Table 1 Summary of relevant literature.
From: Adaptive production strategy in vertical farm digital twins with Q-learning algorithms
Research Stream | Reference | Application context | Focus | Hybrid Modeling Approach |
|---|---|---|---|---|
Dt in agriculture | Kampket et al.9 | Potato harvesting | Business model of potato DT | NA |
Skobelev et al.10 | Wheat farming | Multi-agent DT ontology for wheat growth and yield forecast | Agent-based simulation and traditional optimisation | |
Kim and Heo12 | Mandarin orchards | Multi-scale DTs of orchards for sugar content and fruit size prediction | Automated machine learing algorithm | |
Li et al.14 | Vertical farming | MINLP optimisation with sustainability assessment; system modeling | MINLP optimisation | |
Ghandaret al.2 | Aquaponic systems | Fish and plant growth predicton | Comparisons among Linear regression, support vector regression, decision trees, XGBoost with decision trees | |
DT in production and supply chains | Badakhshan & Ball5 | Supply chain planning | Decision-making under disruptions | Discrete-event simulation and decision-tree algorithm |
Corsiniet al.13 | Manufacturing supply chain | Replenishment and storage resilience under disruptions | Artificial neural network and particle swarm optimisation | |
Maheswariet al.15 | Food supply chain | Supply chain productivity | Agent-based simulation and MILP | |
Du et al.17 | Flow shop scheduling | Assembly completion time and energy efficiency | Knowledge-based bi-objective collaborative optimisation and Q learning | |
Current Study | Urban vertical farming | DT implementation for yield with demand fluctuation and energy consideration | MILP and Q-learning algorithms |
