Kunwoo Park

WAVE: Popularity-based and collaborative in-network caching for content-oriented networks

In content-oriented networking, content files are typically cached in network nodes, and hence how to cache content files is crucial for the efficient content delivery and cache storage utilization. In this paper, we propose a content caching scheme, WAVE, in which the number of chunks to be cached is adjusted based on the popularity of the content. In WAVE, an upstream node recommends the number of chunks to be cached at its downstream node, which is exponentially increased as the request count increases. Simulation results reveal that the average hop count of content delivery of WAVE is lower than other schemes, and the inter-ISP traffic volume of WAVE is the second lowest (CDN is the lowest). Also, WAVE achieves higher cache hit ratio and fewer frequent cache replacements than other on-demand caching strategies.

SCAN: Scalable Content Routing for Content-Aware Networking

Since Internet routers are not aware of the contents being forwarded, the same content file is often delivered multiple times inefficiently. Similarly, users cannot exploit a nearby copy of the content of interest unless the content file is serviced by costly content delivery networks. Prior studies on the content-aware routing for efficient content delivery suffer from the scalability problem due to a large number of contents. We propose a scalable content routing, dubbed SCAN, which can exploit nearby and multiple content copies for the efficient delivery. SCAN exchanges the information of the cached contents using Bloom filter. Compared with IP routing, SCAN can offer reduced delivery latency, reduced traffic volume, and load balancing among links.

SAMP: scalable application-layer mobility protocol

As wireless/mobile technologies evolve, the market for mobile Internet is rapidly growing. To proliferate mobile Internet market, scalable mobility support is a key question. In this article, we propose a scalable application-layer mobility protocol (SAMP) that is based on peer-to-peer (P2P) overlay networking and session initiation protocol (SIP). SAMP keeps track of locations of mobile nodes leveraging SIP mobility functions. In SAMP, all SIP servers form a P2P overlay network, which enables scalable, load balanced, and robust mobile Internet. In addition, two optimization techniques, hierarchical registration and two-tier caching schemes, are employed to localize signaling traffic for mobility and to reduce the session setup latency, respectively. Simulation results demonstrate that SAMP is an attractive choice for scalable mobile Internet and its limitations such as long handoff and session setup latencies arc substantially mitigated by the optimization techniques

Proxy-Based Wireless Data Access Algorithms in Mobile Hotspots

In this paper, we investigate efficient wireless data access algorithms in mobile hotspots. We introduce a proxy cache (PC) and propose PC-based poll-each-read (P-PER) and PC-based callback (P-CB) data access algorithms to reduce the transmission cost over wireless links in mobile hotspots. An analytical model is developed, and extensive simulations are conducted to demonstrate the performance of P-PER and P-CB. It is shown that P-PER and P-CB can improve cache hit performance and significantly reduce transmission cost. A tradeoff between P-PER and P-CB suggests the need to use a hybrid proxy-based approach to attain optimal performance of wireless data access in mobile hotspots.

Efficient Data Access Algorithms for ITS-based Networks with Multi-Hop Wireless Links

In this paper, we investigate efficient data access algorithms in intelligent transportation system (ITS)-based networks with multi-hop wireless links. We introduce a proxy cache (PC) and propose PC-based poll-each-read (P-PER) and PC-based callback (P-CB) data access algorithms to reduce the transmission cost over the bottleneck wireless links. Extensive simulation results are given to demonstrate the performance of P-PER and P-CB. It is shown that P-PER and P-CB can improve the cache hit performance and reduce the transmission cost significantly. A tradeoff between P-PER and P-CB suggests the need to use a hybrid proxy-based approach to attain optimal performance of data access in ITS-based networks with multi-hop wireless links.

Proximity Based Peer-to-Peer Overlay Networks (P3ON) with Load Distribution

Construction of overlay networks without any consideration of real network topologies causes inefficient routing in peer-to-peer networks. This paper presents the design and evaluation of a proximity based peer-to-peer overlay network (P3ON). P3ON is composed of two-tier overlay rings. The high tier ring is a global overlay in which every node participates. Whereas, the low tier ring is a local overlay that consists of nodes in the same autonomous system (AS). Since the low tier ring consists of nearby nodes (in the same AS), the lookup latency can be significantly reduced if the first search within the low tier ring is successful. Also, to cope with skewness of load (of key lookup) distribution, P3ON effectively replicates the popular keys (and results) to neighbor nodes and neighbor ASs. Simulation results reveal that P3ON outperforms the existing ring-based P2P network in terms of lookup time and achieves relatively balanced load distribution.

Waterfall: Video Distribution by Cascading Multiple Swarms

Video on demand services have been increasingly proliferated in the Internet. One popular way to disseminate video files among numerous users is to leverage peer-to-peer (P2P) systems (e.g., BitTorrent). However, BitTorrent is not designed with video streaming requirements and hence suffers from long setup delay. In this paper, the drawbacks of existing P2P-based streaming solutions are analyzed in terms of sequential delivery. Then we propose Waterfall that splits the whole swarm into multiple swarms, which are then cascaded by the scene sequence. In this way, peers in a swarm download the chunks of the same video scene from the peers in the same swarm as well as the ones in the preceding swarm that already moved on to the next scene. The average setup delay and maximum playback rate of Waterfall are analyzed. Experiments from a wide area network testbed reveal that Waterfall achieves two to three times higher playback rate and significantly low setup delay than the prior BitTorrent-based streaming solutions.

A Hybrid Wireless Data Access Algorithm in Mobile Hotspots

In this paper, we propose a hybrid wireless data access algorithm in mobile hotspots, which enables ubiquitous Internet access in vehicular networks. We first introduce a novel architecture with proxy cache (PC) for strongly consistent wireless data access and investigate the trade-off relationship between a PC-based poll-each-read (P-PER) algorithm and a PC-based callback (P-CB) algorithm. We then present a hybrid wireless data access algorithm which reduces the transmission cost by adaptively choosing P-PER and P-CB depending on the access-to-update ratio. Extensive simulation results are given to demonstrate the performance of the proposed algorithm.

The Implementation of Layer-three Site Multihoming Protocol (L3SHIM)

Layer-three SHIM (L3SHIM) protocol is designed to support site multihoming in IPv6 network and now being standardized at SHIM6 working group in IETF. A host or router can have more than two egress interfaces which are connected to a different ISP and configured by distinct IPv6 network prefixes. By using L3SHIM, when an interface is down, another interface can backup for the ongoing connections as it adopts identifier/locator decoupling architecture. Our team is implementing the L3SHIM protocol on Linux based PC using netfilter hooks in the network kernel. We implemented L3SHIM core and REAP component, and verified the feasibility and usefulness of L3SHIM in multi-homed environment by an experiment. We reported the implementation progress to SHIM6 working group in IETF 67th meeting.

Wireless Data Access in Mobile Hotspots: A Simulation Study

Mobile hotspots enable ubiquitous Internet access while users are on-board a vehicle. In this paper, we investigate wireless data access applications with strong consistency in mobile hotspots. Through extensive simulations, we quantify the performances of two well-known strongly consistent data access algorithms: poll-each-read (PER) and callback (CB). We develop a comprehensive simulation model that considers wireless link characteristics in mobile hotspots. Simulation results demonstrate the access-to-update ratio is an important factor to determine the performances of PER and CB. In addition, the effects of cache size, data access pattern, and wireless link bandwidth on the wireless data access algorithms are analyzed. Finally, valuable observations for performance optimizations are given.