Abstract
A super-peer based overlay network architecture for peer-to-peer (P2P) systems allows for some nodes, known as the super-peers, that are more resource-endowed than others, to assume a higher share of workload. Ordinary peers are connected to the super-peers and rely on them for their transactional needs. Many criteria for a peer to choose its super-peer have been explored, some of them based on physical proximity, semantic proximity, or by purely random choice. In this paper, we propose an incentive-based criterion that uses semantic similarities between the content interests of the peers and, at the same time, encourages even load distribution across the super-peers. The incentive is achieved via a game theoretic framework that considers each peer as a rational player, allowing stable Nash equilibria to exist and hence guarantees a fixed point in the strategy space of the peers. This guarantees convergence (assuming static network parameters) to a locally optimal assignment of peers to super-peers with respect to a global cost that approximates the average query resolution time. We also show empirically that the local cost framework that we employ performs closely to (and in some cases better than) a similar scheme based on the formulation of a centralized cost function that requires the peers to know an additional global parameter.
Similar content being viewed by others
Notes
Note that apart from the load of processing queries generated by the peers that belong to the super-peer, and maintaining their caches, the super-peer also has to bear the cost of processing queries that arrive at it from other super-peers. The latter depends on the “centrality” of the super-peer in the overlay network graph. For our study, we assume this cost is uniform across all the super-peers and hence it is not considered in the local cost function.
References
Freenet. http://freenet.sourceforge.net. Accessed 09 Apr 2013
Gnutella. http://www.gnutella.com. Accessed 09 Apr 2013
Kazaa. http://www.kazaa.com. Accessed 09 Apr 2013
Skype. http://www.skype.com. Accessed 09 Apr 2013
Beverly Yang B, Garcia-Molina H (2003) Designing a super-peer network. In: Proceeding 19th IEEE international conference on data engineering, pp 49–60
Busnel Y, Kermarrec A (2007) Proxsem: Interest-based proximity measure to improve search efficiency in p2p systems. In: Proceeding fourth IEEE European conference on universal multiservice networks, ECUMN’07, pp 62–74
Cramton P, Shoham Y, Steinberg R (2006) Combinatorial auctions. MIT Press, Cambridge
Crespo A, Garcia-Molina H (2005) Semantic overlay networks for p2p systems. In: Agents and peer-to-peer computing. Springer, Berlin Heidelberg, pp 1–13
Doulkeridis C, Vlachou A, Nørvåg K, Kotidis Y, Vazirgiannis M (2010) Efficient search based on content similarity over self-organizing p2p networks. Peer-to-peer Netw Appl 3(1):67–79
Doulkeridis C, Vlachou A, Nørvåg K, Vazirgiannis M (2010) Distributed semantic overlay networks. In: Handbook of peer-to-peer networking. Springer, New York, pp 463–494
Feldman M, Lai K, Stoica I, Chuang J (2004) Robust incentive techniques for peer-to-peer networks. In: Proceedings of the 5th ACM conference on electronic commerce. ACM, New York, pp 102–111
Garbacki P, Epema D, van Steen M (2008) Broker-placement in latency-aware peer-to-peer networks. Comput Netw 52(8):1617–1633
Garbacki P, Epema D, Van Steen M (2010) The design and evaluation of a self-organizing superpeer network. IEEE Trans Comput 59(3):317–331
Garey M, Johnson D (1979) Computers and intractability. Freeman, San Francisco
Goldschlag D, Reed M, Syverson P (1999) Onion routing. Commun ACM 42(2):39–41
Karger D, Ruhl M (2004) Simple efficient load balancing algorithms for peer-to-peer systems. In: Proceeding 16th annual ACM symposium on parallelism in algorithms and architectures, pp 36–43
Karypis G, Kumar V (1996) Parallel multilevel k-way partitioning scheme for irregular graphs. In: Proceeding 1996 ACM/IEEE conference on supercomputing
Karypis G, Kumar V (1999) A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J Sci Comput 20(1):359
Kernighan B, Lin S (1970) An efficient heuristic procedure for partitioning graphs. Bell Syst Tech J 49(2):291–307
Kurve A, Kotobi K, Kesidis G (2013) An agent-based framework for performance modeling of an optimistic parallel discrete event simulator. newblock Complex Adaptive Systems Modeling (accepted)
Lv Q, Ratnasamy S, Shenker S (2002) Can heterogeneity make gnutella scalable? In: peer-to-peer networks. Springer, Berlin Heidelberg, pp 94–103
Maymounkov P, Mazieres D (2002) Kademlia: A peer-to-peer information system based on the xor metric. In: peer-to-peer networks. Springer, Berlin Heidelberg, pp 53–65
Monderer D, Shapley L (1996) Potential games. Games Econ Behav 14:124–143
Nejdl W,Wolf B, Qu C, Decker S, Sintek M, Naeve A, Nilsson M, Palmér M, Risch T (2002) Edutella: A p2p networking infrastructure based on rdf. In: Proceeding of the 11th ACM international conference on world wide web. ACM, New York, pp 604–615
Nejdl W, Wolpers M, Siberski W, Schmitz C, Schlosser M, Brunkhorst I, Löser A (2003) Super-peer-based routing and clustering strategies for rdf-based peer-to-peer networks. In: Proceeding 12th ACM international conference on world wide web, pp 536–543
Pothen A (1997) Graph partitioning algorithms with applications to scientific computing. ICASE LaRC Interdiscip Ser Sci Eng 4:323–368
Ratnasamy S, Francis P, Handley M, Karp R, Shenker S (2001) A scalable content-addressable network. ACM SIGCOMM Comput Commun Rev 31(4):161–172
Saroiu S, Gummadi P, Gribble S (2002) A measurement study of peer-to-peer file sharing systems. In: Proceeding multimedia computing and networking, vol 2002, p 152
Schlosser M, Condie T, Kamvar S (2003) Simulating a file-sharing p2p network. In: Proceeding 1st workshop on semantics in grid and P2P networks
Sripanidkulchai K, Maggs B, Zhang H (2003) Efficient content location using interest-based locality in peer-to-peer systems. In: Proceeding IEEE INFOCOM , vol 3, pp 2166–2176
Stoica I, Morris R, Karger D, Kaashoek M, Balakrishnan H (2001) Chord: A scalable peer-to-peer lookup service for internet applications. ACM SIGCOMM Comput Commun Rev 31(4):149–160
Tirado J, Higuero D, Isaila F, Carretero J, Iamnitchi A (2010) Affinity p2p: A self-organizing content-based locality-aware collaborative peer-to-peer network. Comput Netw 54(12):2056–2070
Tisue S, Wilensky U (2004) Netlogo: A simple environment for modeling complexity. In: Proceeding international conference on complex systems, pp 16–21
Van Den Bout D, Thomas Miller T III (1990) Graph partitioning using annealed neural networks. IEEE Trans Neural Netw 1(2):192–203
Voulgaris S, Kermarrec A, Massoulié L (2004) Exploiting semantic proximity in peer-to-peer content searching. In: Proceeding 10th IEEE international workshop on future trends of distributed computing systems, FTDCS, pp 238–243
Author information
Authors and Affiliations
Corresponding author
Additional information
This research was supported in part by NSF CNS grants 0916179 and 1152320. The game formulation part of the work was presented at the International Workshop on Modeling Analysis and Control of Complex Network (CNET) 2011 at San Fransisco.
Appendix
Appendix
Proof of Theorem 1
We can express \(C_{0}(\mathbf {r})\) as the aggregation of four partial sums: i) cost of peer l itself; ii)sum of costs of peers that belong to super-peer \(k_{1} \) except l; iii) sum of costs of peers that belong to super-peer \(k_{2} \) except l; and iv) sum of costs of those peers that belong neither to super-peer \(k_{1} \) nor to super-peer \(k_{2} \). In the three steps given below, we show that i), ii) and iii) decrease as peer l changes its assignment to minimize its cost (peer-level) while iv) is left unchanged. Thus, \(C_{0}(\textbf {r})\) decreases, contradicting our assumption that \(\hat {\mathbf {r}}\) is the global optimum (minimum) solution of \(C_{0} \). We can divide the objective function as follows:
Thus,
The first term is the cost of peer l, the second term is sum of the costs of the peers that are assigned to the former super-peer of peer l (except peer l), the third term is the sum of the costs of the peers that belong to the prospective super-peer of peer l (except peer l) and the fourth term is the sum of the costs of the peers that belong neither to the current super-peer \(k_{1} \) of peer l nor to the prospective super-peer \(k_{2} \) of peer l.
Let the new assignment vector be \(\textbf {r}^*=(r_{1} ^*,r_{2} ^*,...,r_{N} ^*)\), where \(r_{i} ^*=\hat {r}_{i} \) \(\forall ~i \neq l\).
STEP 1:
By assumption, we know that \(C_{l} (\textbf {r}^*)-C_{l} (\hat {\textbf {r}})<0\).
STEP 2:
We can also deduce that
because this term represents the sum of the change in the cost values of peers which belong to neither of the two super-peers involved in the transfer of peer l.
STEP 3:
Next we show that
First,
Note that the two sets \(\{i:i\neq l,\hat {r}_{i} =\hat {r}_{l} \}\) and \(\{i:i\neq l,r_{i} ^*=\hat {r}_{l} \}\) are equal because all other assignments except \(r_{l} \) are the same in the new assignment vector \(\textbf {r}^*\). Thus,
For \(i \neq l\), \(\{j:r_{j} ^*=\hat {r}_{l} ,j\neq i\}\) represents the set of peers except the lth and ith peer which are currently assigned to \(\hat {r}_{l} {}\)th super-peer and \(\{j:\hat {r}_{j} =\hat {r}_{l} ,j\neq i\}\) represents the set of peers except the lth and ith peer whose new assignment is the \(\hat {r}_{l} {}\)th super-peer. So, for \(i \neq l\), \(\{j:r_{j} ^*=\hat {r}_{l} ,j\neq i\} \setminus \{j:\hat {r}_{j} =\hat {r}_{l} ,j\neq i\} = l \). This implies
Also, \(\{j:r^*_{j} \neq \hat {r}_{l} \} \setminus \{j:\hat {r}_{j} \neq \hat {r}_{l} \} = l\). Thus, we can write
which implies,
Using a similar approach, we can show:
So,
Now consider
We know that,
However,
Thus we see:
But we also know that \(\{i:\hat {r}_{i} =\hat {r}_{l} ,i\neq l\} = \{i:r^*_{i} =\hat {r}_{l} ,i\neq l\}\) and \(\{\hat {r}_{i} = r^*_{l} ,i\neq l\}=\{r^*_{i} = r^*_{l} ,i\neq l\}\). So,
The last step follows from Eq. 13. Thus we have shown:
This completes the proof for STEP 3.
Hence using Steps \(1, 2\) and 3, \(C_{0}(\textbf {r}^*)-C_{0}(\hat {\textbf {r}})= 2\bigl (C_{l} (\textbf {r}^*)-C_{l} (\hat {\textbf {r}})\bigr )< 0\). This contradicts our assumption that \(\hat {\textbf {r}}\) is a globally optimal solution of \(C_{0} \). Hence \(\hat {\textbf {r}}\) is also a Nash equilibrium in pure strategies. □
Rights and permissions
About this article
Cite this article
Kurve, A., Griffin, C., Miller, D.J. et al. Optimizing cluster formation in super-peer networks via local incentive design. Peer-to-Peer Netw. Appl. 8, 1–21 (2015). https://doi.org/10.1007/s12083-013-0206-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12083-013-0206-6