Network and Multimedia Systems Lab (NMSL)

We are interested in the broad area of computer networking and distributed systems. We develop algorithms and protocols to enhance the performance of networks, especially the Internet, and to efficiently distribute multimedia content (e.g., video and audio objects) to large-scale user communities. The Network Systems Lab is led by Dr. Mohamed Hefeeda, and is affiliated with the Network Modeling Group at SFU.

Our current research interests include multimedia networking, peer-to-peer systems, wireless sensor networks, and network security. Some of the currently active projects are listed below.

Multimedia Networking

We are focusing on distributed streaming in dynamic environments in which a receiver is served by multiple senders. We are developing models to understand the characteristics (rate-distortion curves) of the fine-grained scalability of MPEG-4 video sequences. We are also working on methods to infer and model the network paths characteristics (available bandwidth, packet loss rate). Guided by these models, we seek to optimize the streaming quality.

• Rate-Distortion Optimized Streaming

• Scalable Multimedia Streaming

• Streaming to Wireless and Mobile Devices

• Content-Aware Adaptive Streaming

• Peer-assisted Content Distribution Network: Currently, there is a significant interest in the academic and industrial environments to employ the P2P computing paradigm to develop cost-effective content distribution systems over the Internet. Major content distribution networks, such as Akamai, consider the P2P paradigm as a real threat for their content distribution business. This is because the P2P paradigm may in the future achieve similar services with a fraction of the cost. However, there are several research challenges that need to be addressed to enable the P2P paradigm to achieve this potential. In this research, we tackle these research challenges. Our final objective is to develop a fully functional and reliable P2P content distribution system.

• Peer to Peer Systems: We are exploring the applicability of the P2P paradigm to build cost-effective content distribution systems. Problems such as sender selection, adaptive object replication, and content caching are being studied. We are also developing models to analyze the new characteristics of the P2P traffic and the impact of these characteristics on the cache replacement policies and object replication strategies. Furthermore, we are devising analytic models to study the dynamics of the system capacity and the impact of various parameters on it.

• Wireless Sensor Networks: We are developing algorithms to determine the minimum number of sensors and their distribution to ensure that: (i) each point in a monitored area is within the sensing range of at least <math>K</math> sensors (<math>K</math>-coverage), and (ii) each sensor is within the wireless communication rage of at least <math>C</math> sensors (<math>C</math>-connectivity). <math>K</math> and <math>C</math> are tunable parameters that depend on the reliability and security requirements of the application considered.
• Network Security: We are working on methods to assess the trustworthiness of nodes in dynamic systems (such as P2P systems) and incorporating this information into system protocols such as sender selection. In addition, we are exploring network monitoring techniques to detect and thwart intrusion and denial-of-service attacks in their early stages by observing unusual traffic patterns injected by such attacks.