An optimal uplink traffic offloading algorithm via opportunistic communications based on machine learning
- PDF / 2,263,671 Bytes
- 15 Pages / 595.224 x 790.955 pts Page_size
- 103 Downloads / 179 Views
An optimal uplink traffic offloading algorithm via opportunistic communications based on machine learning Qian Wang1 · Zhipeng Gao2 · Zifan Li3 · Xiaojiang Du4 · Mohsen Guizani5 Received: 12 October 2019 / Accepted: 11 March 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Opportunistic communications as an efficient traffic offloading method can be used to offload uplink traffic of cellular networks to Wi-Fi networks. However, because of its contact pattern (contact frequency and contact duration) the offloading method could not ensure the data to be successfully offloaded to Wi-Fi Access Points (APs) within a time constraint. In this paper, we focus on maximizing the probability of offloading data to Wi-Fi APs by fragmenting the data and assigning the fragments to different direct or indirect paths generated by opportunistic contacts. Firstly, we propose two methods based on mobility prediction, which is realized by machine learning, to separately calculate the probability of offloading data to WiFi APs by the direct offloading path considering multiple opportunistic contacts and contact duration, and the probability of indirectly offloading data to Wi-Fi APs by the indirect offloading path. Then, based on the probability calculation methods the offloading probability maximization is formulated as a non-linear integer programming problem, and we propose a distributed heuristic algorithm to solve it considering complexity of the probability calculation and limited computation capacities of devices. Simulation results prove the data offloading probability of our proposed algorithm outperforms other algorithms under different simulation environment. Keywords Uplink traffic offloading · Opportunistic communications · Machine learning · Offloading probability optimization
1 Introduction Opportunistic communication is a method using short-range radios (e.g. Bluetooth, WiFi) to intermittently transmit data between mobile devices without the support of infrastructure when they are within the range of each other. It can be used in 4G/5G networks to help offload portion of the traffic of cellular networks [1] without affecting the final user experience and avoiding the introduction of additional complexity in networks [2], for example, instead of directly transferring data to a specific device by cellular networks, devices can transfer data to
This article is part of the Topical Collection: Special Issue on Security and Privacy in Machine Learning Assisted P2P Networks Guest Editors: Hongwei Li, Rongxing Lu and Mohamed Mahmoud Qian Wang
[email protected]
Extended author information available on the last page of the article.
the destination by opportunistic communications. However, nowadays, most research working on opportunistic offloading focuses on offloading downlink data. There is limited research on uplink offloading. The now existing research working on uplink offloading focuses on offloading data to a specific Wi-Fi AP [3] or to multiple Wi-Fi APs by direct opportunistic
Data Loading...
