A*-Based Task Assignment Algorithm for Context-Aware Mobile Patient Monitoring Systems

Mobile Patient Monitoring System (MPMS) is positioned to provide high quality healthcare services in the near future. The gap between its application demands and resource supplies, however, still remains and may hinder this process. Dynamic context-aware adaptation mechanisms are required in order to meet the stringent requirements on such mission critical applications. The fundamental model underlying an MPMS includes a set of biosignal data processing tasks distributed across a set of networked devices. In our earlier work, we designed and validated a task distribution framework to support dynamic system reconfiguration of MPMS by means of task redistribution. This paper focuses on its decision-making component that can calculate the optimal task assignment by taking into account the reconfiguration costs. This paper has three major contributions. Firstly, we study a context-aware scenario and derive the design requirements for a task assignment algorithm in MPMS. Secondly, using a graph-based system model, we proposed an A*-based task assignment algorithm that minimizes the system end-to-end delay while guaranteeing required system battery lifetime and availability. We introduce a set of node expansion rules and a pre-processing procedure to calculate the heuristic function (h(n)). Thirdly, we evaluate the algorithm performance with experiments and compare this A*-based algorithm with other heuristic approaches, e.g. greedy and bounded A*.