Roland Niwareeba

Mr. Roland Niwareeba

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 September 2026
Verified
Book Chapter
Open access
PDF file
JSJohn Bosco Ssemakula
John Bosco Ssemakula
GMGodfrey Kibalya Mirondo
Godfrey Kibalya Mirondo
RNRoland Niwareeba
Roland Niwareeba
AKAbel Kamagara
Abel Kamagara
The introduction of Beyond Fifth Generation (B5G) and Sixth Generation (6G) technologies demands that future networks have the ability to sustain compute-intensive and latency-sensitive workloads with varying degrees of criticality. Holographic-type communication (HTC) services, where high-resolution three-dimensional (3D) real-time holograms of people or objects are transmitted with or without multi-sensory data (sound, video, haptics, or smell), are one prominent example. As 5G technologies mature, the conventional centralized cloud computing systems become ineffective due to the dramatic increase and high demands of such treasured applications. Thus, Edge Computing (EC) is the strategy adopted in this chapter to mitigate some of these issues by reducing latency and improving the use of networks. Scalability, flexibility, and agile decision-making are, however, also revealed as key requirement aspects for deploying these next-generation services in a cost and resource-efficient manner. To work around such a complicated environment of providing such services, a reinforcement learning (RL) approach is introduced that can select the most suitable serving tier and edge-site, considering all the criticality levels and various conflicting costs. Additionally, a heuristic approach is used to allocate streaming tasks efficiently on the selected edge-sites using available computing and network resources. Our simulation findings show that the RL-based approach is close to optimal within a margin of 7% and is better than other existing benchmarks. The purpose of this chapter is to give insight into how to leverage a decentralized, responsive, and intelligent network approach that can deliver the dynamically changing needs of service applications of the future.