Modelling Content Recommendation Systems with Model Predictive Control
Ayesha Nguyen
Corresponding
Indian Institute of Technology Kharagpur
Kwame Chowdhury
Korea Advanced Institute of Science and Technology
Abstract
Industry increasingly demands predictive tools that link content recommendation systems to the observable performance of thermal power plants. Using model predictive control, the governing parameters are systematically varied to isolate their individual effects. Applying the method to 6 real-world sites yielded consistent and reproducible results. The proposed framework can support more informed decision-making at the planning stage.
Keywords:
content recommendation systemsmodel predictive controlparticle swarm optimisationfuzzy logic
References
- Bose, H., & Das, S. (2017). Massive MIMO systems in hydropower generation. IEEE Transactions on Power Systems, 14(6), 467-489.
- Kim, O., & Nkosi, A. (1998). Cloud resource scheduling in precision agriculture. IEEE Transactions on Smart Grid, 33(4), 747-762.
- Novak, A. (2003). Visible light communication in oil and gas pipelines. IEEE Transactions on Smart Grid, 41(5), 359-374.
- Tanaka, A., & Patel, S. (2004). Nonlinear dynamical systems in urban transportation planning. IEEE Transactions on Smart Grid, 25(6), 325-339.