To tackle a challenging energy efficiency problem caused by the growing mobile Internet traffic, this paper proposes a deep reinforcement learning (DRL)-based green content task offloading scheme in cloud-edge-end cooperation networks. Specifically, we formulate the problem as a power minimization model, where requests arriving at a node for the same content can be aggregated in its queue and in-network caching is widely deployed in heterogeneous environments. A novel DRL algorithm is designed to minimize the power consumption by making collaborative caching and task offloading decisions in each slot on the basis of content request information in previous slots and current network state. Numerical results show that our proposed content task offloading model achieves better power efficiency than the existing popular counterparts in cloud-edge-end collaboration networks, and fast converges to the stable state.

No abstract

Task allocation plays an important role in Unmanned Combat Aerial Vehicles' (UCAVs) cooperative control. In order to solve the problem of multiple UCAVs' cooperative task allocation, an improved ant colony algorithm (ACA) is proposed. On the basis of modeling cooperative multiple task assignment problem, the application of improved ACA is discussed. Cooperative task allocation for UCAVs shows a property of dynamic multiple phased decision problems and a task tree is used to represent that case. In the improved ACA, pheromone change is very different from other classic improved ACA. Especially when pop-up targets appear, with the help of changed pheromone matrix which is gained from former iterations, it becomes easier and quicker to find good solutions.

No abstract

No abstract