FAMAC: A Federated Assisted Modified Actor-Critic Framework for Secured Energy Saving in 5G and Beyond Networks
The constant surge in the traffic demand on cellular networks has led to continuous expansion in network capacity in order to accommodate existing and new service demands. This has given rise to ultra-dense base station deployment in 5G and beyond networks which leads to increased energy consumption in the network. Hence, these ultra-dense base station deployments must be operated in a way that the energy consumption of the network can be adapted to the spatio-temporal traffic demands on the network in order to minimize the overall energy consumption of the network. To achieve this goal, we leverage two artificial intelligence algorithms, federated learning and actor-critic algorithm, to develop a proactive and intelligent base station switching framework that can learn the operating policy of the small base station in an ultra-dense heterogeneous network (UDHN) that would result in maximum energy saving in the network while respecting the quality of service (QoS) constraints. The performance evaluation reveals that the proposed framework can achieve an energy saving that is about 77% more than that of the state-of-the-art solutions while respecting the QoS constraints of the network.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning
This paper presents a novel federated reinforcement learning (Fed-RL) methodology to enhance the cyber resiliency of networked microgrids. We formulate a resilient reinforcement learning (RL) training setup which (a) gen…
OpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)Federated Channel Learning for Intelligent Reflecting Surfaces With Fewer Pilot Signals
Channel estimation is a critical task in intelligent reflecting surface (IRS)-assisted wireless systems due to the uncertainties imposed by environment dynamics and rapid changes in the IRS configuration. To deal with th…
Federated LearningDeep Reinforcement Learning-Assisted Federated Learning for Robust Short-term Utility Demand Forecasting in Electricity Wholesale Markets
Short-term load forecasting (STLF) plays a significant role in the operation of electricity trading markets. Considering the growing concern of data privacy, federated learning (FL) is increasingly adopted to train STLF …
Deep Reinforcement LearningDemand ForecastingDimensionality ReductionFederated Learning+1Scheduling for Ground-Assisted Federated Learning in LEO Satellite Constellations
Distributed training of machine learning models directly on satellites in low Earth orbit (LEO) is considered. Based on a federated learning (FL) algorithm specifically targeted at the unique challenges of the satellite …
Federated LearningSchedulingA Modified UDP for Federated Learning Packet Transmissions
This paper introduces a Modified User Datagram Protocol (UDP) for Federated Learning to ensure efficiency and reliability in the model parameter transport process, maximizing the potential of the Global model in each Fed…
Federated Learning