Presented by: Nagwa Shaghluf

Date: Tuesday, May 20, 2025
Time: 11:00 am - 11:45 am
Place: Zoom - see below.

Abstract:

As wireless communication networks face increasing congestion, efficient resource allocation is essential to support high-bandwidth applications and the growing number of connected devices. This research explores an integrated approach to improving spectrum efficiency and network performance in Cognitive Radio Networks (CRNs), which enable Secondary Users (SUs) to dynamically access underutilized spectrum licensed to Primary Users (PUs), while minimizing interference. The first contribution introduces a Predictive-Cooperative Spectrum Sensing (PCSS) strategy that combines historical PU activity with cooperative sensing results to guide spectrum access decisions. This centralized framework improves spectral utilization and energy efficiency, establishing a foundation for adaptive resource management. Building on this, a learning-based framework for cognitive Device-to-Device (D2D) communication is proposed, using Multi-Agent Deep Reinforcement Learning (MADRL) to dynamically allocate spectrum and power in decentralized environments. This approach enhances adaptability in complex and time-varying network conditions. Overall, the work presents a structured solution to key challenges in CRNs, emphasizing real-time decision-making and efficient resource allocation, while highlighting how the integration of CRNs with D2D and MADRL forms a strong basis for future wireless systems, including 5G and beyond.

Location: Remote via Zoom

Join Zoom Meeting

https://uvic.zoom.us/j/84667234758?pwd=Io8372wNYeoeK2gzYYwk188Fq2kdme.1

Meeting ID: 846 6723 4758

Password: 681633

One tap mobile

+16475580588,,84667234758# Canada

+17789072071,,84667234758# Canada

Dial by your location

        +1 647 558 0588 Canada

        +1 778 907 2071 Canada

Meeting ID: 846 6723 4758

Find your local number: https://uvic.zoom.us/u/kdqPUejBoD