Resource Allocation Management in Patient-to-Physician (P2P) Communications based on Deep Reinforcement Learning in Smart Healthcare

The integration of smart cities and healthcare has led to the employment of technology and information into medical practices and health around the world. In this work, we improve a mechanism of resource allocation for communications as decentralized of patient-to-physician (P2P). We studied capabilities of deep reinforcement learning to enhance the resource allocation model, to optimally exploiting resources, and fulfillment the QoS. Regarding to mechanism of the decentralized resource allocation, independently the “agent”, patient-to-physician, it's decisions making to detect the efficient power level for transmission and channel without requiring a piece of global information. We develop a decentralized resource allocation management model in P2P communications according to deep reinforcement learning based on multi-agent, where the constraints of the delay on P2P links can be addressed directly. The aftereffects of recreation, every operator can proficiently figure out how to satisfy the severe limitations of dormancy on P2P links correspondence while decreasing the obstruction to patient/doctor to-infrastructure(PP2I) links interchanges.