Proactive Cross-Layer Framework Based on Classification Techniques for Handover Decision on WLAN Environments

Abstract

In recent years, modern technology has been increasing, and this has grown a derivate in big challenges related to the network and application infrastructures. New devices have been providing more high functionalities to users than ever before; however, these devices depend on a high functionality of network in order to ensure a correct functioning ability over applications. This is essential for mobile networking systems to evolve in order to meet the future requirements of capacity, coverage, and data rate. In addition, when a network problem happens, it could be converted into somethingmore disastrous and difficult to solve. A crucial point is the network physical change and the difficulties, such as loss continuity of services and the decision to select the future network to be connected. In this article, a new framework is proposed to forecast a future network to be connected through a mobile node in WLAN environments. The proposed framework considers a decision-making process based on five classifiers and the user’s position and acceleration data in order to anticipate the network change, reaching up to 96.75% accuracy in predicting the connection of this future network. In this way, an early change of network is obtained without packet and time loss during the network change.

Artificial neural network and symmetric key cryptography based verification protocol for 5G enabled Internet of Things

“…It is clear from Figure 7, that the scheme in Shangguang et al (2016) had the highest communication overheads followed by the proposed protocol, the schemes in Cervantes‐Bazán et al (2022), 3GPP R16, (Nyangaresi & Rodrigues, 2022b) and the protocol in Nyangaresi and Rodrigues (2022a) in that order.…”

“…It is clear from Table 8 that the scheme in Shangguang et al (2016) had the highest computation costs followed by the schemes in Cervantes‐Bazán et al (2022), the proposed protocol, (Nyangaresi & Rodrigues, 2022a), 3GPP R16 and (Nyangaresi & Rodrigues, 2022b). The extremely high computation costs for the scheme in Shangguang et al (2016) are attributed to the bilinear pairing operations executed in this protocol.…”

“…These computations for UE as well as the SgNB and TgNB ends are listed in Table 7. Based on Table 7, the total computation overhead for the proposed protocol is 0.0198 ms. On the other hand, the schemes in (Cervantes-Bazán et al, 2022;Nyangaresi & Rodrigues, 2022b;Shangguang et al, 2016) and 3GPP R16 5G consume 1.1625, 7.2782, 0.0088 and 0.0117 ms, respectively, as presented in Table 8.…”

“…To offer handoff decision in hybrid Li‐Fi and Wi‐Fi network, a scheme based on a combination of artificial neural network and fuzzy logic is presented in Sanusi et al (2020). Similarly, a new machine learning framework for forecasting future network for connection is presented in Cervantes‐Bazán et al (2022) for wireless local area networks. This scheme uses five classifiers and network change is detected based on acceleration data as well as user position.…”

“…It is clear from Table 9 that the overall communication cost of the suggested protocol is 1824 bits or 228 bytes. Whereas, the schemes in Cervantes‐Bazán et al (2022), Nyangaresi and Rodrigues (2022b), Shangguang et al (2016) and 3GPP R16 5G require 160, 1348, 108 and 112 bytes respectively, as mentioned in Table 10.…”