Forecasting the load and renewable energy source using hybrid techniques

dc.contributor.guideGomathi, V
dc.coverage.spatialForecasting the load and renewable energy source using hybrid techniques
dc.creator.researcherArun Jees, S
dc.date.accessioned2021-07-28T06:14:20Z
dc.date.available2021-07-28T06:14:20Z
dc.date.awarded2019
dc.date.completed2019
dc.date.registered
dc.description.abstractForecasting is crucial for several operations in power system. To attain short and long-term objectives of power system like demand and inventory planning, capacity planning, pricing and marketing strategy planning forecasting becomes very vital input. Forecasting in power system can majorly depend on load and generation. Each consumer s daily load curves are categorized into a number of clusters in order to identify the electricity usage patterns. Influential factors have been identified for each individual consumer. Short-term load prediction is carried out using big data techniques which includes clustering analysis, classification and appropriate prediction model using machine learning algorithms. High penetrations of variable renewable energy increase the variability and uncertainty associated with power system operation. To manage the grid more efficiently and economically. Integrating wind and solar forecasts into scheduling and dispatch operations reduces uncertainty, helping to lower costs and improve reliability. Renewable energy forecasting improves unit commitment, dispatch efficiency, optimize reserve levels and decrease curtailment of renewable energy generation. Forecasting methods are classified into statistical, non-statistical and hybrid. For load forecasting non-statistical method predict more accurately than statistical method therefore the need of hybrid model is not much needed. In case of wind and solar energy prediction, the wind speed and solar irradiation is more vulnerable to predict so hybrid models will help to predict the accurate value. Load demand for 2015 year is predicted using 2014 year data as input. The Multilayer Artificial Neural Network (ANN) predicts more accurate results than Linear Regression (LR) and Support Vector Machine (SVM). For wind energy prediction the results of Sakarankoil and Akkanayakkanpatti have been compared with Weibull, Gamma, Numerical Weather Prediction (NWP) and ANN methods newline
dc.description.note
dc.format.accompanyingmaterialNone
dc.format.dimensions21cm
dc.format.extentxx,166p.
dc.identifier.urihttp://hdl.handle.net/10603/333528
dc.languageEnglish
dc.publisher.institutionFaculty of Electrical Engineering
dc.publisher.placeChennai
dc.publisher.universityAnna University
dc.relationp.156-165
dc.rightsuniversity
dc.source.universityUniversity
dc.subject.keywordRenewable energy
dc.subject.keywordPower system
dc.subject.keywordLinear Regression
dc.titleForecasting the load and renewable energy source using hybrid techniques
dc.title.alternative
dc.type.degreePh.D.

Files

Original bundle

Now showing 1 - 5 of 20
Loading...
Thumbnail Image
Name:
01_title.pdf
Size:
25.56 KB
Format:
Adobe Portable Document Format
Description:
Attached File
Loading...
Thumbnail Image
Name:
02_certificates.pdf
Size:
72.64 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
03_vivaproceedings.pdf
Size:
721.41 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
04_bonafidecertificate.pdf
Size:
108.9 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
05_abstracts.pdf
Size:
67.13 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.79 KB
Format:
Plain Text
Description: