An Adaptive Energy Saving Mechanism for LTE-A Self-Organizing HetNets

Since the information and communication technology industry is one of contributors to global warming, how to utilize self-organizing networks (SONs), which can simplify network management, to achieve energy saving over future cellular networks has been a significant issue. We propose an adaptive energy saving mechanism (AES) for LTE-A self-organizing heterogeneous networks (HetNets). The proposed AES is designed for multi-hop cellular networks, in which each cell has an enhanced Node B (eNB) and multiple relay nodes (RNs). The AES uses two-level multi-threshold load management for each RN under different eNBs (inter-cell level) and for each RN within the same eNB (intra-cell level) so as to reduce the congestion in hot spot eNBs and RNs. In addition, the AES can dynamically switch an RN between active and sleep modes to maximize the number of sleep RNs for adaptive energy saving. It can also dynamically change an RN's coverage area to reduce energy consumption and to increase radio resource utilization. Besides, the AES adopts a neural network predictor to forecast the loading of each RN to determine whether it is appropriate to switch an RN to sleep mode. Simulation results show that with slightly sacrificing average throughput (1.16% lower) and radio interface delay (1.4% higher), the proposed AES's percentage of sleep RNs is from 0.28 to 0.19 under the percentage of active UEs from 0.7 to 1. Comparing with a representative related work, reinforcement learning (RL), the proposed AES's average energy consumption is 26.44% lower than RL's.