Projects per year
Abstract
We consider wireless caching both at the network edge and at User Equipment (UE) to alleviate traffic congestion, aiming to find a joint cache placement and delivery policy by maximizing the Quality of Service (QoS) while minimizing backhaul load and User Equipment (UE) power consumption. We assume unknown and time-variant file popularities which are affected by the UE cache content, leading to a non-stationary Partial Observable Markov Decision Process (POMDP). We address this problem in a deep reinforcement learning framework, employing Feed Forward Neural Network (FFNN) and Long Short Term Memory (LSTM) networks in conjunction with Advantageous Actor Critic (A2C) algorithm. LSTM exploits the correlation of the file popularity distribution across time slots to learn information of the dynamics of the environment and A2C algorithm is used due to its ability of handling continuous and high dimensional spaces. We leverage LSTM and A2C tools based on its virtue to find an optimal solution for the POMDP environment. Simulation results show that using LSTM-based A2C outperforms a FFNN-based A2C in terms of sample efficiency and optimality. An LSTM-based A2C gives a superior performance under the non-stationary POMDP paradigm.
Original language | English |
---|---|
Title of host publication | 2023 IEEE International Conference on Communications Workshops |
Subtitle of host publication | Sustainable Communications for Renaissance, ICC Workshops 2023 |
Publisher | IEEE |
Pages | 764-769 |
Number of pages | 6 |
ISBN (Electronic) | 979-8-3503-3307-7 |
ISBN (Print) | 979-8-3503-3308-4 |
DOIs | |
Publication status | Published - 23 Oct 2023 |
MoE publication type | A4 Conference publication |
Event | IEEE International Conference on Communications Workshops - Rome, Italy Duration: 28 May 2023 → 1 Jun 2023 |
Publication series
Name | IEEE International Conference on Communications workshops |
---|---|
Publisher | IEEE |
ISSN (Electronic) | 2694-2941 |
Workshop
Workshop | IEEE International Conference on Communications Workshops |
---|---|
Abbreviated title | ICC Workshops |
Country/Territory | Italy |
City | Rome |
Period | 28/05/2023 → 01/06/2023 |
Fingerprint
Dive into the research topics of 'Cache Policy Design via Reinforcement Learning for Cellular Networks in Non-Stationary Environment'. Together they form a unique fingerprint.Projects
- 1 Active
-
RILREW: Reinforcement Learning for Real-time Wireless Scheduling and Edge Caching: Theory and Algorithm Design
Tirkkonen, O. (Principal investigator), Amidzade, M. (Project Member), Srinivasan, A. (Project Member), Singh, U. (Project Member), Shaikh, B. (Project Member) & Al-Tous, H. (Project Member)
01/01/2022 → 31/12/2024
Project: Academy of Finland: Other research funding