Energy-Efficiency Oriented Traffic Offloading in Wireless Networks: A Brief Survey and a Learning Approach for Heterogeneous Cellular Networks

TLDR

The paper surveys existing traffic offloading techniques in wireless networks and highlights how cell energy consumption depends on coupled system loads across shared frequency bands. It proposes an online reinforcement learning framework to offload traffic in stochastic heterogeneous cellular networks, aiming to minimize total discounted energy consumption while preserving user QoS. The authors model the problem as a discrete‑time Markov decision process and develop centralized and decentralized QC‑learning algorithms that learn optimal offloading policies without prior DTMDP statistics. Simulations demonstrate that the model‑free QC‑learning algorithms effectively balance energy savings and QoS, proving especially useful when the state space is large.

Abstract

This paper first provides a brief survey on existing traffic offloading techniques in wireless networks. Particularly as a case study, we put forward an online reinforcement learning framework for the problem of traffic offloading in a stochastic heterogeneous cellular network (HCN), where the time-varying traffic in the network can be offloaded to nearby small cells. Our aim is to minimize the total discounted energy consumption of the HCN while maintaining the quality-of-service (QoS) experienced by mobile users. For each cell (i.e., a macro cell or a small cell), the energy consumption is determined by its system load, which is coupled with system loads in other cells due to the sharing over a common frequency band. We model the energy-aware traffic offloading problem in such HCNs as a discrete-time Markov decision process (DTMDP). Based on the traffic observations and the traffic offloading operations, the network controller gradually optimizes the traffic offloading strategy with no prior knowledge of the DTMDP statistics. Such a model-free learning framework is important, particularly when the state space is huge. In order to solve the curse of dimensionality, we design a centralized Q-learning with compact state representation algorithm, which is named QC-learning. Moreover, a decentralized version of the QC-learning is developed based on the fact the macro base stations (BSs) can independently manage the operations of local small-cell BSs through making use of the global network state information obtained from the network controller. Simulations are conducted to show the effectiveness of the derived centralized and decentralized QC-learning algorithms in balancing the tradeoff between energy saving and QoS satisfaction.