CN107464007A - Continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle - Google Patents
Continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle Download PDFInfo
- Publication number
- CN107464007A CN107464007A CN201610384138.5A CN201610384138A CN107464007A CN 107464007 A CN107464007 A CN 107464007A CN 201610384138 A CN201610384138 A CN 201610384138A CN 107464007 A CN107464007 A CN 107464007A
- Authority
- CN
- China
- Prior art keywords
- mtd
- mrow
- wind
- power
- msup
- 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 18
- 230000005611 electricity Effects 0.000 claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims abstract description 15
- 230000007704 transition Effects 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 238000012614 Monte-Carlo sampling Methods 0.000 claims abstract description 3
- 238000005070 sampling Methods 0.000 claims description 6
- 101100001674 Emericella variicolor andI gene Proteins 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 4
- 238000012546 transfer Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
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)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
Abstract
The present invention proposes a kind of continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle, sets anticipation to carry out the continuous time hop count of Load flow calculation first, Markov chain model is established according to the historical data of regional wind power；Then the state vector of power probability distribution and the state vector that the wind-powered electricity generation prediction power probability of state transition probability matrix calculating subsequent time is distributed are predicted according to current time wind-powered electricity generation, use ratio distribution principle and Monte Carlo sampling are sampled to subsequent time wind-powered electricity generation prediction power and variable, establish the sample matrix of wind-powered electricity generation prediction power and variable；The sample matrix for finally predicting power and variable according to wind-powered electricity generation carries out continuous time probabilistic load flow.The probabilistic load flow of single point in time is generalized in continuous time section by the present invention, and can predict each Branch Power Flow of power probability the forecast of distribution distribution situation at each moment and trend of development in continuous time according to initial wind-powered electricity generation.
Description
Technical field
The invention belongs to Power System Analysis technical field, and in particular to a kind of Markov reason based on pro rate principle
By continuous time Probabilistic Load Flow Forecasting Methodology.
Background technology
With extensive generation of electricity by new energy access power network, generation of electricity by new energy is predicted can prevent generation of electricity by new energy with
Machine adversely affects to caused by Operation of Electric Systems.If the trend of the power system in continuous time can be carried out pre-
Survey, the probability distribution situation of each moment Branch Power Flow can be predicted, and can obtains what Branch Power Flow in continuous time was distributed
It development trend, can be more beneficial for planning the planning of generation of electricity by new energy access amount in power system, the stable of power system is transported
Row has important directive significance.Nowadays in the case where extensive generation of electricity by new energy accesses, Branch Power Flow is carried out continuous
Prediction in period does not obtain the common concern of researcher also, therefore needs research one kind to predict in continuous time
The method of Probabilistic Load Flow.
The content of the invention
The present invention proposes a kind of Markov theory continuous time Probabilistic Load Flow Forecasting Methodology based on pro rate principle, can
To predict the probability distribution feelings at power probability forecast of distribution Branch Power Flow each moment in continuous time according to initial wind-powered electricity generation
Condition and development trend.
In order to solve the above-mentioned technical problem, the present invention provides a kind of continuous based on Markov theory and pro rate principle
Period Probabilistic Load Flow Forecasting Methodology, it is characterised in that step is as follows：
Step 1, set anticipation to carry out the continuous time hop count of Load flow calculation, built according to the historical data of regional wind power
Vertical wind power Markov chain model；
Step 2, the shape being distributed according to the wind power Markov chain model and initial time wind-powered electricity generation prediction power probability
State vector calculates the state vector of the wind-powered electricity generation prediction power probability distribution of subsequent time；Proportion of utilization distribution principle calculates next
Moment wind-powered electricity generation predicts the frequency in sampling of each state interval of power and variable；Using Monte Carlo sampling respectively to the pre- measurement of power of wind-powered electricity generation
Each state interval of rate variable is sampled to obtain corresponding wind-powered electricity generation prediction performance number；Predict that performance number is established according to the wind-powered electricity generation
Wind-powered electricity generation predicts the sample matrix of power and variable；
Step 3, the sample matrix that the wind-powered electricity generation predicts power and variable is entered as the input quantity of certainty power flow algorithm
Row probabilistic load flow；Carry out cycle calculations when, every time circulation selection wind-powered electricity generation prediction power and variable sample matrix row to
Amount completes the probabilistic load flow at a moment, the probabilistic load flow until completing each moment in continuous time；Root
It is fitted, is obtained using Density Estimator according to the discrete results of each moment output variable in the continuous time obtained by cycle calculations
The probability distribution curve of output variable.
Further, wind power Markov chain model is established according to the historical data of regional wind power in the step 1
Method be：State interval is divided to wind power according to the historical data of regional wind power, calculates each shape of wind power
Transition probability value between state establishes wind power so as to obtain state transition probability matrix according to state transition probability matrix
Markov chain model；The Markov chain model of the wind power such as (1) is shown,
In formula (1)：pk ijState transition probability matrix PkAn element, represent wind power drilled from state i to state j
The probability of change, andI, j=1,2 ... m；M is the state for being divided into power historical data at equal intervals
The number in section, Nk ijFor wind power variable XkThe number developed from state i to state j, k ∈ K, K are wind-powered electricity generation
The number of field
Compared with prior art, its remarkable advantage is the present invention, of the invention by Markov theory and pro rate principle
It is combined with Monte Carlo Analogue Method probabilistic load flow, the probabilistic load flow of single point in time is generalized to continuous time section
It is interior, and can according to initial wind-powered electricity generation predict power probability forecast of distribution Branch Power Flow in continuous time each moment it is general
Rate distribution situation and development trend.
Brief description of the drawings
Fig. 1 is Markov theory continuous time Probabilistic Load Flow Forecasting Methodology flow letter of the present invention based on pro rate principle
Figure.
Fig. 2 is that the Markov theory continuous time Probabilistic Load Flow Forecasting Methodology of the invention based on pro rate principle is specifically real
Existing flow chart of steps.
Embodiment
It is readily appreciated that, according to technical scheme, in the case where not changing the connotation of the present invention, this area
Those skilled in the art can imagine the present invention based on pro rate principle Markov theory continuous time probability tide
Flow the numerous embodiments of Forecasting Methodology.Therefore, detailed description below and accompanying drawing are only to technical scheme
Exemplary illustration, and be not to be construed as the whole of the present invention or be considered as limitation or restriction to technical solution of the present invention.
With reference to Fig. 1 and figure, Markov theory continuous time Probabilistic Load Flow prediction of the present invention based on pro rate principle
Method, comprise the following steps：
Step 1, anticipation is set to carry out the continuous time hop count of Load flow calculation；According to the historical data of regional wind power
State interval is divided to wind power, the transition probability value between each state of wind power is calculated and obtains state transition probability
Matrix, so as to establish the Markov chain model of wind power.
Assuming that the continuous time hop count for setting anticipation progress Load flow calculation according to demand is T, there is K wind-powered electricity generation in this area
, the wind-powered electricity generation prediction power and variable of each wind power plant is X1,X2,…XK, by wind-powered electricity generation in each wind power plant continuous time
Power historical data are divided into m state interval at equal intervals, represent m state respectively, and state interval segment length is ΔkX,
Wind power historical data fluctuation range is [xk min,xk max], then institute's isloation state section is
Dk i=[xk min+(i-1)Δkx,xk min+iΔkX] (i=1,2 ..., m), in formula：
Judge wind power variable Xk(k=1,2 ... K) which state interval is historical data belong to, and finds all belong to
State interval Dk iWind power historical data sample, then find it in these wind power historical data samples
Subsequent time belongs to state interval Dk jNumber of samples, i.e. wind power variable XkDeveloped from state i to state j
Number is Nk ij, obtain the state transfer frequency matrix of wind power variable：
And then the state transition probability matrix of wind power variable is obtained, establish the Markov chain model of wind power variable：
In formula：pk ijIt is state transition probability matrix PkAn element, be referred to as
State transition probability, represent the probability that wind power develops from state i to state j.
Step 2, the wind power Markov chain model established according to step 1 and the pre- power scale of initial time wind-powered electricity generation
The state vector of probability distribution calculates the state vector of the wind-powered electricity generation prediction power probability distribution of subsequent time；Proportion of utilization point
The frequency in sampling of subsequent time wind-powered electricity generation prediction each state interval of power and variable is calculated with principle, and then is taken out using Monte Carlo
Sample method is sampled to wind-powered electricity generation prediction each state interval of power and variable respectively, establishes the sample moment of wind-powered electricity generation prediction power and variable
Battle array.
During initial time, according to wind power variable XkPrediction probability be distributed to obtain wind power variable current time
Probability distribution state vector Xk(0)；If at other moment, wind power variable states that last moment is obtained
Wind power variable states probability vector of the probability vector as current time：
By current time wind power variable states probability vector Xk(0) with wind power variable XkState transfer it is general
Rate matrix is multiplied to obtain the wind power variable states probability vector of subsequent time：
If total frequency in sampling is N, for wind power variable Xk(k=1,2 ... K) calculating of proportion of utilization distribution principle is respectively
The frequency in sampling of state interval：
By state interval Dk iCarry out Numk iDecile, generate Numk iIndividual subinterval, subinterval at intervals ofThen in each subinterval
[xk min+(i-1)Δkx+(j-1)·Δintervalk i,xk min+(i-1)Δkx+j·Δintervalk i] (j=1,2 ... Numk i)
Sample point of the wind power value that sampling Monte Carlo samples to obtain as subinterval.All wind power variables are all pressed
Generated after being sampled according to the above method after initial sample matrix the sampled value of each wind power variable is carried out it is randomly ordered,
Establish the sample matrix X of wind power variableK×N。
Step 3, the wind-powered electricity generation that step 2 is established predict that the sample matrix of power and variable carries out probability tide as input quantity
Stream calculation, the calculation of tidal current at whole moment in the period is fitted using Density Estimator, obtains output variable
Probability distribution curve.
By the sample matrix X of wind power variableK×NInput quantity as certainty power flow algorithm carries out circulation meter
Calculate, select X every time in the circulating cycleK×NA column vector as input quantity, until XK×NAll column vectors be involved in
Calculating is crossed, that is, completes the probabilistic load flow inscribed at one.When the probabilistic load flow at each moment in continuous time
After the completion of all, the calculation of tidal current at whole moment in the period is fitted to obtain output variable using Density Estimator
Probability distribution curve.
Claims (2)
1. the continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle, its feature exist
In step is as follows：
Step 1, anticipation is set to carry out the continuous time hop count of Load flow calculation, according to the historical data of regional wind power
Establish wind power Markov chain model；
Step 2, it is distributed according to the wind power Markov chain model and initial time wind-powered electricity generation prediction power probability
State vector calculates the state vector of the wind-powered electricity generation prediction power probability distribution of subsequent time；Proportion of utilization distribution principle calculates
Subsequent time wind-powered electricity generation predicts the frequency in sampling of each state interval of power and variable；Using Monte Carlo sampling respectively to wind-powered electricity generation
Prediction each state interval of power and variable is sampled to obtain corresponding wind-powered electricity generation prediction performance number；According to the pre- measurement of power of the wind-powered electricity generation
Rate value establishes the sample matrix of wind-powered electricity generation prediction power and variable；
Step 3, the sample matrix that the wind-powered electricity generation predicts power and variable is entered as the input quantity of certainty power flow algorithm
Row probabilistic load flow；Carry out cycle calculations when, every time circulation selection wind-powered electricity generation prediction power and variable sample matrix row to
Amount completes the probabilistic load flow at a moment, the probabilistic load flow until completing each moment in continuous time；Root
It is fitted, is obtained using Density Estimator according to the discrete results of each moment output variable in the continuous time obtained by cycle calculations
The probability distribution curve of output variable.
2. continuous time Probabilistic Load Flow Forecasting Methodology as claimed in claim 1, it is characterised in that in the step 1
The method that wind power Markov chain model is established according to the historical data of regional wind power is：
According to the historical data of regional wind power to wind power divide state interval, calculate each state of wind power between
Transition probability value so as to obtain state transition probability matrix, the horse of wind power is established according to state transition probability matrix
Er Kefu chain models；
The Markov chain model of the wind power such as (1) is shown,
<mrow>
<msup>
<mi>P</mi>
<mi>k</mi>
</msup>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mn>11</mn>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mn>12</mn>
</msub>
</mrow>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mrow>
<mn>1</mn>
<mi>m</mi>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mn>21</mn>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mn>22</mn>
</msub>
</mrow>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mrow>
<mn>2</mn>
<mi>m</mi>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mrow>
<mi>m</mi>
<mn>1</mn>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mrow>
<mi>m</mi>
<mn>2</mn>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mrow>
<msub>
<msup>
<mi>p</mi>
<mi>k</mi>
</msup>
<mrow>
<mi>m</mi>
<mi>m</mi>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula (1)：pk ijState transition probability matrix PkAn element, represent wind power from state i to shape
The probability that state j is developed, andI, j=1,2 ... m；M is to divide power historical data at equal intervals
Into state interval number, Nk ijFor wind power variable XkThe number developed from state i to state j, k ∈ K,
K is the number of wind power plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610384138.5A CN107464007A (en) | 2016-06-02 | 2016-06-02 | Continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610384138.5A CN107464007A (en) | 2016-06-02 | 2016-06-02 | Continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107464007A true CN107464007A (en) | 2017-12-12 |
Family
ID=60544599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610384138.5A Pending CN107464007A (en) | 2016-06-02 | 2016-06-02 | Continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107464007A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108336739A (en) * | 2018-01-15 | 2018-07-27 | 重庆大学 | A kind of Probabilistic Load Flow on-line calculation method based on RBF neural |
| CN108573322A (en) * | 2018-03-13 | 2018-09-25 | 中联达通广（镇江）新能源科技有限公司 | One kind sharing electrical changing station Dynamic Load Forecasting method based on multi-vehicle-type |
| CN112748276A (en) * | 2020-12-28 | 2021-05-04 | 国网冀北电力有限公司秦皇岛供电公司 | Method and device for pre-estimating harmonic emission level |
| CN113076697A (en) * | 2021-04-20 | 2021-07-06 | 潍柴动力股份有限公司 | Typical driving condition construction method, related device and computer storage medium |
| CN113807019A (en) * | 2021-09-24 | 2021-12-17 | 清华大学 | MCMC wind power simulation method based on improved scene classification and coarse grain removal |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140172329A1 (en) * | 2012-12-17 | 2014-06-19 | Junshan Zhang | System and method for wind generation forecasting |
| CN103986156A (en) * | 2014-05-14 | 2014-08-13 | 国家电网公司 | Dynamical probability load flow calculation method with consideration of wind power integration |
| CN103996084A (en) * | 2014-06-06 | 2014-08-20 | 山东大学 | Wind power probabilistic forecasting method based on longitudinal moment Markov chain model |
| CN104463371A (en) * | 2014-12-16 | 2015-03-25 | 山东大学 | Markov chain modeling and predicating method based on wind power variable quantity |
| CN104537448A (en) * | 2015-01-21 | 2015-04-22 | 山东大学 | Method for improving state division of wind power Markov chain model based on longitudinal moments |
| CN104682387A (en) * | 2015-03-10 | 2015-06-03 | 东南大学 | Probability load flow calculation method based on multi-zone interactive iteration |
| CN104810826A (en) * | 2015-05-07 | 2015-07-29 | 东南大学 | Bidirectional iteration parallel probability load flow calculation method combining Latin hypercube sampling |
| CN105610192A (en) * | 2016-01-26 | 2016-05-25 | 山东大学 | On-line risk assessment method considering large-scale wind power integration |
-
2016
- 2016-06-02 CN CN201610384138.5A patent/CN107464007A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140172329A1 (en) * | 2012-12-17 | 2014-06-19 | Junshan Zhang | System and method for wind generation forecasting |
| CN103986156A (en) * | 2014-05-14 | 2014-08-13 | 国家电网公司 | Dynamical probability load flow calculation method with consideration of wind power integration |
| CN103996084A (en) * | 2014-06-06 | 2014-08-20 | 山东大学 | Wind power probabilistic forecasting method based on longitudinal moment Markov chain model |
| CN104463371A (en) * | 2014-12-16 | 2015-03-25 | 山东大学 | Markov chain modeling and predicating method based on wind power variable quantity |
| CN104537448A (en) * | 2015-01-21 | 2015-04-22 | 山东大学 | Method for improving state division of wind power Markov chain model based on longitudinal moments |
| CN104682387A (en) * | 2015-03-10 | 2015-06-03 | 东南大学 | Probability load flow calculation method based on multi-zone interactive iteration |
| CN104810826A (en) * | 2015-05-07 | 2015-07-29 | 东南大学 | Bidirectional iteration parallel probability load flow calculation method combining Latin hypercube sampling |
| CN105610192A (en) * | 2016-01-26 | 2016-05-25 | 山东大学 | On-line risk assessment method considering large-scale wind power integration |
Non-Patent Citations (3)
| Title |
|---|
| JIE YU 等: "Probabilistic load flow calculation with irregular distribution variables considering power grid receivability of wind power generation", 《2016 IEEE 8TH INTERNATIONAL POWER ELECTRONICS AND MOTION CONTROL CONFERENCE》 * |
| 周松林 等: "考虑风力发电随机性的微电网潮流预测", 《中国电机工程学报》 * |
| 茆美琴 等: "基于风光联合概率分布的微电网概率潮流预测", 《电工技术学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108336739A (en) * | 2018-01-15 | 2018-07-27 | 重庆大学 | A kind of Probabilistic Load Flow on-line calculation method based on RBF neural |
| CN108336739B (en) * | 2018-01-15 | 2021-04-27 | 重庆大学 | RBF neural network-based probability load flow online calculation method |
| CN108573322A (en) * | 2018-03-13 | 2018-09-25 | 中联达通广（镇江）新能源科技有限公司 | One kind sharing electrical changing station Dynamic Load Forecasting method based on multi-vehicle-type |
| CN112748276A (en) * | 2020-12-28 | 2021-05-04 | 国网冀北电力有限公司秦皇岛供电公司 | Method and device for pre-estimating harmonic emission level |
| CN113076697A (en) * | 2021-04-20 | 2021-07-06 | 潍柴动力股份有限公司 | Typical driving condition construction method, related device and computer storage medium |
| CN113807019A (en) * | 2021-09-24 | 2021-12-17 | 清华大学 | MCMC wind power simulation method based on improved scene classification and coarse grain removal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107464007A (en) | Continuous time Probabilistic Load Flow Forecasting Methodology based on Markov theory and pro rate principle | |
| CN107591844B (en) | Active power distribution network robust reconstruction method considering node injection power uncertainty | |
| Jung et al. | Prediction of building energy consumption using an improved real coded genetic algorithm based least squares support vector machine approach | |
| CN105631528B (en) | Multi-target dynamic optimal power flow solving method based on NSGA-II and approximate dynamic programming | |
| CN109102155B (en) | Ultra-short-term node marginal electricity price probability prediction method and system | |
| Perninge et al. | Importance sampling of injected powers for electric power system security analysis | |
| CN108365608A (en) | A kind of Regional Energy internet uncertain optimization dispatching method and system | |
| CN109214708A (en) | Study of Risk Evaluation Analysis for Power System method based on cross entropy theoretical optimization support vector machines | |
| CN102768701A (en) | High-voltage switch cabinet insulator electric field optimization method based on quantum genetic algorithm | |
| CN105809349A (en) | Scheduling method considering incoming water correlation cascade hydropower stations | |
| CN102509027A (en) | Wind powder combined predication method based on cross entropy theory | |
| Domínguez et al. | Multi-chronological hierarchical clustering to solve capacity expansion problems with renewable sources | |
| CN104037761A (en) | AGC power multi-objective random optimization distribution method | |
| Tian et al. | A network traffic hybrid prediction model optimized by improved harmony search algorithm | |
| Shirbhate et al. | Time-series energy prediction using hidden Markov model for smart solar system | |
| Luo et al. | Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine | |
| CN104537233B (en) | A kind of power distribution network puppet based on Density Estimator measures generation method | |
| Lange et al. | Probabilistic day-ahead forecast of available thermal storage capacities in residential households | |
| CN107358059A (en) | Short-term photovoltaic energy Forecasting Methodology and device | |
| CN105449667A (en) | Prediction method for reliability of power generation system and power transmission system | |
| CN113363976B (en) | Scene graph-based wind-solar-water complementary power generation system medium-term optimization scheduling method | |
| CN109523077A (en) | A kind of wind power forecasting method | |
| CN102750542A (en) | Support vector regression machine wind speed combination forecast method with interpolation being smoothed and optimized | |
| CN108110756A (en) | Consider the industrial park distribution network planning method of uncertain factor | |
| CN104408531B (en) | A kind of uniform dynamic programming method of multidimensional multistage complicated decision-making problems |
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: 20171212 |
|
| RJ01 | Rejection of invention patent application after publication |