Mariam Ishtiaq

Bio: Mariam Ishtiaq is an academic researcher. The author has contributed to research in topics: Radio access network & Enhanced Data Rates for GSM Evolution. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.

Edge Computing in IoT: A 6G Perspective

Abstract: Edge computing is one of the key driving forces to enable Beyond 5G (B5G) and 6G networks. Due to the unprecedented increase in traffic volumes and computation demands of future networks, Multi-access Edge Computing (MEC) is considered as a promising solution to provide cloud-computing capabilities within the radio access network (RAN) closer to the end users. There has been a huge amount of research on MEC and its potential applications; however, very little has been said about the key factors of MEC deployment to meet the diverse demands of future applications. In this article, we present key considerations for edge deployments in B5G/6G networks including edge architecture, server location and capacity, user density, security etc. We further provide state-of-the-art edge-centric services in future B5G/6G networks. Lastly, we present some interesting insights and open research problems in edge computing for 6G networks.

ML-based Handover Prediction and AP Selection in Cognitive Wi-Fi Networks

Abstract: Device mobility in dense Wi-Fi networks offers several challenges. Two well-known problems related to device mobility are handover prediction and access point selection. Due to the complex nature of the radio environment, analytical models may not characterize the wireless channel, which makes the solution of these problems very difficult. Recently, cognitive network architectures using sophisticated learning techniques are increasingly being applied to such problems. In this paper, we propose a data-driven machine learning (ML) schemes to efficiently solve these problems in WLAN networks. The proposed schemes are evaluated and results are compared with traditional approaches to the aforementioned problems. The results report significant improvement in network performance by applying the proposed schemes. For instance, the proposed scheme for handover prediction outperforms traditional methods i.e. RSS method and traveling distance method by reducing the number of unnecessary handovers by 60% and 50% respectively. Similarly, in AP selection, the proposed scheme outperforms the SSF and LLF algorithms by achieving higher throughput gains upto 9.2% and 8% respectively.

Cluster-Based Multi-User Multi-Server Caching Mechanism in Beyond 5G/6G MEC

Abstract: The work on perfecting the rapid proliferation of wireless technologies resulted in the development of wireless modeling standards, protocols, and control of wireless manipulators. Several mobile communication technology applications in different fields are dramatically revolutionized to deliver more value at less cost. Multiple-access Edge Computing (MEC) offers excellent advantages for Beyond 5G (B5G) and Sixth-Generation (6G) networks, reducing latency and bandwidth usage while increasing the capability of the edge to deliver multiple services to end users in real time. We propose a Cluster-based Multi-User Multi-Server (CMUMS) caching algorithm to optimize the MEC content caching mechanism and control the distribution of high-popular tasks. As part of our work, we address the problem of integer optimization of the content that will be cached and the list of hosting servers. Therefore, a higher direct hit rate will be achieved, a lower indirect hit rate will be achieved, and the overall time delay will be reduced. As a result of the implementation of this system model, maximum utilization of resources and development of a completely new level of services and innovative approaches will be possible.

ML-Based Handover Prediction and AP Selection in Cognitive Wi-Fi Networks

Abstract: Abstract Device mobility in dense Wi-Fi networks offers several challenges. Two well-known problems related to device mobility are handover prediction and access point selection. Due to the complex nature of the radio environment, analytical models may not characterize the wireless channel, which makes the solution of these problems very difficult. Recently, cognitive network architectures using sophisticated learning techniques are increasingly being applied to such problems. In this paper, we propose data-driven machine learning (ML) schemes to efficiently solve these problems in wireless LAN (WLAN) networks. The proposed schemes are evaluated and results are compared with traditional approaches to the aforementioned problems. The results report significant improvement in network performance by applying the proposed schemes. The proposed scheme for handover prediction outperforms traditional methods i.e. received signal strength method and traveling distance method by reducing the number of unnecessary handovers by 60% and 50% respectively. Similarly, in AP selection, the proposed scheme outperforms the strongest signal first and least loaded first algorithms by achieving higher throughput gains up to 9.2% and 8% respectively.

A Low-code Development Framework for Cloud-native Edge Systems

Abstract: Customizing and deploying an edge system are time-consuming and complex tasks because of hardware heterogeneity, third-party software compatibility, diverse performance requirements, and so on. In this article, we present TinyEdge, a holistic framework for the low-code development of edge systems. The key idea of TinyEdge is to use a top-down approach for designing edge systems. Developers select and configure TinyEdge modules to specify their interaction logic without dealing with the specific hardware or software. Taking the configuration as input, TinyEdge automatically generates the deployment package and estimates the performance with sufficient profiling. TinyEdge provides a unified development toolkit to specify module dependencies, functionalities, interactions, and configurations. We implement TinyEdge and evaluate its performance using real-world edge systems. Results show that: (1) TinyEdge achieves rapid customization of edge systems, reducing 44.15% of development time and 67.79% of lines of code on average compared with the state-of-the-art edge computing platforms; (2) TinyEdge builds compact modules and optimizes the latent circular dependency detection and message routing efficiency; (3) TinyEdge performance estimation has low absolute errors in various settings.