CN108964019B - Power grid multi-element regulation and control method - Google Patents

Power grid multi-element regulation and control method Download PDF

Info

Publication number
CN108964019B
CN108964019B CN201810615099.4A CN201810615099A CN108964019B CN 108964019 B CN108964019 B CN 108964019B CN 201810615099 A CN201810615099 A CN 201810615099A CN 108964019 B CN108964019 B CN 108964019B
Authority
CN
China
Prior art keywords
power grid
output
day
regulation
node
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.)
Active
Application number
CN201810615099.4A
Other languages
Chinese (zh)
Other versions
CN108964019A (en
Inventor
滕云
王晴瀚
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.)
Shenyang University of Technology
Original Assignee
Shenyang University of Technology
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 Shenyang University of Technology filed Critical Shenyang University of Technology
Priority to CN201810615099.4A priority Critical patent/CN108964019B/en
Publication of CN108964019A publication Critical patent/CN108964019A/en
Application granted granted Critical
Publication of CN108964019B publication Critical patent/CN108964019B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • 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
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

A multivariate regulation and control method for a power grid is characterized in that a system repeatedly learns historical data of the same period of time in the previous day in a period of time, and continuously adjusts the regulation and control coefficient of the system through multiple iterations to determine the value of the output of each power generation unit of the power grid required by a node. And then adding the required output of all nodes in the power grid to obtain the planned output condition of each power generation unit of the power grid in the period of the next day. And then repeating the step in the next time period, and finally adjusting the output of each power generation unit of the power grid in all time periods of the whole day, so that the day-ahead plan is more accurate. And for the generated error, real-time regulation and control can be performed through AGC so as to ensure the stability of the frequency of the power grid.

Description

Multi-element regulation and control method for power grid
Technical Field
The invention belongs to the technical field of intelligent power grids, and particularly relates to a multivariate power grid coordination control method based on self-adaptive control of a multi-model neural network.
Background
In recent years, a new round of energy revolution is promoted worldwide, the adjustment of the structure of the energy industry in China is accelerated, the grid-connected capacity of clean energy represented by photovoltaic and wind power is increased continuously, the utilization of energy gradually forms the characteristics of high efficiency, diversification and intellectualization, and the accelerated improvement of a power grid is required to adapt to the national optimal configuration of energy. In the face of global environment deterioration and resource shortage pressure, energy conservation, emission reduction and energy utilization efficiency improvement become requirements which must be met by a future power grid. At present, the existing power grid regulation and control mainly adopts two scheduling modes of day-ahead scheduling plan and Automatic Generation Control (AGC). For the day-ahead scheduling plan, due to the fact that enough time is available for making the scheduling scheme, the scheduling plan of 24 periods in the future can be made on the basis of learning of a large amount of past historical data. However, because the day-ahead plan has large human participation factors, the related range is wide, the number of departments is large, and the errors between the output of each unit and the real-time load of each node of the power grid are often large; and the difficulty of power grid regulation is increased due to the defects of uncontrollable property, uncertainty and the like of wind power generation and photovoltaic power generation.
Disclosure of Invention
The invention aims to:
aiming at the defects in the prior art, the invention discloses a smart power grid regulation and control method based on a multi-model neural network self-adaptive regulation and control theory. The purpose is to solve the problems existing in the past.
The technical scheme is as follows:
in order to achieve the purpose, the invention adopts the following technical scheme to realize the purpose:
for each single power grid node, the system repeatedly learns the historical data of the same period of time in the previous day in a period of time, and continuously adjusts the regulation and control coefficient of the system through multiple iterations to determine the value of the output of each power generation unit of the power grid required by the node. And then adding the required output of all nodes in the power grid to obtain the planned output condition of each power generation unit of the power grid in the period of the next day. And then repeating the step in the next time period, and finally adjusting the output of each power generation unit of the power grid in all time periods of the whole day, so that the day-ahead plan is more accurate. And for generated errors, real-time regulation and control can be performed through AGC (automatic gain control) so as to ensure the frequency stability of the power grid.
The method comprises the following specific steps:
step 1: data acquisition:
load x of each node of power grid in different periods in power grid within P daysiAnd the output a of each thermal power generating unitl,pB output of each thermoelectric unitj,pC, each wind turbine generator set outputk,pAnd the output d of photovoltaic power generationpEnergy storage battery output spAnd the predicted load of each grid node at the same time every day
Figure BDA0001696720250000021
Day-ahead planned generating capacity of each generator set
Figure BDA0001696720250000022
Figure BDA0001696720250000025
(l ═ 1,2, L L), (j ═ 1,2, L J), (k ═ 1,2, L K), L, J, K are the number of thermal, thermoelectric, and wind turbines, respectively; (i ═ 1,2, L24), and i is the number of periods. (P-1, 2, L P), P is the total number of days observed. Such as al,pAnd representing the power output of the ith thermal power generating unit on the p day.
Step 2: and calculating the autonomous learning model of the single-node regulation and control system.
Step 2.1: defining a tuning model for the mth node control system:
Figure BDA0001696720250000023
wherein (M is 1,2, L M), and M is the total number of nodes in the power grid.
Defining a day-ahead planning model:
Figure BDA0001696720250000024
step 2.2: calculating the systematic adjustment error of each time period on the p day:
Figure BDA0001696720250000031
step 2.3: and defining an autonomous learning model of a regulation and control system.
The output scheme of each unit to the m node on the P +1 th day is as follows:
Figure BDA0001696720250000032
wherein WPFor post-iteration regulation of the coefficients, APTo adjust the matrix, αP、βPIs the correction factor of the P +1 th iteration.
And step 3: iterative determination of adaptive control model of regulation and control system for a single node
Step 3.1: calculating a correction factor
P-th iteration correction coefficient:
Figure BDA0001696720250000033
Figure BDA0001696720250000034
step 3.2: calculating a regulatory matrix
The p-th iteration regulation matrix:
Figure BDA0001696720250000035
step 3.3: and performing P iterations on the initial data, and determining the output of each power generation unit required by the mth power grid node on the P +1 th day.
And 4, step 4: and superposing the output of each power generation unit required by each node to obtain the total output of all the power generation units:
Figure BDA0001696720250000036
advantageous effects
According to past experience, the daily injection power change of each node of the power grid has strong similar characteristics, the load change of the nodes of the power grid at the same time every day and the output conditions of thermoelectric, thermal and wind generation units, photovoltaic power generation systems and energy storage systems at the same time are recorded by collecting panoramic operation information of the power grid, and a gradual learning type power grid regulation and control strategy is established by learning past data and self-adaptive control of a power grid regulation and control system. The method can accurately calculate the day-ahead power generation of the power grid, balance the load of each node of the power grid and the power generation capacity of the power grid, and stabilize the frequency of the power grid.
In other words, the method provided by the invention learns historical data through the power grid regulation and control system, establishes a system self-adaptive control model, comprehensively regulates and controls the output of a plurality of power generation units of thermal power, thermoelectricity, wind power, photovoltaic and energy storage, and improves the precision of the day-ahead plan. In addition, compared with the traditional scheduling method, the method provided by the invention is less influenced by human factors, and the scheduling efficiency is improved.
Drawings
Fig. 1 is a flow chart of adaptive control of a power grid control system.
FIG. 2 is a diagram of multi-model neural network adaptation for a single node.
FIG. 3 is a 16-20 point self-adaptive control planned power generation curve, an original day-ahead planned curve and an actual load curve of a certain local power grid on a certain day.
Detailed Description
For the power grid universe multivariate coordination control method based on the multi-model neural network adaptive control, the method is implemented by taking the actual operation condition calculation of a certain power grid as an example:
the number of the nodes of a local power grid is 5, and the load in the ith time interval every day in 10 days is as follows:
number of days 1 2 3 4 5 6 7 8 9 10
Load (kVA) 499.5 502.3 511.1 496.2 490.9 503.7 508.9 500.1 492.8 503.3
The load of each power grid node in the period within 10 days is as follows:
Figure BDA0001696720250000041
Figure BDA0001696720250000051
in the period of 10 days in the power grid, the output conditions of all the units are as follows:
Figure BDA0001696720250000052
the planned output condition of each generator set in 10 days of the power grid is as follows:
Figure BDA0001696720250000053
Figure BDA0001696720250000061
further, α0＝α1＝1，β0＝β1＝1，
Figure BDA0001696720250000062
Estimated value
Figure BDA0001696720250000063
1. Aiming at the first node of the local power grid, the data of the first day and the second day are brought into a correction coefficient formula:
Figure BDA0001696720250000064
Figure BDA0001696720250000065
calculated to alpha1,2＝1.032，β1,2＝0.984，
Figure BDA0001696720250000066
2. Substituting the correction coefficients of the first iteration into the model:
Figure BDA0001696720250000067
get W by solution1，1＝0.4897，
Figure 4
3. Repeating the last step P-1 (P10) times to obtain W1，11＝0.5011，
Figure 3
Namely the output requirement of each generator set by the node I.
4. Repeating the first two steps, and calculating by iteration
Figure BDA0001696720250000071
5. And summing the output requirements of each node on each power generation unit, namely the day-ahead plan subjected to system self-adaptive adjustment.
A16-20 point self-adaptive control planned power generation curve, an original day-ahead planned curve and an actual load curve of a certain power grid on a certain day are shown in figure 3.
As can be seen from fig. 3, the grid adaptive control power generation plan is significantly closer to the actual power generation in the time range of 16-20 points.
In summary, the invention provides an artificial intelligent power grid regulation and control strategy based on a multi-model neural network adaptive control theory aiming at the previous strategy defects. In the existing power system network, a day-ahead plan is adjusted by learning past data and monitoring real-time grid load. As thermal power, thermoelectricity, a small amount of wind power and photovoltaic power generation are mainly adopted in northern areas of China, only the power grid dispatching condition containing the thermal power, the wind power, hot spots, the photovoltaic power generation and an energy storage system is discussed.

Claims (2)

1. A power grid multivariate regulation and control method is characterized by comprising the following steps: for each single power grid node, the system repeatedly learns historical data of the same time period in the previous day in a period of time, and continuously adjusts the regulation and control coefficient of the system through multiple iterations to determine the value of the output of each power generation unit of the power grid required by the node; adding the output required by all nodes in the power grid to obtain the planned output condition of each power generation unit of the power grid in the period of the next day; then repeating the step in the next time period, and finally adjusting the output of each power generation unit of the power grid in all time periods of the whole day to make the day-ahead plan more accurate; for the error, real-time regulation and control are carried out through AGC;
the method comprises the following specific steps:
step 1: data acquisition:
load x of each node of power grid in different periods in power grid within P daysiAnd the output a of each thermal power generating unitl,pB output of each thermoelectric unitj,pAnd c output of each wind turbine generatork,pAnd the output d of photovoltaic power generationpEnergy storage battery output spAnd the predicted load of each grid node at the same time every day
Figure FDA0003602391670000011
Day-ahead planned generating capacity of each generator set
Figure FDA0003602391670000012
Figure FDA0003602391670000013
L, J, K are the numbers of thermal power, thermoelectric and wind power generation units respectively; i is 1,2, … 24, i is the time period number; p is 1,2, … P, P is total number of days observed, such as al,pRepresenting the power output of the ith thermal power generating unit on the p day;
step 2: calculating an autonomous learning model of the single-node regulation and control system;
and step 3: determining a regulation and control system adaptive control model aiming at a single node through iteration;
and 4, step 4: and (3) superposing the output of each power generation unit required by each node to obtain the total output of each power generation unit:
Figure FDA0003602391670000014
m is the total number of nodes in the power grid;
in the step 3:
step 3.1: calculating a correction factor
P-th iteration correction coefficient:
Figure FDA0003602391670000021
Figure FDA0003602391670000022
Δpadjusting the error of the system for each time interval on the p day;
step 3.2: calculating a regulatory matrix
The p-th iteration regulation matrix:
Figure FDA0003602391670000023
step 3.3: and performing P iterations on the initial data, and determining the output of each power generation unit required by the mth power grid node on the P +1 th day.
2. The power grid multivariate regulation and control method as claimed in claim 1, characterized in that:
in the step 2:
step 2.1: defining a tuning model for the mth node control system:
Figure FDA0003602391670000024
wherein M is 1,2, … M, and M is the total number of nodes in the power grid;
defining a day-ahead planning model:
Figure FDA0003602391670000025
step 2.2: calculating the systematic adjustment error of each time period on the p day:
Figure FDA0003602391670000026
step 2.3: defining an autonomous learning model of a regulation and control system:
the output scheme of each unit to the m node on the P +1 th day is as follows:
Figure FDA0003602391670000031
wherein Wm,PFor post-iteration regulation of the coefficients, APTo adjust the matrix, αm,P+1、βm,P+1Correction system for P +1 th iterationAnd (4) counting.
CN201810615099.4A 2018-06-14 2018-06-14 Power grid multi-element regulation and control method Active CN108964019B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810615099.4A CN108964019B (en) 2018-06-14 2018-06-14 Power grid multi-element regulation and control method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810615099.4A CN108964019B (en) 2018-06-14 2018-06-14 Power grid multi-element regulation and control method

Publications (2)

Publication Number Publication Date
CN108964019A CN108964019A (en) 2018-12-07
CN108964019B true CN108964019B (en) 2022-05-27

Family

ID=64489105

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810615099.4A Active CN108964019B (en) 2018-06-14 2018-06-14 Power grid multi-element regulation and control method

Country Status (1)

Country Link
CN (1) CN108964019B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104881706A (en) * 2014-12-31 2015-09-02 天津弘源慧能科技有限公司 Electrical power system short-term load forecasting method based on big data technology
CN105576699A (en) * 2016-01-12 2016-05-11 四川大学 Independent micro-grid energy storage margin detection method
US20160156186A1 (en) * 2010-07-02 2016-06-02 General Electric Technology Gmbh Multi-interval dispatch method for enabling dispatchers in power grid control centers to manage changes background

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160156186A1 (en) * 2010-07-02 2016-06-02 General Electric Technology Gmbh Multi-interval dispatch method for enabling dispatchers in power grid control centers to manage changes background
CN104881706A (en) * 2014-12-31 2015-09-02 天津弘源慧能科技有限公司 Electrical power system short-term load forecasting method based on big data technology
CN105576699A (en) * 2016-01-12 2016-05-11 四川大学 Independent micro-grid energy storage margin detection method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Load control for supply-demand balancing under Renewable Energy forecasting;Daud Mustafa Minhas et al;《2017 IEEE Second International Conference on DC Microgrids (ICDCM)》;20170807;第365-370页 *
一种未来电网调控策略研究;陶旭嫣等;《山东电力技术》;20161031;第43卷(第10期);第7-11页 *

Also Published As

Publication number Publication date
CN108964019A (en) 2018-12-07

Similar Documents

Publication Publication Date Title
CN106981888B (en) Wind based on multi-source complementation stores the multiple target dynamic dispatching method of Thermal and Hydroelectric Power Systems
CN107301472B (en) Distributed photovoltaic planning method based on scene analysis method and voltage regulation strategy
CN110365013B (en) Capacity optimization method of photo-thermal-photovoltaic-wind power combined power generation system
CN112396220B (en) Optimized scheduling method for wind power-containing and demand side resources based on scene reduction
CN109886567B (en) Short-term load prediction method considering somatosensory temperature and radiation intensity
CN111092451B (en) Photovoltaic consumption early warning method based on power distribution network grid
CN109066747B (en) Capacity allocation method for multi-energy complementary power station energy storage system meeting three-section line requirement of power grid
CN113054688B (en) Renewable energy cluster output distributed coordination control method considering uncertainty
CN110571850B (en) Wind power plant power fluctuation track prediction and correction control method
CN111612244B (en) QRA-LSTM-based method for predicting nonparametric probability of photovoltaic power before day
CN110826805B (en) Low-water-head cascade hydropower station medium-term optimization scheduling method considering water unevenness
CN109474007B (en) Energy internet scheduling method based on big data cloud technology
CN108964121B (en) Wind, light and water real-time control method considering water and power planning and power target in day before water and power
CN114707767A (en) Method for predicting peak-adjustable power of new energy power system in off-peak period
CN116526469A (en) Long-term random dynamic scheduling method for water-wind-solar complementary system
CN113363976B (en) Scene graph-based wind-solar-water complementary power generation system medium-term optimization scheduling method
Zhang et al. Joint optimization of the number, type and layout of wind turbines for a new offshore wind farm
CN108964019B (en) Power grid multi-element regulation and control method
CN112598175A (en) Watershed type virtual power plant scheduling method
CN116706869A (en) Prediction method and device for supply and demand balance scene of regional power grid
CN107453366B (en) UPFC-containing multi-target optimal power flow calculation method considering wind power decision risk
CN114530848B (en) Multi-time scale dynamic partitioning method for optical storage virtual power plant
CN113394820B (en) Optimized scheduling method for new energy grid-connected power system
CN114188942A (en) Power grid dispatching method comprising large-scale new energy base
CN110717694B (en) Energy storage configuration random decision method and device based on new energy consumption expected value

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