Task offloading in hybrid-decision-based multi-cloud computing network: a cooperative multi-agent deep reinforcement learning

Multi-cloud computing is becoming a promising paradigm to provide abundant computation resources for Internet-of-Things (IoT) devices. For a multi-device multi-cloud network, the real-time computing requirements, frequently varied wireless channel gains and changeable network scale, make the system more dynamic. It is critical to satisfy the dynamic nature of network with different constraints of IoT devices in multi-cloud environment. In this paper, we establish a continuous-discrete hybrid decision offloading model, each device should learn to make coordinated actions, including cloud server selection, offloading ratio and local computation capacity. Therefore, both continuous-discrete hybrid decision and coordination among IoT devices are challenging. To this end, we first develop a probabilistic method to relax the discrete action (e.g. cloud server selection) to a continuous set. Then, by leveraging a centralized training and distributed execution strategy, we design a cooperative multi-agent deep reinforcement learning (CMADRL) based framework to minimize the total system cost in terms of the energy consumption of IoT device and the renting charge of cloud servers. Each IoT device acts as an agent, which not only learns efficient decentralized policies, but also relieves IoT devices’ computing pressure. Experimental results demonstrate that the proposed CMADRL could efficiently learn dynamic offloading polices at each IoT device, and significantly outperform the four state-of-the-art DRL based agents and two heuristic algorithms with lower system cost.