CN109523310A - A kind of electricity market quotation prediction technique based on adaptive-filtering - Google Patents
A kind of electricity market quotation prediction technique based on adaptive-filtering Download PDFInfo
- Publication number
- CN109523310A CN109523310A CN201811272244.XA CN201811272244A CN109523310A CN 109523310 A CN109523310 A CN 109523310A CN 201811272244 A CN201811272244 A CN 201811272244A CN 109523310 A CN109523310 A CN 109523310A
- Authority
- CN
- China
- Prior art keywords
- electricity
- price
- market
- clear
- moment
- 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
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- 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
Abstract
The electricity market quotation prediction technique based on adaptive-filtering that the invention discloses a kind of.It is the following steps are included: S1: establishing electricity market and goes out clear Price Forecasting;S2: choosing 1 month before the electricity market of estimation range clear electricity price data out, calculates the clear electricity price mean value out of each transaction moment k in one day, it is fitted with moment t, fits state-transition matrix;S3: estimating the covariance of observation noise, and the covariance of the observation noise estimated is substituted into electricity market and goes out clear Price Forecasting;S4: the state-transition matrix estimated substitution electricity market is gone out clear Price Forecasting by estimated state transfer matrix;S5: the number of step S3-S4 setting is repeated;S6: output k moment electricity market goes out clear electricity price estimated value;S7: using step S2-S7 estimate electricity market a few days ago each moment go out clear electricity price estimated value.The present invention can predict the clear electricity price out of electricity market according to the historical data of transaction, offer convenient for Power Generation.
Description
Technical field
The present invention relates to Research on electricity price prediction technical field more particularly to a kind of electricity market quotation based on adaptive-filtering are pre-
Survey method.
Background technique
In the Competitive Electricity Market for carrying out electricity commodity, electricity market participant is to guarantee that number one is maximum
Change, certain strategy can be taken to participate in power market transaction.According to the formulating rules of market clearing price, if participating in electric power
The Power Generation of marketing can accurately predict the clear electricity price that goes out of electricity market, and slightly below to go out the valence of clear electricity market
Lattice are offered, it is ensured that all power generation capacity can participate in power market transaction, to guarantee the maximization of number one.
However, currently without the method that can predict electricity market quotation.
Summary of the invention
The electricity market quotation prediction based on adaptive-filtering that in order to solve the above technical problems, The present invention provides a kind of
Method, electricity market can be predicted according to the historical data of transaction goes out clear electricity price.
To solve the above-mentioned problems, the present invention is achieved by the following scheme:
A kind of electricity market quotation prediction technique based on adaptive-filtering of the invention, comprising the following steps:
S1: it establishes electricity market and goes out clear Price Forecasting, formula is as follows:
Meet following constraint condition: E (ωk)=0, E (υk)=0,
Wherein, XkFor Kalman filter state, indicate k moment electricity market goes out clear electricity price;HkFor observing matrix;ωkFor
System noise;υkFor observation noise;YkFor the observation sequence of state, the electricity market for indicating that the k moment observes goes out clear electricity price;Φk
For state-transition matrix;System noise ωkWith observation noise υkIt is white Gaussian noise;QkFor the covariance of system noise;RkFor
The covariance of observation noise;The initial value of k is 1;
S2: 1 month before the electricity market of estimation range clear electricity price data out are chosen, each in one day is calculated and trades
Moment k's goes out clear electricity price mean valueEach transaction moment k is gone out into clear electricity price mean valueIt is carried out with moment t minimum
Two multiply fitting, obtainAmTo go out coefficient matrix of the clear electricity price about moment t, the state transfer fitted is determined
MatrixTake DkAs state-transition matrix ΦkValue substitute into electricity market go out clear Price Forecasting;
S3: estimate the covariance R of observation noisek, by the covariance R of the observation noise estimatedkIt is clear out to substitute into electricity market
Price Forecasting;
S4: estimated state transfer matrix Φk, the state-transition matrix Φ that will estimatekIt is pre- that substitution electricity market goes out clear electricity price
Survey model;
S5: judging whether F is less than E, and E is preset the number of iterations, and F initial value is 0, if F is less than E, F=F+1, is jumped
Step S3 is gone to, it is no to then follow the steps S6;
S6: output k moment electricity market goes out clear electricity price estimated value
S7: judge that k whether less than 24, if k, less than 24, k=k+1, go to step S2, otherwise terminates.
In the present solution, first establishing electricity market according to adaptable Kalman filter goes out clear Price Forecasting, shape in model
State transfer matrix ΦkIt is unknown quantity with observation noise covariance R.This is determined in the historical data according to power market transaction
After two parameters, the clear electricity price that goes out of Day-ahead electricity market could be predicted.
Then, according to 1 month before the electricity market of estimation range clear electricity price historical data out, pass through the fitting to data
To determine systematic state transfer matrix ΦkInitial value.
Then, the covariance R of the observation noise estimated is substituted into electricity market and gone out by the covariance R for estimating observation noise
Clear Price Forecasting, estimated state transfer matrix Φk, the state-transition matrix Φ that will estimatekIt substitutes into electricity market and goes out clear electricity
Valence prediction model, so repeats E times, goes out clear Price Forecasting parameter to the electricity market determined and is modified, and comes
Guarantee that model parameter is the prediction model that most true electricity market goes out clear electricity price.
Finally, predicting 1 point of market clearing price of Day-ahead electricity market, recycles 24 times, find out Day-ahead electricity market
The market clearing price at each moment.
Preferably, in the step S2, by the clear electricity price mean value out of each transaction moment k in one dayIt imports
Least square fitting is carried out in MATLAB, is obtained
Preferably, being calculated in the step S2Method the following steps are included:
It is calculated using following formula
Wherein,It indicates to go out clear electricity price mean value, x in k moment electricity marketId, kIt is the k moment market clearing in one day
Electricity price, qId, kClear capacity is carved when being corresponding, N indicates the number of days in a middle of the month, qId, gIt indicates in this middle of the month power market transaction
Clear total capacity out.
Preferably, the step S3 the following steps are included:
S301: according to Weierstrass theorem, the Closed Interval Continuous Function of any bounded can be by more in the section
For item formula with arbitrary accuracy Uniform approximat, k moment electricity market goes out the observation signal Y of clear electricity pricekIt can indicate are as follows:
Yk=a0+a1k+…+aMkM,
Wherein, a0, a1... aMIt is multinomial coefficient;
S302: selectedFor wavelet function:
Wherein, s is the scale that observation market clearing price signal is chosen in wavelet transformation, and τ indicates time-shifting;
S303: the wavelet transformation of market clearing price is the convolution of the wavelet function according to observation signal and selection come table
Show, therefore the market clearing price signal y with observation noisem(k) wavelet transformation are as follows:
Wherein, WY(S, τ) indicates the details approximate part of the wavelet transformation of observation signal, Wω(s, τ) indicates observation signal
Wavelet transformation detail section,
High-frequency wavelet transform inhibits observation signal only to remain noise component(s) Wω(s, τ), thus since can separate
The noise component(s) of observation signal out,
304: the standard deviation δ of observation noisekIt can be exhausted by the observation noise component detail section retained after wavelet transformation
The mediant estimation of value is come out:
Wherein, thIt is τ in the discrete representation of observation noise component details scale, Med expression market clearing price, which is observed, makes an uproar
The median of acoustical signal sequence;
S305: according to the standard deviation δ of the observation noise estimatedkDetermine the covariance R of observation noisek,
By the covariance R of the observation noise estimatedkIt substitutes into electricity market and goes out clear Price Forecasting.
In the prediction that electricity market goes out clear electricity price, the statistical property of observation noise is unknown.To estimate observation noise
Covariance, select the method for wavelet transformation to handle.Wavelet transformation can separate signal and noise, and wavelet transformation is sought observing
Noise covariance mainly passes through the lower order polynomial expressions that high-frequency wavelet transform inhibits signal, only remains higher order polynomial, i.e.,
The wavelet function of observation noise passes through the standard deviation of observation noise in wavelet transformation estimating system.In electricity market, observation letter
Number refer to the true value for the historical trading data that Power Generation obtains during power market transaction.Choose the main of wavelet transformation
Purpose is to isolate noise component(s).
Preferably, the step S4 the following steps are included:
S401: state-transition matrix Φ is estimated using following formulak:
Pk=(In-KkHk)Pk|k-1(5),
It is derived according to formula (1)-(6):
Initial value
Wherein,Go out the one-step prediction of clear electricity price, K for k moment electricity marketkFor gain matrix, Pk|k-1For a step
Predict variance matrix, PkFor estimation error variance matrix,Jk, MkSystem is minimum when being to guarantee to do state-transition matrix
The intermediate variable that square error linear unbiased esti-mator introduces;
S402: the state-transition matrix Φ that will be estimatedkIt substitutes into electricity market and goes out clear Price Forecasting.
The beneficial effects of the present invention are: the clear electricity price out of electricity market can be predicted according to the historical data of transaction, it is convenient for
Power Generation is offered when being offered with being slightly below the market clearing price predicted, it is ensured that unit capacity all participates in
Marketing reaches profit maximization.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Specific embodiment
Below with reference to the embodiments and with reference to the accompanying drawing the technical solutions of the present invention will be further described.
Embodiment: a kind of electricity market quotation prediction technique based on adaptive-filtering of the present embodiment, as shown in Figure 1,
The following steps are included:
S1: it establishes electricity market and goes out clear Price Forecasting, formula is as follows:
Meet following constraint condition: E (ωk)=0, E (υk)=0,
Wherein, XkFor Kalman filter state, indicate k moment electricity market goes out clear electricity price;HkFor observing matrix;ωkFor
System noise;υkFor observation noise;YkFor the observation sequence of state, the electricity market for indicating that the k moment observes goes out clear electricity price;Φk
For state-transition matrix;System noise ωkWith observation noise υkIt is white Gaussian noise, meets the condition that mean value is 0;QkTo be
It unites the covariance of noise, chooses Q in modelkValue be random value;RkFor the covariance of observation noise, according to the electric power observed
Marketing real-time deal goes out clear electricity price to carry out ART network;The initial value of k is 1;
S2: 1 month before the electricity market of estimation range clear electricity price data out are chosen, each in one day is calculated and trades
Moment k's goes out clear electricity price mean valueEach transaction moment k is gone out into clear electricity price mean valueIt is carried out with moment t minimum
Two multiply fitting, obtainAmTo go out coefficient matrix of the clear electricity price about moment t, the state transfer fitted is determined
MatrixTake DkAs state-transition matrix ΦkValue substitute into electricity market go out clear Price Forecasting;
S3: estimate the covariance R of observation noisek, by the covariance R of the observation noise estimatedkIt is clear out to substitute into electricity market
Price Forecasting;
S4: estimated state transfer matrix Φk, the state-transition matrix Φ that will estimatekIt is pre- that substitution electricity market goes out clear electricity price
Survey model;
S5: judging whether F is less than E, and E is preset the number of iterations, and F initial value is 0, if F is less than E, F=F+1, is jumped
Step S3 is gone to, it is no to then follow the steps S6;
S6: output k moment electricity market goes out clear electricity price estimated value
S7: judge that k whether less than 24, if k, less than 24, k=k+1, go to step S2, otherwise terminates.
In the present solution, first establishing electricity market according to adaptable Kalman filter goes out clear Price Forecasting, shape in model
State transfer matrix ΦkIt is unknown quantity with observation noise covariance R.This is determined in the historical data according to power market transaction
After two parameters, the clear electricity price that goes out of Day-ahead electricity market could be predicted.
Then, according to 1 month before the electricity market of estimation range clear electricity price historical data out, pass through the fitting to data
To determine systematic state transfer matrix ΦkInitial value.
Then, the covariance R of the observation noise estimated is substituted into electricity market and gone out by the covariance R for estimating observation noise
Clear Price Forecasting, estimated state transfer matrix Φk, the state-transition matrix Φ that will estimatekIt substitutes into electricity market and goes out clear electricity
Valence prediction model, so repeats E times, goes out clear Price Forecasting parameter to the electricity market determined and is modified, and comes
Guarantee that model parameter is the prediction model that most true electricity market goes out clear electricity price.
Finally, predicting 1 point of market clearing price of Day-ahead electricity market, recycles 24 times, find out Day-ahead electricity market
The market clearing price at each moment.
In step S2, by the clear electricity price mean value out of each transaction moment k in one dayIt imports in MATLAB and carries out most
Small two multiply fitting, obtain
It is calculated in step S2Method the following steps are included:
It is calculated using following formula
Wherein,It indicates to go out clear electricity price mean value, x in k moment electricity marketId, kIt is the k moment market clearing in one day
Electricity price, qId, kClear capacity is carved when being corresponding, N indicates the number of days in a middle of the month, qId, gIt indicates in this middle of the month power market transaction
Clear total capacity out.
Step S3 the following steps are included:
S301: according to Weierstrass theorem, the Closed Interval Continuous Function of any bounded can be by more in the section
For item formula with arbitrary accuracy Uniform approximat, k moment electricity market goes out the observation signal Y of clear electricity pricekIt can indicate are as follows:
Yk=a0+a1k+…+aMkM,
Wherein, a0, a1... aMIt is multinomial coefficient;
S302: selectedFor wavelet function:
Wherein, s is the scale that observation market clearing price signal is chosen in wavelet transformation, and τ indicates time-shifting;
S303: the wavelet transformation of market clearing price is the convolution of the wavelet function according to observation signal and selection come table
Show, therefore the market clearing price signal y with observation noisem(k) wavelet transformation are as follows:
Wherein, WY(s, τ) indicates the details approximate part of the wavelet transformation of observation signal, Wω(s, τ) indicates observation signal
Wavelet transformation detail section,
High-frequency wavelet transform inhibits observation signal only to remain noise component(s) Wω(s, τ), thus since can separate
The noise component(s) of observation signal out,
304: setting observation signal YkIt is a piecewise polynomial in the L of section, in high-frequency wavelet transform, observation signal
Signal section is suppressed, and only remains the detail section of wavelet transformation, therefore the standard deviation δ of observation noisekSmall echo can be passed through
The mediant estimation of the observation noise component detail section absolute value retained after transformation comes out:
Wherein, thIt is τ in the discrete representation of observation noise component details scale, Med expression market clearing price, which is observed, makes an uproar
The median of acoustical signal sequence, setting scale s are 0.5;
S305: according to the standard deviation δ of the observation noise estimatedkDetermine the covariance R of observation noisek,
By the covariance R of the observation noise estimatedkIt substitutes into electricity market and goes out clear Price Forecasting.
In the prediction that electricity market goes out clear electricity price, the statistical property of observation noise is unknown.To estimate observation noise
Covariance, select the method for wavelet transformation to handle.Wavelet transformation can separate signal and noise, and wavelet transformation is sought observing
Noise covariance mainly passes through the lower order polynomial expressions that high-frequency wavelet transform inhibits signal, only remains higher order polynomial, i.e.,
The wavelet function of observation noise passes through the standard deviation of observation noise in wavelet transformation estimating system.In electricity market, observation letter
Number refer to the true value for the historical trading data that Power Generation obtains during power market transaction.Choose the main of wavelet transformation
Purpose is to isolate noise component(s).
Step S4 the following steps are included:
S401: state-transition matrix Φ is estimated using following formulak:
Pk=(In-KkHk)Pk|k-1(5),
It is derived according to formula (1)-(6):
Initial value
Wherein,Go out the one-step prediction of clear electricity price, K for k moment electricity marketkIt is according to observation for gain matrix
To the clear electricity price signal that goes out predict clear electricity price, Pk|k-1For one-step prediction variance matrix, PkFor estimation error variance matrix,Jk, MkSystem is the intermediate variable that Minimum variance linear unbiased estimate introduces when being to guarantee to do state-transition matrix;
S402: the state-transition matrix Φ that will be estimatedkIt substitutes into electricity market and goes out clear Price Forecasting.
Claims (5)
- The prediction technique 1. a kind of electricity market based on adaptive-filtering is offered, which comprises the following steps:S1: it establishes electricity market and goes out clear Price Forecasting, formula is as follows:Meet following constraint condition:Wherein, XkFor Kalman filter state, indicate k moment electricity market goes out clear electricity price;HkFor observing matrix;ωkFor system noise;υkFor observation noise;YkFor the observation sequence of state, indicate that the k moment observes Electricity market go out clear electricity price;ΦkFor state-transition matrix;System noise ωkWith observation noise υkIt is white Gaussian noise;Qk For the covariance of system noise;RkFor the covariance of observation noise;The initial value of k is 1;S2: choosing 1 month before the electricity market of estimation range clear electricity price data out, calculates each transaction moment in one day K's goes out clear electricity price mean valueEach transaction moment k is gone out into clear electricity price mean valueLeast square is carried out with moment t Fitting, obtainsAmTo go out coefficient matrix of the clear electricity price about moment t, the state-transition matrix fitted is determinedTake DkAs state-transition matrix ΦkValue substitute into electricity market go out clear Price Forecasting;S3: estimate the covariance R of observation noisek, by the covariance R of the observation noise estimatedkIt substitutes into electricity market and goes out clear electricity price Prediction model;S4: estimated state transfer matrix Φk, the state-transition matrix Φ that will estimatekIt substitutes into electricity market and goes out clear Research on electricity price prediction mould Type;S5: judging whether F is less than E, and E is preset the number of iterations, and F initial value is 0, if F is less than E, F=F+1, jumps to Step S3, it is no to then follow the steps S6;S6: output k moment electricity market goes out clear electricity price estimated valueS7: judge that k whether less than 24, if k, less than 24, k=k+1, go to step S2, otherwise terminates.
- The prediction technique 2. a kind of electricity market based on adaptive-filtering according to claim 1 is offered, which is characterized in that In the step S2, by the clear electricity price mean value out of each transaction moment k in one dayIt imports and carries out minimum two in MATLAB Multiply fitting, obtains
- The prediction technique 3. a kind of electricity market based on adaptive-filtering according to claim 1 is offered, which is characterized in that It is calculated in the step S2Method the following steps are included:It is calculated using following formulaWherein,It indicates to go out clear electricity price mean value, x in k moment electricity marketId, kIt is the k moment market clearing price in one day, qId, kClear capacity is carved when being corresponding, N indicates the number of days in a middle of the month, qId, gIt indicates clear out in this middle of the month power market transaction Total capacity.
- The prediction technique 4. a kind of electricity market based on adaptive-filtering according to claim 1 or 2 or 3 is offered, it is special Sign is, the step S3 the following steps are included:S301: according to Weierstrass theorem, the Closed Interval Continuous Function of any bounded can be by the multinomial in the section With arbitrary accuracy Uniform approximat, k moment electricity market goes out the observation signal Y of clear electricity pricekIt can indicate are as follows:Yk=a0+a1k+…+aMkM,Wherein, a0, a1... aMIt is multinomial coefficient;S302: selectedFor wavelet function:Wherein, s is the scale that observation market clearing price signal is chosen in wavelet transformation, and τ indicates time-shifting;S303: the wavelet transformation of market clearing price is the convolution of the wavelet function according to observation signal and selection to indicate, because This market clearing price signal y with observation noisem(k) wavelet transformation are as follows:Wherein, WY(s, τ) indicates the details approximate part of the wavelet transformation of observation signal, WωThe small echo of (s, τ) expression observation signal The detail section of transformation,High-frequency wavelet transform inhibits observation signal only to remain noise component(s) Wω(s, τ), thus since can isolate sight The noise component(s) of signal is surveyed,S304: the standard deviation δ of observation noisekIt can be by the observation noise component detail section absolute value that retains after wavelet transformation Mediant estimation come out:Wherein, thDiscrete representation for τ in observation noise component details scale, Med expression market clearing price observation noise signal The median of sequence;S305: according to the standard deviation δ of the observation noise estimatedkDetermine the covariance R of observation noisek,It will estimate The covariance R for the observation noise counted outkIt substitutes into electricity market and goes out clear Price Forecasting.
- The prediction technique 5. a kind of electricity market based on adaptive-filtering according to claim 1 or 2 or 3 is offered, it is special Sign is, the step S4 the following steps are included:S401: state-transition matrix Φ is estimated using following formulak:Pk=(In-KkHk)Pk|k-1(5),It is derived according to formula (1)-(6):Initial valueWherein,Go out the one-step prediction of clear electricity price, K for k moment electricity marketkFor gain matrix, Pk|k-1For one-step prediction Variance matrix, PkFor estimation error variance matrix,Jk, MkSystem is minimum variance when being to guarantee to do state-transition matrix The intermediate variable that linear unbiased estimate introduces;S402: the state-transition matrix Φ that will be estimatedkIt substitutes into electricity market and goes out clear Price Forecasting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811272244.XA CN109523310A (en) | 2018-10-29 | 2018-10-29 | A kind of electricity market quotation prediction technique based on adaptive-filtering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811272244.XA CN109523310A (en) | 2018-10-29 | 2018-10-29 | A kind of electricity market quotation prediction technique based on adaptive-filtering |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109523310A true CN109523310A (en) | 2019-03-26 |
Family
ID=65773081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811272244.XA Pending CN109523310A (en) | 2018-10-29 | 2018-10-29 | A kind of electricity market quotation prediction technique based on adaptive-filtering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109523310A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110148006A (en) * | 2019-05-20 | 2019-08-20 | 国网天津市电力公司 | A kind of electricity market malice is bidded Activity recognition method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140330695A1 (en) * | 2013-05-06 | 2014-11-06 | Viridity Energy, Inc. | Facilitating revenue generation from wholesale electricity markets based on a self-tuning energy asset model |
CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
CN107766976A (en) * | 2017-10-17 | 2018-03-06 | 国网江苏省电力公司盐城供电公司 | A kind of active demand response platform of electric power market |
-
2018
- 2018-10-29 CN CN201811272244.XA patent/CN109523310A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140330695A1 (en) * | 2013-05-06 | 2014-11-06 | Viridity Energy, Inc. | Facilitating revenue generation from wholesale electricity markets based on a self-tuning energy asset model |
CN106815677A (en) * | 2016-12-09 | 2017-06-09 | 国网北京市电力公司 | The recognition methods of non-intrusion type load and device |
CN107766976A (en) * | 2017-10-17 | 2018-03-06 | 国网江苏省电力公司盐城供电公司 | A kind of active demand response platform of electric power market |
Non-Patent Citations (2)
Title |
---|
LIANG DING、QUANBO GE: "Electricity Market Clearing Price Forecast Based on Adaptive Kalman Filter", 《2018 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND INFORMATION SCIENCES (ICCAIS)》 * |
张小丽: "利用小波变换进行高噪背景下的信号提取", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110148006A (en) * | 2019-05-20 | 2019-08-20 | 国网天津市电力公司 | A kind of electricity market malice is bidded Activity recognition method |
CN110148006B (en) * | 2019-05-20 | 2023-05-12 | 国网天津市电力公司 | Malicious bidding behavior identification method for electric power market |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cai et al. | Option pricing under a mixed-exponential jump diffusion model | |
Omane-Adjepong et al. | Determining the better approach for short-term forecasting of ghana’s inflation: Seasonal ARIMA Vs holt-winters | |
CN109873712A (en) | A kind of network flow prediction method and device | |
Bayraktar et al. | Inventory management with partially observed nonstationary demand | |
CN104217091B (en) | A kind of website visiting amount Forecasting Methodology based on history tendency weight | |
JP2010263754A (en) | Method and device for estimating state of power distribution system | |
Huang et al. | A generalized birth–death stochastic model for high-frequency order book dynamics | |
CN113281790A (en) | Beidou satellite clock error forecasting method and device | |
Hansun et al. | Brown’s Weighted Exponential Moving Average Implementation in Forex Forecasting | |
CN109523310A (en) | A kind of electricity market quotation prediction technique based on adaptive-filtering | |
Haq et al. | An improved maximum exponentially weighted moving average control chart for monitoring process mean and variability | |
CN109816165B (en) | Wind power ultra-short term power prediction method and system | |
Ammann et al. | Robust estimation of risk‐neutral moments | |
CN104809647A (en) | Volatility index compiling method | |
CN116760006A (en) | Wind power prediction method, device, equipment and storage medium | |
Shukur et al. | Electricity load forecasting using hybrid of multiplicative double seasonal exponential smoothing model with artificial neural network | |
An et al. | Short‐Term Stock Price Prediction Based on Limit Order Book Dynamics | |
CN104407256B (en) | A kind of Electrical Power System Dynamic state updating method for handling measuring section time delay | |
Gokpinar et al. | Generalization of inclusion probabilities in ranked set sampling | |
Chao et al. | Bidding model incorporating bid position for determining overhead-cum-markup rate | |
Nursimulu et al. | Excessive volatility is also a feature of individual level forecasts | |
Xie et al. | Measuring Bullwhip Effect in a Single Echelon SupplyChain Using Fuzzy Approach | |
Awwad et al. | A risk-sensitive markup decision model | |
Reddy et al. | Parameters for estimation of entropy to study price manipulation in stock market | |
CN111582937B (en) | Calculation method and device for node electricity price deviation accuracy and storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190326 |