CN110046765A - A kind of power system stabilizer, PSS implementation method based on Elman neural network - Google Patents
A kind of power system stabilizer, PSS implementation method based on Elman neural network Download PDFInfo
- Publication number
- CN110046765A CN110046765A CN201910299226.9A CN201910299226A CN110046765A CN 110046765 A CN110046765 A CN 110046765A CN 201910299226 A CN201910299226 A CN 201910299226A CN 110046765 A CN110046765 A CN 110046765A
- Authority
- CN
- China
- Prior art keywords
- data
- wind power
- neural network
- prediction
- elman neural
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 72
- 239000003381 stabilizer Substances 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000001932 seasonal effect Effects 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 8
- 230000005611 electricity Effects 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 230000010355 oscillation Effects 0.000 claims description 6
- 230000000153 supplemental effect Effects 0.000 claims description 5
- 230000002401 inhibitory effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 210000004218 nerve net Anatomy 0.000 claims description 2
- 210000004205 output neuron Anatomy 0.000 claims description 2
- 238000013461 design Methods 0.000 abstract description 3
- 239000000843 powder Substances 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 2
- 241000208140 Acer Species 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
Classifications
-
- 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
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (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 present invention relates to Power Systems electric powder predictions, more particularly to a kind of power system stabilizer, PSS implementation method based on Elman neural network;Elman neural network is trained by modified history wind power by prediction day upper 1 year the same quarter first, will predict that wind performance number, to power system stabilizer, PSS, is established multiplied by the product value feedback after seasonal index number and is based on Elman neural network.Revised wind power historical data and corresponding historical wind speed data are normalized, the Elman neural network of foundation is trained, it will predict control errors within a preset range, prediction day breeze power is predicted according to prediction the last week day wind power using the Elman neural network after training, by wind power prediction value feedback to power system stabilizer, PSS.The present invention has the ability for adapting to time-varying characteristics and wind power swing, can directly predict the dynamic characteristic of wind power, precision of prediction is higher, can be widely applied in the design field of power system stabilizer, PSS.
Description
Technical field
The present invention relates to Power Systems electric powder prediction, more particularly to a kind of based on Elman neural network
Power system stabilizer, PSS implementation method.
Background technique
Wind-powered electricity generation accesses power grid on a large scale, and the safety problem of power grid is more and more prominent.Randomness, intermittence and poor controllability
Wind power plant access serial-parallel power grid makes the trend of regional power grid, stability change caused electric power system fault.Power train
When system breaks down, oscillation is generated to power grid, to reduce the stability of system.Therefore, wind power prediction correction value is introduced
Power system stability be very important.
Wind power prediction contributes to dispatcher and organizes electric system in advance, improves power supply quality, reduces electricity
Net operating cost.The design of power system stabilizer, PSS based on wind power prediction has act foot light at the grid-connected aspect of economy of wind-powered electricity generation
The research of the status of weight, the power system stabilizer, PSS technology of Jian hair wind power prediction realizes that large-scale wind power integration is for China
Necessary and urgent.
Summary of the invention
In view of the deficiencies of the prior art and the above problem, the present invention provides a kind of electric power based on Elman neural network
System stabilizer implementation method, which comprises the following steps:
S1, the wind power historical data and historical wind speed data for obtaining previous year the same quarter, while to the year
Effective number of days date type is classified according to day off and working day two types;
S2, the wind power historical data according to acquisition, calculate the same period average of the wind power in each month, to obtain
Month overall average, by each same period average divided by overall average obtain seasonal index number;
S3, wind power historical data are modified using seasonal index number, by wind power historical data and corresponding season
After index does ratio, revised wind power historical data are obtained;
S4, the input for determining Elman neural network, output data, and optimal hidden layer neuron number are established
Elman neural network;
S5, revised wind power historical data and corresponding historical wind speed supplemental characteristic are normalized, and
Elman neural network is trained according to the data after normalized, by the prediction error range of Elman neural network
It is interior;
S6, the wind power historical data for obtaining prediction the last week day, the wind speed parameter data for predicting day and date type are made
For the input of neural network, predicted using wind power of the Elman neural network after training to prediction day, and then obtain
Prediction data is multiplied by obtaining wind power prediction data after seasonal index number.
Wind power historical data described in the S1~S7 includes each hour wind power data.
The step S4 is further comprising the steps of:
S401, wind power historical data, historical wind speed data and date type are obtained, any day wind power data is made
For the output data of Elman neural network, wind power data and the wind of this day that each of will predict in the last week day hour
The input data of fast data and date type as Elman neural network;
S402, Elman neural network is initialized, set up based on Elman neural network.
Error range described in the step S5 is 1%~5%.
The step S5 is further comprising the steps of:
S501, revised wind power historical data and corresponding historical wind speed supplemental characteristic are returned according to the following formula
One change processing:
Wherein, ckFor k-th of parameter value in wind power historical data, cminMinimum where indicating in wind power data
Value, cmaxMaximum value where indicating in wind power data;
S502, according to the data after normalized by based on Elman neural network prediction control errors default
In error range.
The step S6 is further comprising the steps of:
S601, wind power historical data, air speed data and the date type for obtaining prediction the last week day, as Elman mind
Input through network, using the Elman neural network after training to the wind power prediction of prediction day, per small on the day of obtaining prediction day
When wind power prediction data;
S602, by the wind power prediction data of acquisition multiplied by seasonal index number after, obtain wind power data hourly;
After S603 obtains the practical wind power data on the day of predicting day, wind power prediction data and practical wind power number are calculated
Error amount between, and by error value back to Elman neural network.
By wind power prediction data feedback to power system stabilizer, PSS in the S603, stabilizer is by prediction data and reality
Value power data difference changes the correction value for inhibiting the power system oscillation containing wind-powered electricity generation as stabilizer.
The non-linear state space expression of the neural network based on Elman are as follows:
Y (k)=g (w3x(k))
X (k)=f (w1z(k)+w2u(k-1))
Z (k)=x (k-1)
Wherein, k indicates moment, y, x, and u, z respectively indicate m dimension output node vector, and m ties up hidden layer node unit vector, m
Dimensional input vector, m tie up feedback state vector;w3、w2、w1Respectively hidden layer is to the connection weight of output layer, and input layer is to implicit
Layer, the connection weight matrix of undertaking layer to hidden layer;F (*) is the transmission function of hidden layer neuron;G (*) is output neuron
Transmission function.
9, a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 1,
It is characterized in that: modified weight being carried out using BP algorithm to the neural network based on Elman, and index letter is carried out using mean function
Mathematics is practised, then target function formula are as follows:
E (x) is target function in formula,For target input vector.
The invention has the benefit that the present invention includes obtaining the wind power historical data of upper 1 year the same quarter and right
The historical wind speed data answered, and date type classification is carried out to the year effective number of days, according to the wind power historical data of acquisition, meter
The wind power same period average for calculating each month, takes each same period average and the ratio of season same period average value to refer to as season
Number, is modified wind power historical data using seasonal index number, so that it is determined that Elman neural network outputs and inputs number
According to, establish based on Elman neural network, and revised wind power historical data and historical wind speed data are normalized
Processing, is trained, by the pre- of Elman neural network according to Elman neural network of the data after normalized to foundation
Control errors are surveyed in default error range.Obtain wind power historical data, wind speed parameter data and the day of prediction the last week day
Input of the phase type as Elman neural network is carried out pre- using wind power of the Elman neural network after training to prediction day
It surveys, and then by the prediction data of acquisition multiplied by obtaining wind power data after seasonal index number.By wind power prediction value feedback to electric power
System stabilizer, stabilizer inhibit the oscillation of the electric system containing wind-powered electricity generation using the ratio of predicted value and actual value as correction value, from
And improve the stability of the electric system containing wind-powered electricity generation.Building of this method by the Elman neural network based on seasonal index number, knot
Relative region wind power historical data and corresponding historical wind speed data are closed, the wind power data of prediction day is obtained, considers
The characteristics of wind power is with seasonal variations influence of fluctuations stability of power system, by wind power prediction value feedback to power system stability
Device improves system stability to inhibit system oscillation.
Detailed description of the invention
Fig. 1 is flow diagram of the invention;
Fig. 2 is the Elman neural network structure schematic diagram that the present invention establishes;
Fig. 3 is stabilizer structure figure of the present invention;
Specific embodiment
Embodiment 1
In conjunction with the embodiments, the invention will be further described for attached drawing:
Fig. 1, the present invention provides a kind of power system stabilizer, PSS implementation methods based on Elman neural network, comprising:
S1 obtains the wind power historical data and historical wind speed data of previous year, while carrying out to effective number of days of this year
Date is sorted out.
S2 calculates the same period average of the wind power in each month according to maple wind power historical data, calculates the season same period
After the value of wind power averaging number, same period moon average is obtained into seasonal index number divided by the same period in season average value.
S3 is modified wind power historical data using seasonal index number, obtains the wind power correction data in each month.
S4 determines Elman neural network hidden layer neuron number, establish based on Elman neural network.
Revised wind power historical data and corresponding historical wind speed data are normalized in S5, according to returning
One changes that treated that data are trained Elman neural network, and by control errors in default error range.
S6 obtains wind power historical data, air speed data and the date type of prediction the last week day as Elman nerve net
The input of network, using the Elman neural network after training to the wind power prediction of prediction day, by the prediction data of acquisition multiplied by season
The wind power data predicted after section index.
Preset range described in the step S5 is 1%~5%.
The step S4 includes:
S401 obtains wind power historical data, historical wind speed data and date type, and any day wind power data is made
For the output data of Elman neural network, wind power data and the wind of this day that each of will predict in the last week day hour
The input data of fast data and date type as Elman neural network.
S402 initializes Elman neural network, set up based on Elman neural network.
As the embodiment preferentially selected, it is described based on Elman neural network non-linear state space expression
Are as follows:
Y (k)=g (w3x(k))
X (k)=f (w1z(k)+w2u(k-1))
Z (k)=x (k-1)
Wherein, k indicates moment, y, x, and u, z respectively indicate m dimension output node vector, and m ties up hidden layer node unit vector, m
Dimensional input vector, m tie up feedback state vector;w3、w2、w1Hidden layer is respectively indicated to the connection weight of output layer, input layer is to hidden
Containing layer, the connection weight matrix of undertaking layer to hidden layer;The transmission function of f (*) expression hidden layer neuron;G (*) indicates output
The transmission function of neuron.
The step S5 includes:
S501 is according to the following formula normalized revised wind power historical data, historical wind speed data:
Wherein, ckFor k-th of parameter value in wind power historical data sequence or historical wind speed supplemental characteristic ordered series of numbers, cmax
For the maximum value of institute's wind power.cminFor the minimum value of wind power.
S502 carries out error calculation, threshold value update and weight more according to the data Elman neural network after normalized
It is new so by based on Elman neural network prediction control errors in default error range.
By based on Elman neural network using BP algorithm carry out modified weight, and using mean function carry out index letter
Mathematics is practised, target function formula are as follows:
E (x) is target function in formula,For target input vector.
The step S6 includes:
S601 obtains wind power historical data, air speed data and the date type of prediction the last week day, as Elman nerve
The input of network obtains same day prediction day per hour using the Elman neural network after training to the wind power prediction of prediction day
Wind power prediction data.
S602 by the wind power prediction data of acquisition multiplied by seasonal index number after, obtain wind power data hourly
After S603 obtains the practical wind power data on the day of predicting day, wind power prediction data and practical wind power number are calculated
Error amount between, and by error value back to Elman neural network.
By wind power prediction value feedback to power system stabilizer, PSS, stabilizer is using the difference of predicted value and actual value as steady
Determine device and changes the correction value for inhibiting the power system oscillation containing wind-powered electricity generation.
The design method of electrical power stabilization device of the invention: by considering the modified wind power same period history number of seasonal index number
According to, it establishes and trains Elman neural network, and there is the wind power data of prediction the last week day to input as neural network, acquisition
Predict day breeze power, will prediction wind power data feedback to power system stabilizer, PSS, thus improve due to wind power with season,
The stability of electric system caused by fluctuations in wind speed.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (9)
1. a kind of power system stabilizer, PSS implementation method based on Elman neural network, which comprises the following steps:
S1, the wind power historical data and historical wind speed data for obtaining previous year the same quarter, at the same it is effective to the year
Number of days date type is classified according to day off and working day two types;
S2, the wind power historical data according to acquisition, calculate the same period average of the wind power in each month, to obtain month
Each same period average is obtained seasonal index number divided by overall average by overall average;
S3, wind power historical data are modified using seasonal index number, by wind power historical data and corresponding seasonal index number
After doing ratio, revised wind power historical data are obtained;
S4, the input for determining Elman neural network, output data, and optimal hidden layer neuron number establish Elman mind
Through network;
S5, revised wind power historical data and corresponding historical wind speed supplemental characteristic are normalized, and according to
Data after normalized are trained Elman neural network, will be in the prediction error range of Elman neural network;
S6, the wind power historical data for obtaining prediction the last week day, the wind speed parameter data for predicting day and date type are as mind
Input through network, the prediction predicted using wind power of the Elman neural network after training to prediction day, and then obtained
Data are multiplied by obtaining wind power prediction data after seasonal index number.
2. a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 1, feature
Be: wind power historical data described in the S1~S7 includes each hour wind power data.
3. a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 1, feature
Be: the step S4 is further comprising the steps of:
S401, wind power historical data, historical wind speed data and date type are obtained, using any day wind power data as
The output data of Elman neural network, by each of in prediction the last week day hours wind power data and the wind speed of this day
The input data of data and date type as Elman neural network;
S402, Elman neural network is initialized, set up based on Elman neural network.
4. a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 1, feature
Be: error range described in the step S5 is 1%~5%.
5. a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 1, feature
Be: the step S5 is further comprising the steps of:
S501, revised wind power historical data and corresponding historical wind speed supplemental characteristic are normalized according to the following formula
Processing:
Wherein, ckFor k-th of parameter value in wind power historical data, cminMinimum value where indicating in wind power data, cmax
Maximum value where indicating in wind power data;
S502, according to the data after normalized by based on Elman neural network prediction control errors in default error
In range.
6. a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 1, feature
Be: the step S6 is further comprising the steps of:
S601, wind power historical data, air speed data and the date type for obtaining prediction the last week day, as Elman nerve net
The input of network, it is hourly on the day of obtaining prediction day using the Elman neural network after training to the wind power prediction of prediction day
Wind power prediction data;
S602, by the wind power prediction data of acquisition multiplied by seasonal index number after, obtain wind power data hourly;
S603 obtain prediction day on the day of practical wind power data after, calculate wind power prediction data and practical wind power data it
Between error amount, and by error value back to Elman neural network.
7. a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 6, feature
Be: by wind power prediction data feedback to power system stabilizer, PSS in the S603, stabilizer is by prediction data and actual value
Power data difference changes the correction value for inhibiting the power system oscillation containing wind-powered electricity generation as stabilizer.
8. according to claim 1 to a kind of power system stabilizer, PSS implementation method based on Elman neural network described in 7,
It is characterized in that: the non-linear state space expression of the neural network based on Elman are as follows:
Y (k)=g (w3x(k))
X (k)=f (w1z(k)+w2u(k-1))
Z (k)=x (k-1)
Wherein, k indicates moment, y, x, and u, z respectively indicate m dimension output node vector, and m ties up hidden layer node unit vector, and m dimension is defeated
Incoming vector, m tie up feedback state vector;w3、w2、w1Respectively connection weight of the hidden layer to output layer, input layer to hidden layer,
Connection weight matrix of the undertaking layer to hidden layer;F (*) is the transmission function of hidden layer neuron;G (*) is output neuron
Transmission function.
9. a kind of power system stabilizer, PSS implementation method based on Elman neural network according to claim 1, feature
It is: modified weight is carried out using BP algorithm to the neural network based on Elman, and target function is carried out using mean function
It practises, then target function formula are as follows:
E (x) is target function in formula,For target input vector.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910299226.9A CN110046765A (en) | 2019-04-15 | 2019-04-15 | A kind of power system stabilizer, PSS implementation method based on Elman neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910299226.9A CN110046765A (en) | 2019-04-15 | 2019-04-15 | A kind of power system stabilizer, PSS implementation method based on Elman neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110046765A true CN110046765A (en) | 2019-07-23 |
Family
ID=67277064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910299226.9A Pending CN110046765A (en) | 2019-04-15 | 2019-04-15 | A kind of power system stabilizer, PSS implementation method based on Elman neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110046765A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268638A (en) * | 2014-09-11 | 2015-01-07 | 广州市香港科大霍英东研究院 | Photovoltaic power generation system power predicting method of elman-based neural network |
CN104636822A (en) * | 2015-01-21 | 2015-05-20 | 广州市香港科大霍英东研究院 | Residential load prediction method of elman-based neural network |
CN104899656A (en) * | 2015-06-05 | 2015-09-09 | 三峡大学 | Wind power combined predication method based on ensemble average empirical mode decomposition and improved Elman neural network |
CN106845694A (en) * | 2016-12-30 | 2017-06-13 | 深圳市麦澜创新科技有限公司 | A kind of wind energy, solar energy management system |
CN106971238A (en) * | 2017-03-10 | 2017-07-21 | 东华大学 | The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S |
-
2019
- 2019-04-15 CN CN201910299226.9A patent/CN110046765A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268638A (en) * | 2014-09-11 | 2015-01-07 | 广州市香港科大霍英东研究院 | Photovoltaic power generation system power predicting method of elman-based neural network |
CN104636822A (en) * | 2015-01-21 | 2015-05-20 | 广州市香港科大霍英东研究院 | Residential load prediction method of elman-based neural network |
CN104899656A (en) * | 2015-06-05 | 2015-09-09 | 三峡大学 | Wind power combined predication method based on ensemble average empirical mode decomposition and improved Elman neural network |
CN106845694A (en) * | 2016-12-30 | 2017-06-13 | 深圳市麦澜创新科技有限公司 | A kind of wind energy, solar energy management system |
CN106971238A (en) * | 2017-03-10 | 2017-07-21 | 东华大学 | The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yang et al. | Modelling a combined method based on ANFIS and neural network improved by DE algorithm: A case study for short-term electricity demand forecasting | |
CN104636822B (en) | A kind of resident load prediction technique based on elman neural networks | |
WO2011114752A1 (en) | Device for prediction of electricity generation amount, method for same, and program for same | |
CN105048499B (en) | Wind-electricity integration real-time scheduling method and system based on Model Predictive Control | |
JP2016136001A (en) | Prediction device | |
CN114362196B (en) | Multi-time-scale active power distribution network voltage control method | |
US20130138468A1 (en) | Power demand plan coordination device, power demand plan coordination method, and program | |
CN109787236A (en) | A kind of power system frequency Tendency Prediction method based on deep learning | |
US10474177B2 (en) | System and method for stability monitoring, analysis and control of electric power systems | |
CN109638812A (en) | A kind of adaptive distribution line very Short-Term Load Forecasting Method and system | |
CN107204615A (en) | A kind of method and system for realizing power prediction | |
CN111784100B (en) | Monthly plan mode generation method | |
CN103887813A (en) | Control method of wind power system operation based on wind power prediction uncertainty | |
JP2016123170A (en) | Prediction apparatus | |
US9639129B2 (en) | Hydroelectric power generation plan adjustment device, hydroelectric power generation plan adjustment method, and program | |
CN109146131A (en) | A kind of wind-power electricity generation prediction technique a few days ago | |
Roy et al. | Smart energy management for optimal economic operation in grid-connected hybrid power system | |
CN105590139A (en) | Short period wind power prediction method on the basis of minimal variance | |
CN110649633B (en) | Power distribution network reactive power optimization method and system | |
CN110046765A (en) | A kind of power system stabilizer, PSS implementation method based on Elman neural network | |
US11921482B2 (en) | Method of controlling a microgrid, power management system, and energy management system | |
CN106684930B (en) | A kind of active power for wind power control method considering power prediction confidence interval | |
CN106682760A (en) | Wind power climbing prediction method | |
US10985561B2 (en) | Method for monitoring and controlling an electrical network | |
TWI662423B (en) | Display system and method for wind power prediction |
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 |