User-Aware and Flexible Proactive Caching using LSTM and Ensemble Learning in IoT-MEC Networks

  • Nguyen, The-Vi; 
  • Dao, Nhu-Ngoc; 
  • Tuong, Van Dat; 
  • Noh, Wonjong.; 
  • Cho, Sungrae.
Citations

WEB OF SCIENCE

43
Citations

SCOPUS

49

초록

To meet the stringent demands of emerging IoT applications such as smart home, smart city, and virtual reality in 5G/6G Internet-of-Things (IoT) networks, edge content caching for mobile/multi-access edge computing (MEC) has been identified as a promising approach to improve the quality of services in terms of latency and energy consumption. However, the limitations of cache capacity makes it difficult to develop an effective common caching framework that satisfies diverse user preferences. In this paper, we propose a new content caching strategy that maximizes the cache hit ratio through flexible prediction in dynamically changing network and user environments. It is based on a hierarchical deep learning architecture: long short-term memory (LSTM)-based local learning and ensemble-based meta-learning. First, as a local learning model, we employ an LSTM method with seasonal-trend decomposition using loess (STL)-based preprocessing. It identifies the attributes for demand prediction on the contents in various demographic user groups. Second, as a meta-learning model, we employ a regression-based ensemble learning method, which uses an online convex optimization framework and exhibits sublinear ‘regret’ performance. It orchestrates the obtained multiple demographic user preferences into a unified caching strategy in real-time. Extensive experiments were conducted on the popular MovieLens datasets. It was shown that the proposed control provides up to a 30% higher cache hit ratio than conventional representative algorithms and a near-optimal cache hit ratio within approximately 9% of the optimal caching scheme with perfect prior knowledge of content popularity. The proposed learning and caching control can be implemented as a core function of the 5G/6G standard’s network data analytic function (NWDAF) module.

키워드

Computational modeling; Computer architecture; demographic classification; ensemble learning; hierarchical learning; Internet of Things; Internet-of-Things (IoT); LSTM learning; Mobile/multi-access edge computing (MEC); Optimization; proactive caching.; Stochastic processes; Training; Wireless networks; 5G mobile communication systems; Automation; Convex optimization; Deep learning; Energy utilization; Green computing; Internet of things; Learning systems; Population statistics; Analytic functions; Content popularities; Demand prediction; Internet of Things (IOT); Learning architectures; Meta-learning models; Online convex optimizations; Proactive caching; Long short-term memory
제목
User-Aware and Flexible Proactive Caching using LSTM and Ensemble Learning in IoT-MEC Networks
저자
Nguyen, The-Vi; Dao, Nhu-Ngoc; Tuong, Van Dat; Noh, Wonjong.; Cho, Sungrae.
DOI
10.1109/JIOT.2021.3097768
발행일
2022-03
유형
Article
저널명
IEEE Internet of Things Journal
권
9
호
5
페이지
3251 ~ 3269