Quantum learning cuts energy costs in 5G base stations fast
Energy Saving in 5G and Beyond Networks: A Quantum Reinforcement Learning Approach
Networking and Internet ArchitectureMachine Learning
Summary
Cell towers for 5G networks use a lot of energy, especially when many devices connect and move around. The authors study a new way to save energy by using a type of AI that learns faster with quantum computing ideas. Their method can quickly figure out when to turn towers on or off or lower power without hurting service quality. Tests show this method uses less energy and learns faster than older AI methods, even with many devices changing connections.
What this means in practice
- •For network operators: Manage base station energy use dynamically in dense 5G networks with faster learning policies from quantum-enhanced algorithms.
- •For telecom equipment vendors: Develop base station controllers that incorporate quantum reinforcement learning to reduce power consumption while maintaining service quality.
Authors
Muhammad Usman, Nguyen Van Huynh, Marianna Lezzi, Mariangela Lazoi
Abstract
Energy saving has become a critical challenge in 5G and beyond networks. The rapid growth of connected devices has increased the overall network energy demand, driving operational expenditure to unsustainable heights. The Base Station (BS) accounts for the largest share of energy usage, typically consuming around 60-70\% of the Radio Access Network (RAN)'s total energy. Therefore, to address this issue, this article optimizes the BS's energy usage while accounting for the dynamic behavior of User Equipment (UE). Deep Reinforcement Learning (DRL) is a natural candidate for determining effective energy saving policies, such as automatically switching BSs on or off when user density is low or adjusting transmission power to balance energy efficiency and Quality of Service (QoS). However, its heavy training burden and the exponential growth of state and action spaces in dense 5G environments make exploration increasingly difficult. To overcome these limitations, we introduce a novel Quantum Reinforcement Learning (QRL) algorithm that leverages quantum principles, including superposition and entanglement, through parameterized quantum circuits, enabling significantly faster convergence than DRL, which relies on conventional deep neural networks. Extensive simulations demonstrate that the proposed QRL can substantially reduce energy consumption while maintaining QoS, even when UEs are highly dynamic and frequently switch their association with BS antennas. Additionally, QRL consistently outperforms DRL and Q-Learning in both convergence speed and learning complexity.