CN110533257A - Prediction method for district heating load - Google Patents
Prediction method for district heating load Download PDFInfo
- Publication number
- CN110533257A CN110533257A CN201910835026.0A CN201910835026A CN110533257A CN 110533257 A CN110533257 A CN 110533257A CN 201910835026 A CN201910835026 A CN 201910835026A CN 110533257 A CN110533257 A CN 110533257A
- Authority
- CN
- China
- Prior art keywords
- load
- heat supply
- data
- heating load
- district heating
- 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 55
- 238000010438 heat treatment Methods 0.000 title claims abstract description 49
- 238000001914 filtration Methods 0.000 claims abstract description 18
- 230000000739 chaotic effect Effects 0.000 claims abstract description 5
- 238000013277 forecasting method Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 239000002245 particle Substances 0.000 claims description 3
- 238000012731 temporal analysis Methods 0.000 claims description 3
- 238000000700 time series analysis Methods 0.000 claims description 3
- 238000002405 diagnostic procedure Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 238000004140 cleaning Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 4
- 238000005183 dynamical system Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011549 displacement method Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000005039 memory span Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method 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)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a prediction method for district heating load, which comprises the following steps: s1, collecting historical data of regional heat supply; s2, cleaning the heat supply historical data to remove abnormal data values and fill blank data; s3, modeling and analyzing the heat supply load, analyzing the time sequence of the heat supply load, and reconstructing the model of the heat supply load under the time sequence into a phase space nonlinear chaotic time sequence; and S4, predicting the heat supply load, and performing prediction filtering on the nonlinear chaotic time sequence of the phase space by adopting a filtering prediction method. In the embodiment of the application, the defects of subjective modeling and excessive dependence on data samples are overcome, the method for predicting the district heating load can be completed only by the load time sequence, the prediction with higher confidence can be realized only by the load time sequence, and the operability and the real-time performance of the algorithm in the industrial application environment are improved.
Description
Technical field
This application involves heating load forecasting technical field more particularly to a kind of prediction sides for district heating load
Method.
Background technique
Heating demand is that heat supply company for user provides the measurement of heat ability, is to measure heat supply company to provide the energy of heat
The important indicator of power.Cell central heating should determine optimal operation scheme, and according to the needs of thermic load to meet thermic load
It needs for main target.Regional electric administrative department should fully consider confession when formulating cell central heating power scheduling curve
Thermic load curve and energy factor are not able to the electricity index limitation external heat supply of cell central heating.Therefore, regional heating is supplied
Thermic load (abbreviation heating demand) carries out Accurate Prediction, has both facilitated grid company reasonable arrangement power plants generating electricity, and optimization distribution is worked as
Ground power resources, elevator net are coordinated horizontal, it helps power plant optimizes electric generation management, improves generating efficiency.
Heating demand has that data volume is big, randomness mainly by when the inside even from weather such as ground temperature, weather, wind speed
Feature high, variation is fast.Currently, mainly having to the method for heating load forecasting in the prior art: 1, using
LogicRegression (logistic regression) and time series models predict heating demand；2, using neural network model
Heating demand is predicted；3, predict that heating demand, model above is using using SVM (support vector machines) model
When need subjective modeling, introduce and artificially understand difference.
Summary of the invention
The application provides a kind of prediction technique for district heating load, with solve subjective modeling in the prior art, according to
The defect for relying data sample excessive.
The embodiment of the present application provides a kind of prediction technique for district heating load, comprising the following steps:
S1, pickup area heat supply historical data；
S2, data cleansing is carried out to heat supply historical data, realizes that data outliers are rejected and clear data is filled；
The modeling analysis of S3, heating demand；
S4, heating load forecasting.
Further, the step S3 is specially the time series analysis to heating demand, by heating demand in time sequence
Model reconstruction under column is the non-linear chaos time sequence of phase space.
Further, the step S4 be specially use filter forecasting method to the non-linear chaotic time sequence of phase space into
Row predictive filtering.
Further, the step S1 specially acquires thermic load and heat exchange station from heat supply at regular intervals
Heating demand.
Further, the step S2 is specially that data outliers are rejected using threshold value diagnostic method, and clear data fills out use
Two o'clock fit mean value method.
Further, the filter forecasting method is gaussian filtering or Kalman filtering or particle filter or dual-tree complex wavelet
Filtering or the filtering of functional series.
In the embodiment of the present application, due to the adoption of the above technical scheme, overcome subjectivity to model, rely on data sample excessively
Defect, it is only necessary to which the method that district heating load prediction can be completed in Load Time Series relies only on Load Time Series
The forecast for realizing high confidence, improves algorithm in industrial application situational operative and real-time.For the energy, provider is mentioned
Theoretical tool has been supplied, has been provided the foundation guarantee to implement energy saving policy, reducing carbon emission.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 is the application somewhere data reconstruction phase space plot；
Fig. 2 is the application space attractor；
Fig. 3 is the matched curve figure of the application predicted value and actual value；
Specific embodiment
To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with the application specific embodiment pair
Technical scheme is clearly and completely described.Obviously, described embodiment is only some embodiments of the present application,
Instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not making creative labor
Every other embodiment obtained under the premise of dynamic, shall fall in the protection scope of this application.
The technical solution that each embodiment of the application described further below provides.
The application provides a kind of prediction technique for district heating load, comprising the following steps:
S1, pickup area heat supply historical data；
The heating demand of thermic load and heat exchange station from heat supply is acquired at regular intervals.
S2, data cleansing is carried out to heat supply historical data, realizes that data outliers are rejected and clear data is filled；
Data outliers reject the exception that can filter extraordinary reason using disturbed value, can use but be not limited to threshold value and sentence
Other method；
Null value caused by clear data filling can be added because of reasons such as equipment faults, can use but be not limited to two o'clock
Fit mean value method, according to the missing values method that nearby value seeks algorithm average.
The modeling analysis of S3, heating demand, the time series analysis to heating demand, by heating demand under time series
Model reconstruction be phase space non-linear chaos time sequence.
Selection delay time t and Embedded dimensions m is needed in phase space reconfiguration, process can refer to phase space reconfiguration delay time
With the selection of Embedded dimensions.
There are two crucial parameters for phase space reconfiguration: delay time t and Embedded dimensions m, due in the practical application of engineering
Time series is all noisy finite sequence, and Embedded dimensions m and delay time t have to be chosen according to practical situation and close
Suitable value.
Value about Embedded dimensions m and delay time t, it is believed that Embedded dimensions m and delay time t be it is irrelevant,
It first finds out delay time t and finds out suitable Embedded dimensions m further according to it later.
Finding out the more commonly used method of delay time t mainly has correlation method, average displacement method, complex autocorrelation method and mutual trust
Breath method etc., the method for finding Embedded dimensions m are mainly geometrical invariants method, falseness closest to method (False Nearest
Neighbors) and it improve after Cao method etc..
About the determination of delay time t, the method that can be used such as: auto-correlation coefficient method, it is linear between abstraction sequence
Correlation or interactive information method, for judging that mission nonlinear is relational.
About the determination of Embedded dimensions m, geometry not political reform can be used, calculates the Lyapunov index of attractor, gradually
Increase dimension to change until stopping.Or it is false closest to method and its improved method falseness closest to the side improvement-Cao of method
Method.
S4, heating load forecasting carry out prediction filter using non-linear chaotic time sequence of the filter forecasting method to phase space
Wave, filter forecasting method can be gaussian filtering, Kalman filtering, particle filter, dual-tree complex wavelet filtering, the filtering of functional series
The methods of.
The predictive filtering for describing nonlinear system using Volterra functional series, and applying to use of as chaos time sequence.
Assuming that the input and output sequence of discrete non-linear hour system is u (n), then output sequence y (n)=x (n+1), recognizes
It is output sequence for y (n), Volterra series expression:
In above formula
W if taking p=1, in formula1(m1) the linear impulsive receptance function that is just known as.Likewise, wp(m1,
m2,...,mp) generalized impulse response functions of p rank subsystem can be counted as, it can use the function to the non-linear spy of system
Property is described.
To enable discrete Volterra non-linear stages wavenumber filter to carry out for realistic problem using usually using N
Rank Volterra model, this, which needs that N will be limited the use of in formula, replaces.By taking second order as an example, for Second-Order Volterra grade wavenumber filter,
Have
If the storage length (memory span) for selecting filter is M, i.e., the order of selected filter is M, then can determine
Second-Order Volterra series M rank filter expression are as follows:
Recursive least squares adaptive process is as follows:
Given primary condition is utilized in recursive least squares, is updated according to new data to old estimation,
Its data length corresponds to Current observation moment n.In addition, the order of the transversal filter based on RLS algorithm remains unchanged.According to
Criterion of least squares knowledge, the cost function based on criterion of least squares are
Wherein, λ is weighted factor, 0 < λ≤1；E (i) is the evaluated error of i moment sef-adapting filter.
E (i)=d (i)-wT(n)u(i)
According to least square filter regular equation, the optimal weight vector of the filter should meet
Wherein
Φ (n)=AT(n)Λ(n)A(n)
For the time average autocorrelation matrix of i moment input vector u (i)；
Z (n)=AT(n)Λ(n)d(n)
It is averaged cross-correlation for the time of i moment input vector u (i) and expected response d (i).
Because the operand for directly seeking filter weight vector optimal value is very big, fortune is reduced by the way of recursion
Calculation amount.
Define Φ (n) recurrence formula be
Φ (n)=λ Φ (n-1)+u (n) uT(n)
Meanwhile it defining
C (n)=Φ-1(n)
C (n) is inverse correlation matrix；G (n) is gain vector.
Collated:
C (n)=λ-1C(n-1)-λ-1g(n)uT(n)C(n-1) (2)
In addition, defining cross correlation vector
Z (n)=λ z (n-1)+u (n) d (n)
Finally, the tap weights vector recurrence formula that arrangement obtains RLS algorithm is
Formula (1), (2), (3) constitute basic recurrence least square (RLS) algorithm.
Embodiment 1
1, pickup area heat supply historical data
With one hour for interval, the heat supply of the heat exchange station of the heating demand and plate heat exchanger of sampling site source source heat pump heat is negative
Lotus, area of heat-supply service 5000m2, area is monsoon climate of medium latitudes band.- 3 DEG C of temperature in winter.10 DEG C of mean temperature difference round the clock.
2, data cleansing is carried out to heat supply historical data, realizes that data outliers are rejected and clear data is filled
Setting upper limit 310GJ/h is the heat supply upper limit, and 80GJ/h is heat supply lower limit, removes abnormal point.
By looking into vacancy value, which is filled by arithmetic mean number.
3, the modeling analysis of heating demand
By information exchange entropy algorithm, time delay coefficient t=16 is acquired
By pseudo- domain algorithms, Embedded dimensions m=8 is acquired, model is established.
4, heating load forecasting
Prediction filtering device N=2 takes second-order filter, memory characteristic m=0
With posterior probability of the opposite prediction error within 5%, | e |≤5% posterior probability investigates forecast result.
Wherein,A is relative error this event within 5%, and n is forecast sample, yt
(i) and yd(i) be respectively the i-th moment actual negative charge values and forecast load value.
Test prediction accuracy rate is 85.23%.
Wherein:
Model reconstruction of the heating demand under time series is the non-linear chaos time sequence detailed process of phase space:
Assuming that: it is equipped with a m rank nonlinear-load differential equation:
X (m)=f (x, x (1), x (2), x (3) ... x (m-1)) (1)
X (m) indicates single argument load variations, if the time interval of time series is Δ t,
τ=k Δ t is enabled, then the chaos time sequence reconstructed is:
P (tj)=(x (tj), x (tj+ τ) ..., x (tj+ (m-1) τ) T (2)
Assuming that the time series of certain load is X (i), i=1,2,3 ... N are embedded in it according to formula (2) in the space of m dimension
In, then:
Wherein tj=t- (m-1) τ
It, should so as to predict future load if Xt1 is it is known that can find out X (t1+ τ) according to formula (3)
Model is mainly used in the prediction of heating demand.
Somewhere day heating demand data are taken, as shown in Figure 1, it will by the chaos time sequence formed after its phase space reconfiguration
The phase space attractor of the data reconstruction of Fig. 1 is as shown in Figure 2.
1, t is selected:
It should guarantee in phase space having differences property between difference, this requires sufficiently large τ values；If τ simultaneously
Value is infinitely great, and cannot be guaranteed the continuity of phase space.Takens proves, appropriate access time delay τ and sufficiently large insertion
The phase space of dimension m, reconstruct have geometric properties identical with actual dynamical system and information attribute, and independent of reconstruct
The detail of process.If m value is D0<m<2D0+1, D0For dynamical system strange attractor fractal dimension, so that it may delineate D0Dimension
Dynamical system chaos attractor.
2, the solution of geometrical invariants load maximum lyapunov index
The Jacobian matrix that original system equation is reconstructed by time series, then solves according to Jacobian matrix.Or think
Maximum lyapunov index passes through following equations.
3 processes:
According to Michael.T.rosenstein method, improved result is as follows:
1. estimating Load Time Series delay time T according to given data.
2. according to τ phase space reconstruction
P (tj)=(x (tj), x (tj+ τ) ..., x (tj+ (m-1) τ) T
3. seeking Cj=| Xi-Xj |, Xi is initial point
4. seeking the Dj=after system change | Yi-Yj |
5. obtaining λ=1/k Δ t<lnDj>according to Dj=Cjek Δ t
It is few that this method calculates requirement of this method to data point, and precision of prediction is high, succinctly.
Lyapunov index λ=0.0012, Fig. 3 is taken to show the matched curve of predicted value and actual value, wherein sero2 is
Predicted value, sreo1 are match value.
The result shows that, for the control errors of load prediction within 3%, that less than 1% is 37.5%, 1%- shown in Fig. 3
2% be 33.3%, 2%-3% is 29.2%, illustrates that the precision of prediction is higher, can reach the requirement of practical application.
Due to the adoption of the above technical scheme, overcome subjective modeling, rely on the excessive defect of data sample, it is only necessary to when load
Between sequence method that district heating load prediction can be completed, relying only on Load Time Series can be realized the pre- of high confidence
Report, improves algorithm in industrial application situational operative and real-time.For the energy, provider provides theoretical tool, is practicable
Energy saving policy reduces carbon emission and provides the foundation guarantee.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (6)
1. a kind of prediction technique for district heating load, which comprises the following steps:
S1, pickup area heat supply historical data；
S2, data cleansing is carried out to heat supply historical data, realizes that data outliers are rejected and clear data is filled；
The modeling analysis of S3, heating demand；
S4, heating load forecasting.
2. the prediction technique according to claim 1 for district heating load, which is characterized in that the step S3 is specific
It is the non-linear mixed of phase space by model reconstruction of the heating demand under time series for the time series analysis to heating demand
Chaos time series.
3. the prediction technique according to claim 1 or 2 for district heating load, which is characterized in that the step S4
Predictive filtering is specially carried out using non-linear chaotic time sequence of the filter forecasting method to phase space.
4. the prediction technique according to claim 1 for district heating load, which is characterized in that the step S1 is specific
For the heating demand for acquiring thermic load and heat exchange station from heat supply at regular intervals.
5. the prediction technique according to claim 1 for district heating load, which is characterized in that the step S2 is specific
It is rejected for data outliers and uses threshold value diagnostic method, clear data is filled out using two o'clock fit mean value method.
6. the prediction technique according to claim 3 for district heating load, which is characterized in that the filter forecasting side
Method is gaussian filtering or Kalman filtering or particle filter or dual-tree complex wavelet filtering or the filtering of functional series.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910835026.0A CN110533257A (en) | 2019-09-05 | 2019-09-05 | Prediction method for district heating load |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910835026.0A CN110533257A (en) | 2019-09-05 | 2019-09-05 | Prediction method for district heating load |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110533257A true CN110533257A (en) | 2019-12-03 |
Family
ID=68667093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910835026.0A Pending CN110533257A (en) | 2019-09-05 | 2019-09-05 | Prediction method for district heating load |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533257A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598302A (en) * | 2020-04-19 | 2020-08-28 | 华电郑州机械设计研究院有限公司 | Thermal power plant short-term industrial heat load prediction method based on AP-TS-SVR model |
| CN116257745A (en) * | 2023-05-10 | 2023-06-13 | 杭州致成电子科技有限公司 | Load current extreme abnormality data processing method and device |
-
2019
- 2019-09-05 CN CN201910835026.0A patent/CN110533257A/en active Pending
Non-Patent Citations (2)
| Title |
|---|
| 张永明 等: "《供热负荷时间序列混沌特性分析及预报模型研究》", 《物理学报》 * |
| 赵春晖 等: "《自适应信号处理技术》", 31 August 2009 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598302A (en) * | 2020-04-19 | 2020-08-28 | 华电郑州机械设计研究院有限公司 | Thermal power plant short-term industrial heat load prediction method based on AP-TS-SVR model |
| CN111598302B (en) * | 2020-04-19 | 2023-09-05 | 华电郑州机械设计研究院有限公司 | AP-TS-SVR model-based thermal power plant short-term industrial heat load prediction method |
| CN116257745A (en) * | 2023-05-10 | 2023-06-13 | 杭州致成电子科技有限公司 | Load current extreme abnormality data processing method and device |
| CN116257745B (en) * | 2023-05-10 | 2023-08-15 | 杭州致成电子科技有限公司 | Load current extreme abnormality data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guegan et al. | Developing a module for estimating climate warming effects on hydropower pricing in California | |
| Yang et al. | Multi-dimensional scenario forecast for generation of multiple wind farms | |
| Serttas et al. | Short term solar power generation forecasting: A novel approach | |
| Hasan et al. | A data-driven approach to estimate battery cell temperature using a nonlinear autoregressive exogenous neural network model | |
| Jallal et al. | Air temperature forecasting using artificial neural networks with delayed exogenous input | |
| Chen et al. | Air-conditioning load forecasting for prosumer based on meta ensemble learning | |
| CN110533257A (en) | Prediction method for district heating load | |
| Scott et al. | Machine learning for forecasting a photovoltaic (PV) generation system | |
| Badawi et al. | Weibull probability distribution of wind speed for gaza strip for 10 years | |
| CN117669960A (en) | New energy power prediction method based on multivariable meteorological factors | |
| Mararakanye et al. | Incorporating spatial and temporal correlations to improve aggregation of decentralized day-ahead wind power forecasts | |
| TWI491801B (en) | Wind power fault prediction system and method thereof | |
| Zavala et al. | Economic impacts of advanced weather forecasting on energy system operations | |
| CN113837473A (en) | Charging equipment fault rate analysis system and method based on BP neural network | |
| Ghassemi et al. | Optimal surrogate and neural network modeling for day-ahead forecasting of the hourly energy consumption of university buildings | |
| Shirbhate et al. | Solar panel monitoring and energy prediction for smart solar system | |
| Pinson et al. | Generation of statistical scenarios of short-term wind power production | |
| Wang et al. | Multi-prediction of electric load and photovoltaic solar power in grid-connected photovoltaic system using state transition method | |
| Gemeda et al. | Probabilistic ampacity forecasting of dynamic line rating considering tsos risk-averse | |
| Abeywickrama et al. | Integrating Weather Patterns into Machine Learning Models for Improved Electricity Demand Forecasting in Sri Lanka | |
| Sharma et al. | Renewable Energy Systems Energy Modeling using Deep Learning Techniques | |
| Abdel-Karim et al. | Modeling wind speed for power system applications | |
| Mellit et al. | An ANFIS-based prediction for monthly clearness index and daily solar radiation: application for sizing of a stand-alone Photovoltaic system | |
| Zakerinia et al. | Short term wind power forecasting using time series neural networks | |
| Safarudin et al. | The Number of Nodes Effect to Predict the Electrical Consumption in Seven Distinct Countries |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191203 |