The Covid-19 crisis has highlighted the vulnerability of access to food and the need for local and circular food supply chains in urban environments. Nowadays, Indoor Vertical Farming has been increased in large cities and started deploying Artificial Intelligence to control vegetations remotely. This thesis aims to monitor and control the vertical farm by scheduling the farming activities by solving a newly proposed Job-shop scheduling problem to enhance food productivity. The Job-shop scheduling problem is one of the best-known optimization problems as the execution of an operation may depend on the completion of another operation running at the same time. This paper presents an efficient method based on genetic algorithms developed to solve the proposed scheduling problem. To efficiently solve the problem, a determination of the assignment of operations to the processors and the order of each operation so that the execution time is minimized. An adaptive penalty function is designed so that the algorithm can search in both feasible and infeasible regions of the solution space. The results show the effectiveness of the proposed algorithm and how it can be applied for monitoring the farm remotely. / <p>The presentation was held in zoom</p>
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:mdh-53355 |
| Date | January 2021 |
| Creators | Abukhader, Rami, Kakoore, Samer |
| Publisher | Mälardalens högskola, Akademin för innovation, design och teknik, Mälardalens högskola, Akademin för innovation, design och teknik |
| 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 |
Page generated in 0.0019 seconds