This paper proposes a method to reduce the playback suspension in a Video-on-Demand system based on the Peer-to-Peer technology (P2P VoD). Our main contribution is twofold. The first is the proposal of a hierarchical P2P architecture with the notion of dynamic swarms. Swarm is a group of peers to have similar playback position and those swarms are connected with an overlay so that requested pieces are forwarded from a swarm to another swarm in a bucket brigade manner, where the forward of pieces is regulated by the super-peer (SP) of each swarm. The second contribution is the proposal of a match making scheme between requests and uploaders. The simulation result indicates that the proposed scheme reduces the total waiting time of a randomized scheme by 24% and the load of the media server by 76%.

In this paper, we consider cloud-assisted Peer-to-Peer (P2P) video streaming systems, in which a given video stream is divided into several sub-streams called stripes and those stripes are delivered to all subscribers through different spanning trees of height two, with the aid of cloud upload capacity. We call such a low latency delivery of stripes a 2-hop delivery. This paper proves that if the average upload capacity of the peers equals to the bit rate of the video stream and the video stream is divided into a stripes, then 2-hop delivery of all stripes to n peers is possible if the upload capacity assisted by the cloud is 3n/a. If those peers have a uniform upload capacity, then the amount of cloud assistance necessary for the 2-hop delivery reduces to n/a.

This paper proposes a method to absorb flash crowd in P2P video streaming systems. The idea of the proposed method is to reduce the time before a newly arrived node becoming an uploader by explicitly constructing a group of newly arrived nodes called flash crowd absorber (FCA). FCA grows continuously while serving a video stream to the members of the group, and it is explicitly controlled so that the upload capacity of the nodes is fully utilized and it attains a nearly optimal latency of the stream during a flash crowd. A numerical comparison with a naive tree-based scheme is also given.

In this paper, we propose a new buffer map notification scheme for Peer-to-Peer Video-on-Demand systems (P2P VoDs) which support VCR operations such as fast-forward, fast-backward, and seek. To enhance the fluidity of such VCR operations, we need to refine the size of each piece as small as possible. However, such a refinement significantly degrades the performance of buffer map notification schemes with respect to the overhead, piece availability and the efficiency of resource utilizations. The basic idea behind our proposed scheme is to use a piece-based buffer map with a segment-based buffer map in a complementary manner. The result of simulations indicates that the proposed scheme certainly increases the accuracy of the information on the piece availability in the neighborhood with a sufficiently low cost, which reduces the intermittent waiting time of each peer by more than 40% even under a situation in which 50% of peers conduct the fast-forward operation over a range of 30% of the entire video.

In this paper, we consider a problem of assigning n independent tasks onto m identical processors in such a way that the overall execution time of the tasks will be minimized. Unlike conventional task assignment problem, we assume that the execution time of each task is not fixed in advance, and merely upper and lower bounds of the execution time are given at the compile time. In the following, we first provide a theoretical analysis of several conventional scheduling policies in terms of the worst case slowdown compared with the outcome of an optimal off-line scheduling policy. It is shown that the best known algorithm in the literature achieves a worst case performance ratio of 1 + 1/f(n) where f(n) = O(n2/3) for any fixed m, which approaches to one by increasing n to the infinity. We then propose a new scheme that achieves better worst case ratio of 1 + 1/g(n) where g(n) = Θ (n/log n) for any fixed m, which approaches to one more quickly than previous schemes.

In this paper, we study the problem of efficient processing of conjunctive queries in Peer-to-Peer systems based on Distributed Hash Tables (P2P DHT, for short). The basic idea of our approach is to cache the search result for the queries submitted in the past, and to use them to improve the performance of succeeding query processing. More concretely, we propose to adopt Bloom filters as a concrete implementation of such a result cache rather than a list of items used in many conventional schemes. By taking such an approach, the cache size for each conjunctive query becomes as small as the size of each file index. The performance of the proposed scheme is evaluated by simulation. The result of simulation indicates that the proposed scheme is particularly effective when the size of available memory in each peer is bounded by a small value, and when the number of peers is 100, it reduces the amount of data transmissions of previous schemes by 75%.

In this paper, we propose a new reinforcement learning scheme called CHQ that could efficiently acquire appropriate policies under partially observable Markov decision processes (POMDP) involving probabilistic state transitions, that frequently occurs in multi-agent systems in which each agent independently takes a probabilistic action based on a partial observation of the underlying environment. A key idea of CHQ is to extend the HQ-learning proposed by Wiering et al. in such a way that it could learn the activation order of the MDP subtasks as well as an appropriate policy under each MDP subtask. The goodness of the proposed scheme is experimentally evaluated. The result of experiments implies that it can acquire a deterministic policy with a sufficiently high success rate, even if the given task is POMDP with probabilistic state transitions.

In this paper, we propose a new job scheduling method for distributed parallel systems that can simultaneously achieve two main goals of the job scheduling in those systems: to minimize the execution time of a parallel job without disturbing the execution of the other jobs. We try to achieve those goals by introducing a new scheduler, called active scheduler, that dynamically controls the priority of parallel programs and balances the workload of host computers depending on the status of the underlying runtime environment. We implemented a prototype system of the scheduler to evaluate its effectiveness. The result of experiments implies that the overhead of introducing the active scheduler is at most 15% of the original execution time, and it is in fact effective to adjust the execution of parallel programs to an actual distributed environment in which many users execute their jobs simultaneously.

In this paper, we consider the problem of partitioning a given collection of node sets into k collections such that the average size of collections is the largest, where the size of a collection is defined as the cardinarity of the union of the subsets contained in the collection. More concretely, we give an upper bound on the performance ratio of an approximation algorithm proposed by Abrams et al., which is known to have a performance ratio of at least 1-1/e≅0.6321 where e is Napier's constant. The proposed upper bound is 1-(2-d+1√2)d+1/2 for any d≥1 provided that k=o(n) which approaches to 0.75 as d increases.

Recently Peer-to-Peer Content Delivery Networks (P2P CDNs) have attracted considerable attention as a cost-effective way to disseminate digital contents to paid users in a scalable and dependable manner. However, due to its peer-to-peer nature, it faces threat from “colluders” who paid for the contents but illegally share them with unauthorized peers. This means that the detection of colluders is a crucial task for P2P CDNs to preserve the right of contents holders and paid users. In this paper, we propose two colluder detection schemes for P2P CDNs. The first scheme is based on the reputation collected from all peers participating in the network and the second scheme improves the quality of colluder identification by using a technique which is well known in the field of system level diagnosis. The performance of the schemes is evaluated by simulation. The simulation results indicate that even when 10% of authorized peers are colluders, our schemes identify all colluders without causing misidentifications.

In this paper, we propose a new localization scheme for wireless sensor networks consisting of a huge number of sensor nodes equipped with simple wireless communication devices such as wireless LAN and Bluetooth. The proposed scheme is based on the Point-In-Triangle (PIT) test proposed by He et al. The scheme is actually implemented by using Bluetooth devices of Class 2 standard, and the performance of the scheme is evaluated in an actual environment. The result of experiments indicates that the proposed scheme could realize a localization with an error of less than 2 m.

In this paper, we consider the problem of multicasting a message in k-ary n-cubes under the store-and-forward model. The objective of the problem is to minimize the size of the resultant multicast tree by keeping the distance to each destination over the tree the same as the distance in the original graph. In the following, we first propose an algorithm that grows a multicast tree in a greedy manner, in the sense that for each intermediate vertex of the tree, the outgoing edges of the vertex are selected in a non-increasing order of the number of destinations that can use the edge in a shortest path to the destination. We then evaluate the goodness of the algorithm in terms of the worst case ratio of the size of the generated tree to the size of an optimal tree. It is proved that for any k 5 and n 6, the performnance ratio of the greedy algorithm is c kn - o(n) for some constant 1/12 c 1/2.

In this paper, we propose a method to enhance the download efficiency of BitTorrent protocol with the notion of structures in the set of pieces generated from a shared file and the swarm of peers downloading the same shared file. More specifically, as for the set of pieces, we introduce the notion of super-pieces called clusters, which is aimed to enlarge the granularity of the management of request-and-reply of pieces, and as for the swarm of peers, we organize a clique consisting of several peers with similar upload capacity, to improve the smoothness of the flow of pieces associated with a cluster. As is shown in the simulation results, the proposed extensions significantly reduce the download time of the first 75% of the downloaders, and thereby improve the performance of P2P-assisted video streaming such as Akamai NetSession and BitTorrent DNA.

This paper considers Peer-to-Peer (P2P) video streaming systems, in which a given video stream is divided into b stripes and those stripes are delivered to n peers through b spanning trees under the constraint such that each peer including the source can forward at most b stripes. The delivery of a stripe to n peers is said to be a k-hop delivery if all peers receive the stripe through a path of length at most k. Let Bk=∑i=0k-1bi. It is known that under the above constraint, k-hop delivery of b stripes to n peers is possible only if n≤Bk. This paper proves that (k+1)-hop delivery of b stripes to n peers is possible for any n≤Bk; namely, we can realize the delivery of stripes with a guaranteed latency while it is slightly larger than the minimum latency. In addition, we derive a necessary and sufficient condition on n to enable a k-hop delivery of b stripes for Bk-b+2≤n≤Bk-1; namely for n's close to Bk.

In this paper, we propose a new method to enhance the fault-tolerance of the Content Addressable Network (CAN), which is known as a typical pure P2P system based on the notion of Distributed Hash Table (DHT). The basic idea of the proposed method is to introduce redundancy to the management of index information distributed over the nodes in the given P2P network, by allowing each index to be assigned to several nodes, which was restricted to be one in the original CAN system. To keep the consistency among several copies of indices, we propose an efficient synchronization scheme based on the notion of labels assigned to each copy in a distinct manner. The performance of the proposed scheme is evaluated by simulation. The result of simulations indicates that the proposed scheme significantly enhances the fault-tolerance of the CAN system.

To realize an information-centric networking, IPFS (InterPlanetary File System) generates a unique ContentID for each content by applying a cryptographic hash to the content itself. Although it could improve the security against attacks such as falsification, it makes difficult to realize a similarity search in the framework of IPFS, since the similarity of contents is not reflected in the proximity of ContentIDs. To overcome this issue, we propose a method to apply a locality sensitive hash (LSH) to feature vectors extracted from contents as the key of indexes stored in IPFS. By conducting experiments with 10,000 random points corresponding to stored contents, we found that more than half of randomly given queries return a non-empty result for the similarity search, and yield an accurate result which is outside the σ confidence interval of an ordinary flooding-based method. Note that such a collection of random points corresponds to the worst case scenario for the proposed scheme since the performance of similarity search could improve when points and queries follow an uneven distribution.

In this paper, we consider the problem of constructing a multicast tree in the star graph under the single-port communication model. Unlike previous studies for constructing space-efficient multicast trees, we adopt the completion time of each multicast as the objective function to be minimized. In particular, we study a special case of the problem in which all destination vertices are immediate neighbors of the source vertex, and propose a multicast scheme for the star graph of dimension n in 1.3125log2 n + O(log log n) time units. This running time is at most 1.3125 times of that of an optimal scheme.

In this paper, a new scheme for personalized web page recommendation using multi-user search engine query information is proposed. Our contribution is a scheme that improves the accuracy of personalization for various types of contents (e.g., documents, images and music) without increasing user burden. The proposed scheme combines “preference footprints” for browsed pages with collaborative filtering. We acquire user interest using words that are relevant to queries submitted by users, attach all user interests to a page as a footprint when it is browsed, and evaluate the relevance of web pages in relation to words in footprints. The performance of the scheme is evaluated experimentally. The results indicate that the proposed scheme improves the precision and recall of previous schemes by 1%-24% and 80%-107%, respectively.