Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/343260
Title: | Energy prediction and yielding optimal energy from solar photovoltaic system with the aid of artificial intelligence techniques |
Researcher: | Swamy S M |
Guide(s): | Marsaline Beno M |
Keywords: | Engineering and Technology Engineering Mechanical Artificial Intelligence Techniques Energy Yield Engineering Solar Photovoltaic System Energy Prediction |
University: | Anna University |
Completed Date: | 2020 |
Abstract: | In recent decades, non-renewable energy as a source of power newlinegeneration plays a vital role in industrial purposes and day to day activities. newlineDue to the scarcities and hazardous impact on the environment, alternative newlinesources needed to sort out these issues for growing energy demand. Solar newlineenergy is an abundantly available eco-friendly renewable energy source that newlinecan be used as an alternate source to solve the above problem. Consequently, newlineyielding optimal energy from solar photovoltaic cells is an emerging research newlinearea. The following procedures are expressed as two major objectives of this newlineresearch to resolve the scenario mentioned earlier. First and foremost research newlineanticipates identifying solar energy potential with the Artificial Intelligence newline(AI) technique. Subsequently, the research extends to enhance the newlineperformance of the multi-level inverter by using soft computing techniques. newlineConventionally, a default Artificial Neural Network (ANN) holds a newlinesingle hidden layer associated with ten-neurons used for prediction. This kind newlineof ANN model exhibits inadequate predicting performance in the context of newlineforecasting solar energy potential. The intention of configuring the ANN newlinemodel is the other prospect to overcome the performance deficiency. To newlinepursue ANN configuration via manual take a long time to compute, this urge newlineincorporating optimization techniques to reduce computational timing and newlinecomplexity. An investigation of different optimization techniques laid the newlinefoundation to develop a novel optimization method known as Evolution of newlineCub to Predator (ECP), which effectively configures the ANN model for newlinepredicting solar power. newline newline |
Pagination: | xviii, 232p. |
URI: | http://hdl.handle.net/10603/343260 |
Appears in Departments: | Faculty of Mechanical Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 59.87 kB | Adobe PDF | View/Open |
02_certificates.pdf | 702.87 kB | Adobe PDF | View/Open | |
03_abstracts.pdf | 57.14 kB | Adobe PDF | View/Open | |
04_acknowledgements.pdf | 365.33 kB | Adobe PDF | View/Open | |
05_contents.pdf | 73.18 kB | Adobe PDF | View/Open | |
06_listoftables.pdf | 63.5 kB | Adobe PDF | View/Open | |
07_listoffigures.pdf | 57.83 kB | Adobe PDF | View/Open | |
08_listofabbreviations.pdf | 77.45 kB | Adobe PDF | View/Open | |
09_chapter1.pdf | 252.11 kB | Adobe PDF | View/Open | |
10_chapter2.pdf | 233.82 kB | Adobe PDF | View/Open | |
11_chapter3.pdf | 226.7 kB | Adobe PDF | View/Open | |
12_chapter4.pdf | 920.47 kB | Adobe PDF | View/Open | |
13_chapter5.pdf | 827.61 kB | Adobe PDF | View/Open | |
14_chapter6.pdf | 679.58 kB | Adobe PDF | View/Open | |
15_conclusion.pdf | 67.1 kB | Adobe PDF | View/Open | |
16_appendices.pdf | 833.8 kB | Adobe PDF | View/Open | |
17_references.pdf | 133.91 kB | Adobe PDF | View/Open | |
18_listofpublications.pdf | 73.82 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 108.51 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: