Multipath TCP-Based IoT Communication Evaluation: From the Perspective of Multipath Management with Machine Learning.

Ruiwen Ji,Xiaotian Fan,Gang Lei,Yuanlong Cao,Yirui Jiang,Yong Ma

doi:10.3390/s20226573

Abstract

With the development of wireless networking technology, current Internet-of-Things (IoT) devices are equipped with multiple network access interfaces. Multipath TCP (MPTCP) technology can improve the throughput of data transmission. However, traditional MPTCP path management may cause problems such as data confusion and even buffer blockage, which severely reduces transmission performance. This research introduces machine learning algorithms into MPTCP path management, and proposes an automatic learning selection path mechanism based on MPTCP (ALPS-MPTCP), which can adaptively select some high-quality paths and transmit data at the same time. This paper designs a simulation experiment that compares the performance of four machine learning algorithms in judging path quality. The experimental results show that, considering the running time and accuracy, the random forest algorithm has the best performance in judging path quality.

Highlights

With the extensive application of the Internet-of-Things (IoT) network technology and users’increasing interest in various applications of IoT, the IoT traffic volume has increased significantly in the global Internet traffic [1,2]
Automatic learning path selection mechanism based on multipath Transmission Control Protocol (MPTCP) (ALPS-MPTCP) uses machine learning algorithms
We have introduced machine learning into MPTCP path management at the application layer, taking advantage of portability and convenience of access to a variety of information from wireless networks and mobile devices

Summary

Introduction

With the extensive application of the Internet-of-Things (IoT) network technology and users’increasing interest in various applications of IoT, the IoT traffic volume has increased significantly in the global Internet traffic [1,2]. The development of various wireless access technologies (such as Wi-Fi, WiMax, LTE, etc.) has promoted modern IoT devices to be equipped with multiple network interfaces and attached with multiple heterogeneous access functions [3]. These devices can meet the data transmission requirements in the IoT environment through multiple network links, and are supported by the emerging multipath Transmission Control Protocol (MPTCP) technology [4]. When MPTCP is used for concurrent transmission over heterogeneous networks, the most important thing is how to effectively manage and utilize multiple asymmetric paths to maximize system throughput performance. The lack of intelligent path management will cause various problems in the current MPTCP

Methods

Results

Conclusion