embodiments described herein are illustrative rather than restrictive, and thus the present invention is not limited to the embodiments described in the detailed description, but other embodiments derived from the technical solutions of the present invention by those skilled in the art are also within the scope of the present invention.
Claims (5)
1. A method for predicting the load of a smart grid is characterized by comprising the following steps:
step 1, collecting power load data of a park in 12 months in one year, and observing the trend condition of the park;
2, selecting proper training data for training and predicting a Newton interpolation model;
step 3, predicting the power load data of the missing month by adopting a Newton interpolation method;
step 4, correcting a Newton interpolation result by adopting a post error estimation method;
and 5, calculating the relative error between the final Newton interpolation result and the true value, thereby completing the load prediction of the intelligent power grid.
2. The smart grid load prediction method according to claim 1, wherein: the newton interpolation method is calculated according to the following formula:
f(x)=f(x0)+(x-x0)f(x,x0)+…+(x-x0)…(x-xn-1)f(x,x0,…,xn-1)+(x-x0)…(x-xn-1)(x-xn)f(x,x0,…,xn)
in the formula, f (x) is the electricity consumption data of the missing month; f (x, x)0) Is a first order difference quotient, f (x, x)0,…,xn) Is the N-order difference quotient.
3. The smart grid load prediction method according to claim 2, wherein: the quotient of each step of the Newton interpolation method is calculated by adopting the following formula:
f(x)=f(x0)+(x-x0)f(x,x0)
f(x,x0)=f(x,x1)+(x-x1)f(x,x0,x1)
f(x,x0,x1)=f(x0,x1,x2)+(x-x2)f(x,x0,x1,x2)
…
f(x,x0,…,xn-1)=f(x0,x1,…,xn)+(x-xn)f(x,x0,…,xn) 。
4. the smart grid load prediction method according to claim 1, wherein: step 4, correcting the post error by adopting the following formula:
in the formula, y represents a modified Newton interpolation result; f (x)1) Representing the result of the first Newton interpolation; f (x)2) Representing the second Newton interpolation result; x is the number of1,x2,x3Here representing different months.
5. The smart grid load prediction method according to claim 1, wherein: the step 5 adopts the following formula to calculate the relative error:
σ=(y-yture)/yture*100%
in the formula, y represents a modified Newton interpolation result; y istureRepresenting the true value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911352796.6A CN111178618A (en) | 2019-12-25 | 2019-12-25 | Intelligent power grid load prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911352796.6A CN111178618A (en) | 2019-12-25 | 2019-12-25 | Intelligent power grid load prediction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111178618A true CN111178618A (en) | 2020-05-19 |
Family
ID=70652150
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911352796.6A Pending CN111178618A (en) | 2019-12-25 | 2019-12-25 | Intelligent power grid load prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111178618A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112668765A (en) * | 2020-12-23 | 2021-04-16 | 韶关东阳光科技研发有限公司 | Method and device for load prediction and energy management of power consumers of aluminum processing enterprises |
CN113864372A (en) * | 2021-11-01 | 2021-12-31 | 中国第一汽车股份有限公司 | Transmission predictive thermal protection method and automobile |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103208091A (en) * | 2013-04-25 | 2013-07-17 | 国家电网公司 | Electric larceny preventing method based on data mining of electric load management system |
CN103236025A (en) * | 2013-04-25 | 2013-08-07 | 国家电网公司 | Data consolidation processing method based on power user data |
CN109633262A (en) * | 2019-01-29 | 2019-04-16 | 国网湖南省电力有限公司 | Three phase harmonic electric energy gauging method, device based on composite window multiline FFT |
-
2019
- 2019-12-25 CN CN201911352796.6A patent/CN111178618A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103208091A (en) * | 2013-04-25 | 2013-07-17 | 国家电网公司 | Electric larceny preventing method based on data mining of electric load management system |
CN103236025A (en) * | 2013-04-25 | 2013-08-07 | 国家电网公司 | Data consolidation processing method based on power user data |
CN109633262A (en) * | 2019-01-29 | 2019-04-16 | 国网湖南省电力有限公司 | Three phase harmonic electric energy gauging method, device based on composite window multiline FFT |
Non-Patent Citations (2)
Title |
---|
于波等: "基于负荷预测的园区供热系统运行优化技术", 《电力建设》 * |
无: "插值法的事后误差估计", 《豆丁网DOCIN.COM/P-1007060479.HTML》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112668765A (en) * | 2020-12-23 | 2021-04-16 | 韶关东阳光科技研发有限公司 | Method and device for load prediction and energy management of power consumers of aluminum processing enterprises |
CN113864372A (en) * | 2021-11-01 | 2021-12-31 | 中国第一汽车股份有限公司 | Transmission predictive thermal protection method and automobile |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102074954B (en) | Comprehensive energy-conservation evaluation and decision-making method for urban and rural distribution network | |
CN103296679B (en) | The medium-term and long-term long-term wind power run that optimizes of power system is exerted oneself model modelling approach | |
CN103942613B (en) | Method for grid and province two-stage real-time generation schedule coordinative optimization under generalized tie line mode | |
CN104537428B (en) | One kind meter and the probabilistic economical operation appraisal procedure of wind power integration | |
Pagani et al. | Generating realistic dynamic prices and services for the smart grid | |
CN103530696A (en) | Thermal power generating unit medium and long-term time sequence progressive power generation coordination algorithm considering wind power uncertainty | |
CN117239740B (en) | Optimal configuration and flexibility improvement method and system for virtual power plant system | |
CN111738498B (en) | Robust planning method and system for comprehensive energy system | |
CN111178618A (en) | Intelligent power grid load prediction method | |
Zhang et al. | Study on generation and transmission maintenance scheduling under electricity market | |
Martinez-Rico et al. | Energy storage sizing based on automatic frequency restoration reserve market participation of hybrid renewable power plants | |
CN114792994A (en) | New energy and outgoing connecting line time sequence production simulation optimization method and system | |
Pruckner et al. | A study on the impact of packet loss and latency on real-time demand response in smart grid | |
Ding et al. | A dynamic period partition method for time-of-use pricing with high-penetration renewable energy | |
Veselov et al. | Modeling price effects of upgrading strategies of thermal power plants on the basis of low carbon technologies in a competitive market | |
CN113394820A (en) | Optimized scheduling method for new energy grid-connected power system | |
Yang et al. | Two-Stage Low-Carbon Optimal Scheduling of Power System Based on Carbon Flow Theory and Demand Response | |
Voulis et al. | Storage coordination and peak-shaving operation in urban areas with high renewable penetration | |
Duan et al. | Rolling dispatch of demand response resources considering renewable energy accommodation | |
CN109390938A (en) | A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device | |
CN110912117B (en) | Power balance calculation method and device | |
CN117498467B (en) | Energy coordination control distribution method and system based on multi-level virtual power plant | |
Xiang et al. | Hierarchical multi-objective unit commitment optimization considering negative peak load regulation ability | |
Wang et al. | Requirement Assessment of Demand-side Flexibility for New Power Systems with High Penetration of Renewable Generation | |
Dannecker et al. | The European electricity market: A market study |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |
|
RJ01 | Rejection of invention patent application after publication |