Optimizing Patient Admission and Room Allocation in Cloud-Enabled Healthcare Systems

Efficient patient room allocation is a critical challenge in healthcare management due to increasing patient demand, limited hospital resources, and the need for improved operational efficiency. Cloud-based scheduling and resource allocation techniques have been increasingly adopted in healthcare workflows because they provide scalable computing resources dynamic workload management with service level guarantees. Motivated by these advantages, this study proposes a hybrid multi-object optimization framework that integrates the Non-dominated Sorting Genetic Algorithm III (NSGA-III) with an Artificial Bee Colony (ABC) based hybrid (ABC-NSGA-III) local search strategy for healthcare room scheduling. The proposed model simultaneously optimizes four key objectives: minimization of hard constraint violations caused by overlapping patient room assignments, reduction of average waiting time and balancing of room occupancy load to ensure efficient and fair resource utilization. Experimental evaluation across multiple datasets demonstrates that the hybrid ABC-NSGA-III framework achieves the highest overall performance score of 30.62%, outperforming Harris Hawks Optimization 25.06%, NSGA-III 24.70%, Artificial Bee Colony 16.83% and Marine Predators Algorithm 27%. The consistent top ranking performance confirms the robustness and effectiveness of framework provide a scalable efficient solution for healthcare room scheduling leading to improved resource utilization balance workload and enhanced operational efficiency.