The Unit Commitment Problem (UCP) poses a significant challenge in optimizing powergeneration schedules within complex and dynamic energy systems. This study explores theapplication of Genetic Algorithms (GAs) as a promising approach to address UCP, their ability tonavigate complex solution spaces and adapt to changing operational conditions. The work provides a broad exploration of their effectiveness, challenges, and future prospects. The objective of UCP is to efficiently optimize power generation schedules within complex energy systems, seeking cost-effective and reliable solutions while accommodating various operational constraints. Various encoding techniques and GA operations are implemented and evaluated incomparison to the solutions obtained from a commercial Mixed-Integer Linear Programming (MILP) solver. The key findings point to the potential for achieving high quality solutions and robustness in the application of these techniques. However, it is important to acknowledge and address challenges such as encoding complexity, extensive computation times, the risk of premature convergence, and the complications of handling complex constraints that continue to exist in this domain. The future scope lies in hybrid approaches, scalability enhancement and incorporation of multi-objective optimization, offering unrealized potential for the efficient andsustainable operation of modern energy systems.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:uu-516978 |
Date | January 2023 |
Creators | Mattathil Suresh, Nandini |
Publisher | Uppsala universitet, Institutionen för informationsteknologi |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Relation | IT ; 23125 |
Page generated in 0.0021 seconds