TY - GEN
T1 - Two-Phase Deep Reinforcement Learning of Dynamic Resource Allocation and Client Selection for Hierarchical Federated Learning
AU - Chen, Xiaojing
AU - Li, Zhenyuan
AU - Ni, Wei
AU - Wang, Xin
AU - Zhang, Shunqing
AU - Xu, Shugong
AU - Pei, Qingqi
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper presents a new two-phase Deep Deter-ministic Policy Gradient (DDPG) framework, referred to as 'TP-DDPG', to balance online the learning delay and model accuracy of a federated learning (FL) process in an energy harvesting hierarchical FL (HFL) system. The key idea is to design a DDPG-based approach to learn the selection of participating clients, the CPU configuration, and the transmission powers of the clients, while the other decisions are efficiently optimized by a new straggler-aware client association and bandwidth allocation algorithm. The algorithm evaluates the reward of the DDPG, and substantially improves its convergence rate and stability. Experimental results demonstrate that the proposed TP-DDPG can substantially reduce the training time while achieving a higher test accuracy over the existing benchmarks.
AB - This paper presents a new two-phase Deep Deter-ministic Policy Gradient (DDPG) framework, referred to as 'TP-DDPG', to balance online the learning delay and model accuracy of a federated learning (FL) process in an energy harvesting hierarchical FL (HFL) system. The key idea is to design a DDPG-based approach to learn the selection of participating clients, the CPU configuration, and the transmission powers of the clients, while the other decisions are efficiently optimized by a new straggler-aware client association and bandwidth allocation algorithm. The algorithm evaluates the reward of the DDPG, and substantially improves its convergence rate and stability. Experimental results demonstrate that the proposed TP-DDPG can substantially reduce the training time while achieving a higher test accuracy over the existing benchmarks.
KW - client scheduling
KW - DDPG
KW - Hierarchical federated learning
KW - resource allocation
UR - http://www.scopus.com/inward/record.url?scp=85139481204&partnerID=8YFLogxK
U2 - 10.1109/ICCC55456.2022.9880724
DO - 10.1109/ICCC55456.2022.9880724
M3 - Conference Proceeding
AN - SCOPUS:85139481204
T3 - 2022 IEEE/CIC International Conference on Communications in China, ICCC 2022
SP - 518
EP - 523
BT - 2022 IEEE/CIC International Conference on Communications in China, ICCC 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE/CIC International Conference on Communications in China, ICCC 2022
Y2 - 11 August 2022 through 13 August 2022
ER -