CN106971238A - The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S - Google Patents
The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S Download PDFInfo
- Publication number
- CN106971238A CN106971238A CN201710141487.9A CN201710141487A CN106971238A CN 106971238 A CN106971238 A CN 106971238A CN 201710141487 A CN201710141487 A CN 201710141487A CN 106971238 A CN106971238 A CN 106971238A
- Authority
- CN
- China
- Prior art keywords
- data
- load
- short
- prediction
- neutral nets
- 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
- 230000007935 neutral effect Effects 0.000 title claims abstract description 32
- 238000013277 forecasting method Methods 0.000 title claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims abstract description 11
- 230000004913 activation Effects 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 12
- 210000002569 neuron Anatomy 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 6
- 238000011002 quantification Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 240000002853 Nelumbo nucifera Species 0.000 claims 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims 1
- 230000006870 function Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 230000000869 mutational effect Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000003068 static effect Effects 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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of Short-Term Load Forecasting Method that Elman neutral nets are obscured based on T S, comprise the following steps：The power system historical load data in somewhere is obtained, the abnormal data of historical load data is handled；Influence electric load factor is analyzed and quantified, revised data are normalized；Determine the inputoutput data of neutral net, delay unit is introduced in rules layer, the information that the intensity of activation that the output of rules layer is last moment strictly all rules is inputted as current time, Elman neutral nets are obscured based on T S so as to set up, Elman neutral nets are obscured with the T S trained to be predicted, and by the data renormalization of prediction so as to obtain final prediction load value.The characteristics of present invention can be very good fitting the non-linear of electric load system, dynamic and time variation, precision of prediction is higher, can be widely applied in power-system short-term load forecasting.
Description
Technical field
The present invention relates to a kind of Short-Term Load Forecasting Method that Elman neutral nets are obscured based on T-S, belong to electric power
System loading predicts field.
Background technology
Load Prediction In Power Systems can be divided into Mid-long term load forecasting, short-term load forecasting according to predetermined period classification and surpass
Short-term load forecasting.Wherein, short-term load forecasting refers to for the load of day part is pre- daily in following one day to week age
The research of survey.Short-term load forecasting is vital, its direct shadow of precision predicted in Load Prediction In Power Systems research
Ring to the operation of power system security economic stability, realize power network scientific management and scheduling.At present, artificial neuron is mainly used
The back propagation (BP algorithm) of network algorithm, it has obtained wide application in Load Prediction In Power Systems research direction.By
It is in dynamic characteristic in the influence of the easy climate of power system load, economic dispatch factor, and BP neural network is to ask dynamic modeling
Topic is converted to static modelling problem, can thus make to exist during the network operation and is absorbed in local minimum, one way propagation and does not feed back
Problem.
The content of the invention
The technical problem to be solved in the present invention is：Preferably it is fitted the non-linear of electric load system, dynamic and time-varying
The characteristics of property.
In order to solve the above-mentioned technical problem, the technical scheme is that there is provided a kind of based on the fuzzy Elman nerves of T-S
The Short-Term Load Forecasting Method of network, it is characterised in that comprise the following steps：
Step 1, the power system historical load data for obtaining somewhere, at the abnormal data of historical load data
Reason；
Step 2, influence electric load factor is analyzed and quantified, revised load data is normalized；
Step 3, the inputoutput data for determining neutral net, wherein, by the weather characteristics on the day of predicting day, temperature, day
Phase type and t-1 hours load values and n-1, n-2 of prediction time t, t-1 and t+1 hours day load values are used as input number
According to the t hours integral point load values of prediction day are output data, and determine the number of optimal hidden layer neuron, in rule
Then layer introduces delay unit, and the intensity of activation that the output of rules layer is last moment strictly all rules was inputted as current time
Information, Elman neutral nets are obscured so as to set up based on T-S；
Step 4, using prediction, bimestrial historical load data, weather parameter data and date type data are carried out a few days ago
Training, obscures Elman neutral nets with the T-S trained and is predicted, and by the data renormalization of prediction so as to obtain most
Whole prediction load value；
Preferably, the electric power historical load data in somewhere is obtained in the step 1, its data sample comes from SCADA
System.
Preferably, the processing mode of the dealing of abnormal data in the step 1 includes horizontal processing, vertical processing or curve
Fitting.
Preferably, the influence load factor in the step 2 includes temperature, weather characteristics and date type, according to these
Factor is carried out quantification treatment to the influence degree of load.
Preferably, load data is normalized in the step 2, be normalized to load data using normalization formula [0,
1], same number of levels is at, accelerates neutral net convergence.
Preferably, in the number that optimal hidden layer neuron is determined in the step 3, the hidden layer of the network is single hidden
Containing layer, rule of thumb formula and the effect of training are determined the number of its neuron.
Preferably, the data renormalization of prediction is obtained into final prediction load value always in the step 4, its anti-normalizing
Change the formula that renormalization is can obtain according to the deformation of normalization formula, final data are exactly the load number of actual number magnitude
According to.
Elman neutral nets are a kind of typical dynamic neuron networks, with the ability for adapting to time-varying characteristics, while T-
S fuzzy controls make the output of system to be expressed as the linear combination of input variable, therefore the system can be very good fitting electricity
The characteristics of the non-linear of power load system, dynamic and time variation.
As a result of above-mentioned technical scheme, the present invention compared with prior art, has the following advantages that and actively imitated
Really：T-S fuzzy controls are combined by the present invention with Elman neutral nets to be applied in short-term electric load prediction, and the model is simultaneous
Have Elman neutral nets and the advantage of fuzzy control, not only with very strong kinematic nonlinearity capability of fitting, and preferably mould
Intend the dynamic process of error feedback modifiers, can preferably be fitted the non-linear of electric load system, dynamic and time variation
The characteristics of, precision of prediction is higher, can be widely applied in power-system short-term load forecasting.
Brief description of the drawings
Fig. 1 is the flow chart of the present invention；
Fig. 2 is that T-S of the present invention obscures Elman neural network structure figures.
Embodiment
With reference to specific embodiment, the present invention is expanded on further.It should be understood that these embodiments are merely to illustrate the present invention
Rather than limitation the scope of the present invention.In addition, it is to be understood that after the content of the invention lectured has been read, people in the art
Member can make various changes or modifications to the present invention, and these equivalent form of values equally fall within the application appended claims and limited
Scope.
Embodiments of the present invention are related to a kind of short-term electric load prediction side that Elman neutral nets are obscured based on T-S
Method, as shown in figure 1, comprising the following steps：
(1) the power system historical load data in somewhere is obtained, the abnormal data of historical load data is handled；
Wherein, historical load data sample mostlys come from SCADA system；Abnormal data be due to some other factor interference this be
System can have incomplete data, and there is wrong data.
(2) influence electric load factor is analyzed and quantified, revised data are normalized；Wherein, shadow
Ringing electric load factor includes temperature, weather characteristics and date type etc., according to these factors to the influence degree of load by its
Carry out quantification treatment；Normalization is that load data is normalized into [0,1] using normalization formula, is at the same order of magnitude
Not, neutral net convergence is accelerated.
(3) inputoutput data of neutral net is determined, and determines the number of optimal hidden layer neuron, in rule
Layer introduces delay unit, the letter that the intensity of activation that the output of rules layer is last moment strictly all rules is inputted as current time
Breath, Elman neutral nets are obscured so as to set up based on T-S；Wherein, inputoutput data is that the weather on the day of predicting day is special
Levy, temperature, date type and t-1 hours load values and n-1, n-2 of prediction time t, t-1 and t+1 hours day load values
As input data, the t hours integral point load values of prediction day are output data；The number of hidden layer neuron, rule of thumb
Formula and the effect of training are determined；Delay unit, is that the activation of the i.e. last moment strictly all rules of output of rules layer is strong
The information inputted as current time is spent, mnemon is also considered as.
(4) using prediction, bimestrial historical load data, weather parameter data and date type data are instructed a few days ago
Practice, obscuring Elman neutral nets with the T-S trained is predicted, and the data renormalization of prediction is final so as to obtain
Prediction load value；Wherein, renormalization is will to normalize the renormalization formula that formula deformation is obtained, so as to obtain actual number
The load data of magnitude.
Below the present invention is further illustrated so that the historical load data of certain coastal area prefecture-level city is research object as an example.
It is comprised the following steps that：
Obtain the processing of historical load data and data
In power system at this stage, power system load data mostly come from SCADA system, for various reasons,
The data of SCADA system are simultaneously imperfect, and there are some wrong data.For these abnormal datas, it is necessary to using certain side
Method is detected and corrected to data.
The vertical processing of data：Power system load has certain periodicity, has in similar day synchronization load
Certain similitude, its excursion is maintained in certain scope.If super go beyond the scope, it can determine that as abnormal data.
By the vertical processing to load, part abnormal data can detect that.By the smoothing processing to mutational load, total can be made
It is smaller according to fluctuating.
The horizontal processing of data：In power system load data, similar moment load is not in the feelings being significantly mutated
Condition, therefore can be worth according on the basis of front and rear two moment load data, set the worst error scope of data.If load value is with before
If the absolute value of the difference of the load data at latter two moment is above threshold value, then can determine that the load value is bad data.
Influence load factor is quantified and by revised data normalization
In electricity market, the impacted factor of power system load is more, and it is not only vaporous by electric load demand, day
The factors such as condition, seasonality, region, while also being influenceed by factors such as national economy, politics, residents'living habits.To the littoral
Area's major influence factors are temperature, weather characteristics and date type.When temperature change within the specific limits, on load variations influence
Substantially it is similar, so assigning the quantized value between one [0,1] in different temperatures.For weather characteristics, this area makes a clear distinction between the four seasons,
Therefore according to historical load data and seasonal characteristic, from it is fine to the moon to heavy rain assign one [0,1] between from big to small
Quantized value.To date type, mainly according to working day and day off to its quantification treatment.
Build the model that T-S obscures Elman neutral nets
T-S obscures Elman neutral nets and includes five layers, is input layer respectively, membership function layer, rules layer, parameter layer, defeated
Go out layer, common n input node, 1 output node, its topological structure is as shown in Figure 2.
Bear within weather characteristics, temperature, date type and t-1 hours on the day of input layer is the data of input, including prediction day
N-1, n-2 t, t-1 and t+1 hours day load value of charge values and prediction time；Membership function layer, each node generation of this layer
One membership function of table, the connection weight with input layer is 1, using Gaussian function as membership function, calculates each node
Corresponding degree of membership；Rules layer introduces delay unit, is the intensity of activation of last moment strictly all rules by the output of rules layer
The information inputted as current time；Parameter layer, this layer belongs to the consequent part of T-S fuzzy neural networks；Output layer, realizes T-
The de-fuzzy function of S fuzzy systems, obtains the output of a linear combination.
The realization of short-term load forecasting
Using the data in this area's in May, 2012 and June as raw sample data, by abnormal data processing and return
After one changes, one group of data for being normally available for neural network learning is obtained, by the T-S fuzzy neural networks having had been built up,
Finally give prediction day the load value of 24 hours one day, through examine contrast, its mean absolute error can control 2% with
Interior, MSE can be controlled within 0.6%.Therefore, the model can be very good to predict short-term electric load data.
Claims (7)
1. a kind of Short-Term Load Forecasting Method that Elman neutral nets are obscured based on T-S, it is characterised in that including following
Step：
Step 1, the power system historical load data for obtaining somewhere, are handled the abnormal data of historical load data；
Step 2, influence electric load factor is analyzed and quantified, revised load data is normalized；
Step 3, the inputoutput data for determining neutral net, wherein, by the weather characteristics on the day of predicting day, temperature, date class
Type and t-1 hours load values and n-1, n-2 of prediction time t, t-1 and t+1 hours day load values are as input data, in advance
T hours integral point load values for surveying day are output data, and determine the number of optimal hidden layer neuron, are drawn in rules layer
Enter delay unit, the information that the intensity of activation that the output of rules layer is last moment strictly all rules is inputted as current time,
Elman neutral nets are obscured based on T-S so as to set up；
Step 4, using prediction bimestrial historical load data, weather parameter data and date type data are instructed a few days ago
Practice, obscuring Elman neutral nets with the T-S trained is predicted, and the data renormalization of prediction is final so as to obtain
Prediction load value.
2. the Short-Term Load Forecasting Method according to claim 1 that Elman neutral nets are obscured based on T-S, it is special
Levy and be, the electric power historical load data in somewhere is obtained in the step 1, its data sample comes from SCADA system.
3. the Short-Term Load Forecasting Method according to claim 1 that Elman neutral nets are obscured based on T-S, it is special
Levy and be, the processing mode of the dealing of abnormal data in the step 1 includes horizontal processing, vertical processing or curve matching.
4. the Short-Term Load Forecasting Method according to claim 1 that Elman neutral nets are obscured based on T-S, it is special
Levy and be, the influence load factor in the step 2 includes temperature, weather characteristics and date type, according to these factors to negative
The influence degree of lotus is carried out quantification treatment.
5. the Short-Term Load Forecasting Method according to claim 1 that Elman neutral nets are obscured based on T-S, it is special
Levy and be, load data is normalized in the step 2, load data is normalized to [0,1] using normalization formula, made at it
In same number of levels, accelerate neutral net convergence.
6. the Short-Term Load Forecasting Method according to claim 1 that Elman neutral nets are obscured based on T-S, it is special
Levy and be, in the number that optimal hidden layer neuron is determined in the step 3, the hidden layer of the network is single hidden layer, its
Rule of thumb formula and the effect of training are determined the number of neuron.
7. the Short-Term Load Forecasting Method according to claim 1 that Elman neutral nets are obscured based on T-S, it is special
Levy and be, it is total that the data renormalization of prediction obtained into final prediction load value in the step 4, its renormalization is according to returning
The deformation of one change formula can obtain the formula of renormalization, and final data are exactly the load data of actual number magnitude.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710141487.9A CN106971238A (en) | 2017-03-10 | 2017-03-10 | The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710141487.9A CN106971238A (en) | 2017-03-10 | 2017-03-10 | The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106971238A true CN106971238A (en) | 2017-07-21 |
Family
ID=59330131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710141487.9A Pending CN106971238A (en) | 2017-03-10 | 2017-03-10 | The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971238A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590562A (en) * | 2017-09-05 | 2018-01-16 | 西安交通大学 | A kind of Short-Term Load Forecasting of Electric Power System based on changeable weight combination predicted method |
| CN107704967A (en) * | 2017-10-17 | 2018-02-16 | 吉林省电力科学研究院有限公司 | A kind of Short-Term Load Forecasting Method based on improvement fuzzy neural network |
| CN109240088A (en) * | 2018-10-24 | 2019-01-18 | 闽江学院 | A kind of estimation of electric power networks communication delay and compensation finite-time control method |
| CN109617097A (en) * | 2018-12-26 | 2019-04-12 | 贵州电网有限责任公司 | Three-phase load unbalance self-decision administering method based on fuzzy neural network algorithm |
| CN110009132A (en) * | 2019-03-04 | 2019-07-12 | 三峡大学 | A kind of short-term electric load fining prediction technique based on LSTM deep neural network |
| CN110046765A (en) * | 2019-04-15 | 2019-07-23 | 国网甘肃省电力公司电力科学研究院 | A kind of power system stabilizer, PSS implementation method based on Elman neural network |
| CN111080037A (en) * | 2020-01-02 | 2020-04-28 | 中国电力科学研究院有限公司 | Short-term power load prediction method and device based on deep neural network |
| CN111142027A (en) * | 2019-12-31 | 2020-05-12 | 国电南瑞南京控制系统有限公司 | Lithium iron phosphate battery state-of-charge monitoring and early warning method based on neural network |
| CN111952962A (en) * | 2020-07-30 | 2020-11-17 | 国网江苏省电力有限公司南京供电分公司 | Power distribution network low voltage prediction method based on T-S fuzzy neural network |
| CN112668776A (en) * | 2020-12-25 | 2021-04-16 | 国网黑龙江省电力有限公司电力科学研究院 | Long-short term memory network model power load prediction method suitable for alpine region |
| CN112862194A (en) * | 2021-02-08 | 2021-05-28 | 杭州市电力设计院有限公司余杭分公司 | Power distribution network power supply planning method, device, equipment and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105678404A (en) * | 2015-12-30 | 2016-06-15 | 东北大学 | Micro-grid load prediction system and method based on electricity purchased on-line and dynamic correlation factor |
| CN106022549A (en) * | 2016-07-28 | 2016-10-12 | 兰州理工大学 | Short term load predication method based on neural network and thinking evolutionary search |
-
2017
- 2017-03-10 CN CN201710141487.9A patent/CN106971238A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105678404A (en) * | 2015-12-30 | 2016-06-15 | 东北大学 | Micro-grid load prediction system and method based on electricity purchased on-line and dynamic correlation factor |
| CN106022549A (en) * | 2016-07-28 | 2016-10-12 | 兰州理工大学 | Short term load predication method based on neural network and thinking evolutionary search |
Non-Patent Citations (3)
| Title |
|---|
| 刘齐更: "基于数据挖掘的短期负荷预测方法的研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 袁喜春等: "动态T-S模糊Elman网络及其应用", 《信息与控制》 * |
| 邰晓红等: "基于模糊控制修正Elman神经网络的电力负荷短期动态预测", 《世界科技研究与发展》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590562A (en) * | 2017-09-05 | 2018-01-16 | 西安交通大学 | A kind of Short-Term Load Forecasting of Electric Power System based on changeable weight combination predicted method |
| CN107704967A (en) * | 2017-10-17 | 2018-02-16 | 吉林省电力科学研究院有限公司 | A kind of Short-Term Load Forecasting Method based on improvement fuzzy neural network |
| CN109240088B (en) * | 2018-10-24 | 2020-04-10 | 闽江学院 | Estimation and compensation finite time control method for power network communication delay |
| CN109240088A (en) * | 2018-10-24 | 2019-01-18 | 闽江学院 | A kind of estimation of electric power networks communication delay and compensation finite-time control method |
| CN109617097A (en) * | 2018-12-26 | 2019-04-12 | 贵州电网有限责任公司 | Three-phase load unbalance self-decision administering method based on fuzzy neural network algorithm |
| CN109617097B (en) * | 2018-12-26 | 2022-06-21 | 贵州电网有限责任公司 | Three-phase load unbalance self-decision-making treatment method based on fuzzy neural network algorithm |
| CN110009132A (en) * | 2019-03-04 | 2019-07-12 | 三峡大学 | A kind of short-term electric load fining prediction technique based on LSTM deep neural network |
| CN110046765A (en) * | 2019-04-15 | 2019-07-23 | 国网甘肃省电力公司电力科学研究院 | A kind of power system stabilizer, PSS implementation method based on Elman neural network |
| CN111142027A (en) * | 2019-12-31 | 2020-05-12 | 国电南瑞南京控制系统有限公司 | Lithium iron phosphate battery state-of-charge monitoring and early warning method based on neural network |
| CN111080037A (en) * | 2020-01-02 | 2020-04-28 | 中国电力科学研究院有限公司 | Short-term power load prediction method and device based on deep neural network |
| CN111952962A (en) * | 2020-07-30 | 2020-11-17 | 国网江苏省电力有限公司南京供电分公司 | Power distribution network low voltage prediction method based on T-S fuzzy neural network |
| CN112668776A (en) * | 2020-12-25 | 2021-04-16 | 国网黑龙江省电力有限公司电力科学研究院 | Long-short term memory network model power load prediction method suitable for alpine region |
| CN112862194A (en) * | 2021-02-08 | 2021-05-28 | 杭州市电力设计院有限公司余杭分公司 | Power distribution network power supply planning method, device, equipment and readable storage medium |
| CN112862194B (en) * | 2021-02-08 | 2024-04-26 | 杭州市电力设计院有限公司余杭分公司 | Power distribution network power supply planning method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971238A (en) | The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S | |
| US11409347B2 (en) | Method, system and storage medium for predicting power load probability density based on deep learning | |
| CN106709820A (en) | Power system load prediction method and device based on deep belief network | |
| CN107037373B (en) | Battery remaining capacity prediction technique neural network based | |
| CN109615124B (en) | SCADA master station load prediction method based on deep learning | |
| CN103793887B (en) | Short-term electric load on-line prediction method based on self-adaptive enhancement algorithm | |
| CN111460001B (en) | Power distribution network theoretical line loss rate evaluation method and system | |
| CN109816204A (en) | A kind of safety of subway operation Tendency Prediction method based on GA-SVM | |
| CN112149976B (en) | Power grid accurate investment project decision method based on artificial intelligence | |
| CN113361801A (en) | Hybrid rolling short-term load prediction method based on GAN network and semi-supervised regression | |
| CN112785051A (en) | Cloud resource prediction method based on combination of EMD and TCN | |
| CN115879369A (en) | Coal mill fault early warning method based on optimized LightGBM algorithm | |
| Čurčić et al. | Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data | |
| CN111027760B (en) | Power load prediction method based on least square vector machine | |
| CN110222910B (en) | Active power distribution network situation prediction method and prediction system | |
| CN111539558A (en) | Power load prediction method adopting optimized extreme learning machine | |
| Lin | Short-term prediction of building sub-item energy consumption based on the CEEMDAN-BiLSTM method | |
| CN114462670A (en) | LSTM model-based power consumption prediction method | |
| CN114240687A (en) | Energy hosting efficiency analysis method suitable for comprehensive energy system | |
| CN117521501A (en) | NSGA-based LSTM prediction energy power generation method and system | |
| Xu et al. | Short-term electricity consumption forecasting method for residential users based on cluster classification and backpropagation neural network | |
| CN116862043A (en) | Load prediction method and system based on multilayer feedforward network | |
| Raphel | Artificial intelligence‐based wind forecasting using variational mode decomposition. | |
| CN116303386A (en) | Intelligent interpolation method and system for missing data based on relational graph | |
| Tan et al. | A fast and stable forecasting model to forecast power load |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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: 20170721 |
|
| RJ01 | Rejection of invention patent application after publication |