A Fuzzy Logic–Driven Decision Support Model for Adaptive Resource Allocation in IoT-Enabled Smart Healthcare Systems

Abstract

The integration of the Internet of Things (IoT) into healthcare systems has ushered in the era of Smart Healthcare, enabling continuous patient monitoring, remote diagnostics, and personalized treatment. A critical challenge in these systems is the efficient and adaptive allocation of limited resources (e.g., bandwidth, computing power, medical personnel time) to meet fluctuating demands, particularly during emergencies or critical events. Traditional resource allocation models often rely on crisp, static rules that fail to capture the inherent uncertainty and vagueness associated with patient criticality, sensor data reliability, and dynamic network conditions. This paper proposes a novel Fuzzy Logic–Driven Decision Support Model (FL-DSM) for adaptive resource allocation in IoT-enabled Smart Healthcare Systems. The FL-DSM utilizes Fuzzy Inference Systems (FIS) to process linguistic variables representing real-time parameters—such as "Patient Vital Instability," "Network Congestion," and "Priority of Service Request"—and determines an optimal "Resource Allocation Priority Index" (RAPI). This index then dynamically guides the allocation strategy, ensuring that critical services and high-priority patients receive preferential treatment, thereby minimizing latency and improving the Quality of Service (QoS). Simulation results demonstrate that the FL-DSM significantly outperforms conventional methods in terms of resource utilization efficiency and average service completion time, particularly under high-demand and uncertain operating conditions, offering a robust and intelligent approach to managing complex healthcare resources.