點對點網路(peer-to-peer network)在最近受到了大量的注目。傳統的非結構化點對點網路由於需要將搜尋利用廣播的方式傳遞至整個網路，在整個效率上是比較差並浪費網路頻寬的。因此，結構化點對點網路因應而生。每個網路內的端點以及檔案都由一個hash key表示。根據hash key，每個端點以及檔案皆有規律的連接及放置。使用者欲搜尋檔案的時候，便可以根據檔案的hash key而有效率的找到其所在位置。
雖然改善了非結構化網路的效率，結構化點對點網路卻無法處理一些較複雜的搜尋，因為這些複雜的搜尋無法轉換成搜尋使用的hash key。因此，便有人提出，在結構化點對點網路面對無法處理複雜搜尋的時候時，可以利用廣播的方式來幫助搜尋。利用結構化網路中存在於每個端點的路徑選擇資訊(routing information)，我們可以建造一個展延樹(spanning tree)。經由這個延展樹，我們便可以將廣播訊息有效率的傳遞給網路中的每個端點，進而解決結構化點對點網路無法處理複雜搜尋的問題。
然而，若不限定廣播的範圍(scope)，廣播將會帶給整個網路很大的負擔。因此，在這篇論文中，我們討論了如何利用結構化點對點網路所形成的延展樹來做有效率的限定範圍廣播。我們採用了網路密度(network density)的資訊來幫助設定存活時間(time-to-live)，利用不同的存活時間，進而達成搜尋時想要的廣播範圍。我們提出了數種可能的收集網路密度的方法，並透過實驗來分析各種方法的效能來驗證其效率及可行性。另外，我們的實驗結果顯示，網路密度確實可以幫助我們有效率的做限定範圍廣播。

DHT-based structured P2P networks could not support complex queries, such as range query and wild-card matching, due to their reliance on hashing to name the objects to be managed. A workaround is to broadcast the query to all nodes in the network, where the query can be processed locally. Previous research has suggested to build a spanning tree on a structured P2P network using local routing information. Once the spanning tree is built, queries can be propagated upon it without redundancy. Yet it has not been studied on how to broadcast to a limited scope effectively and efficiently instead of to the whole network. By a scope, we mean a broadcast message is sent to all nodes in a region in the overlay network defined by the scope and centered on the sender. A k-node scoped broadcast is a scoped broadcast that reaches at least k nodes. One way to control the broadcast scope is to set a TTL value. Because of the dynamic nature of P2P networks, the spanning tree changes continuously. Thus the value of TTL must be chosen carefully to achieve different scoped broadcast requirements. The goal of this thesis is to investigate and evaluate ways of selecting TTL values for k-node scoped broadcast in DHT-based P2P networks. We discuss three possible solutions. The main idea of these methods is that network exploration should be performed before broadcast, and the explored information could be used to pick a suitable TTL value for scope k. We evaluate our approaches through simulations. It is showed that with network density information, scoped broadcast could be performed more efficiently.

[1] M. Bawa, H. Garcia-Molina, A. Gionis, and R. Motwani, “Estimating Aggregates on a Peer-to-Peer Network,” Technical Report, Dept. of Computer Science, Stanford University, 2003.
[2] R. Bhagwan, S. Savage and G. M. Voelker, “Understanding Availability,” in Proceedings of the International Workshop on Peer-to-Peer Systems. Springer Press, February 2003.
[3] S. El-Ansary, L. O. Alima, P. Brand, and S. Haridi, “Efficient Broadcast in Structured P2P Networks,” in Proceedings of the International Workshop on Peer-to-Peer Systems. Springer Press, February 2003.
[4] H.C. Hsiao and C.T. King, “Tornado: Capability-Aware Peer-to-Peer Storage Networks,” Journal of Parallel and Distributed Computing, vol. 64, no. 6, pp. 747-758, June 2004.
[5] T. Klingberg, and R. Manfredi, “The Gnutella 0.6 Protocol Draft,” http://rfc-gnutella.sourceforge.net/.
[6] J. Li, K. Sollins, and D.-Y. Lim, “Implementing Aggregation and Broadcast over Distributed Hash Tables,” ACM SIGCOMM Computer Communication Review, vol. 35, issue 1, January 2005, pp. 81-92.
[7] A. Montresor, M. Jelasity, and O. Babaoglu, “Robust Aggregation Protocols for Large-Scale Overlay Networks,” in Proceedings of the 2004 International Conference on Dependable Systems and Networks, June 2004, pp. 19-28.
[8] D. Psaltoulis, D. Kostoulas, I. Gupta, K. Birman, and A. Demers, “Practical Algorithms for Size Estimation in Large and Dynamic Groups.”
[9] S. Ratnasamy, P. Francis, M. Handley, R. Karp, and S. Shenker, “A Scalable Content Addressable Network,” in Proceedings of the International Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications. ACM Press, August 2001, pp. 161-172.
[10] M. Ripeanu, I. Foster, and A. Iamnitchi, “Mapping the Gnutella Network: Properties of Large-Scale Peer-to-Peer Systems and Implications for System Design,” IEEE Internet Computing, vol. 6, issue 1, January-February 2002, pp. 50-57.
[11] A. Rowstron and P. Druschel, “Pastry: Scalable, Distributed Object Location and Routing for Large-Scale Peer-to-Peer Systems,” Lecture Notes in Computer Science, vol. 2218, pp. 161-172, November 2001.
[12] R. Schollmeier, and F. Hermann, “Topology-Analysis of Pure Peer-to-Peer Networks,“ in Proceedings of Kommunikation in Verteilten Systemen, February 2003.
[13] K. Sripanidkulchai, “The Popularity of Gnutella Queries and Its Implications on Scalability,” February 2001, O'Reilly's www.openp2p.com website
[14] I. Stoica, R. Morris, D. Karger, M. F. Kaashoek, and H. Balakrishnan, “Chord: A Scalable Peer-To-Peer Lookup Service for Internet Applications,” in Proceedings of the International Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications. ACM Press, August 2001, pp. 149-160.
[15] E. W. Weisstein. "Pascal's Triangle." From MathWorld--A Wolfram Web Resource, http://mathworld.wolfram.com/PascalsTriangle.html