Cooperation of Congestion Control Based on Energy-aware in Heterogeneous Networks

To increase the energy efficiency of the whole heterogeneous network, a scheme of cooperation in congestion control based on energy-aware is proposed in this paper. In congestion avoidance, the scheme for the first time modeled on Markov chain, will work out the amount of unacknowledged data packages on each path of heterogeneous networks, to figure out the maximum amount of data that each link can carry. Cooperation will start when the congestion window size is larger than twice of the minimal value of the maximal amount of data that each path can carry in heterogeneous networks. In cooperation, based on the Linked Increases algorithm, end-to-end energy consumption model is implemented to work out the overall energy consumption indexes; as congestion window increment is inversely proportional to the square root of the energy cost on each path, the congestion window size will be adjusted simultaneously. Simulation results demonstrate load balancing kept and fairness between single TCP flow and MPTCP flow guaranteed. The results also reveal improvement of energy utilization, and increase of the amount of data packages successfully transmitted in heterogeneous network with the throughput unchanged.