Machine learning of redundant energy of a solar PV Mini-grid system for cooking applications

Simple item page
dc.contributor.authorOpoku, Richard
dc.contributor.authorAdjei, Eunice A.Mensah, Gidphil
dc.contributor.authorAdjei, Eunice A.
dc.contributor.authorDramani, John Bosco
dc.contributor.authorKornyo, Oliver
dc.contributor.authorNijjhar, Rajvant
dc.contributor.authorAddai, Michael
dc.contributor.authorMarfo, Daniel
dc.contributor.authorDavis, Francis
dc.contributor.authorObeng, George Yaw
dc.contributor.orcid0000-0001-8766-3402
dc.contributor.orcid0000-0003-2702-6465
dc.contributor.orcid0000-0002-7945-8676
dc.contributor.orcid0000-0002-3640-2664
dc.contributor.orcid0000-0001-8886-7853
dc.date.accessioned2024-02-28T09:27:54Z
dc.date.available2024-02-28T09:27:54Z
dc.date.issued2023
dc.descriptionThis is an article published in Solar Energy 262 (2023) 111790; https://doi.org/10.1016/j.solener.2023.06.008
dc.description.abstractSolar PV mini-grids are increasingly being deployed in off-grid and island communities especially in sub-Saharan Africa (SSA) countries to meet household energy demand. However, one challenge of solar PV mini-grids for community energy supply is the mismatch between the PV energy generation and household energy demand. PV mini-grid energy generation is highest in the afternoon whilst household energy demand is highest in the mornings and evenings, but lowest in the afternoons. This mismatch creates redundant energy generation during peak sunshine hours when battery energy storage is full, leading to low profitability for mini-grid systems. In this study, four machine learning models have been applied on an installed 30.6 kW mini-grid system in Ghana to ascertain the level of the redundant energy. The study has revealed that redundant energy exists on the mini-grid, in the range of 56.98 – 119.86 kWh/day. Further analysis has shown that the redundant energy can support household cooking energy demand through sustainable thermal batteries. With the four machine learning (ML) models applied in predicting the redundant energy, the most accurate ML model, K-nearest Neighbour Regressor, had a root mean square error (RMSE) of 0.148 and a coefficient of determination (R2 ) value of 0.998.
dc.description.sponsorshipKNUST
dc.identifier.citationSolar Energy 262 (2023) 111790; https://doi.org/10.1016/j.solener.2023.06.008
dc.identifier.urihttps://doi.org/10.1016/j.solener.2023.06.008
dc.identifier.urihttps://ir.knust.edu.gh/handle/123456789/15547
dc.language.isoen
dc.publisherSolar Energy
dc.titleMachine learning of redundant energy of a solar PV Mini-grid system for cooking applications
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S0038092X2300405X-main.pdf
Size:
2.76 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Articles