Sharif Digital Repository

Use of deep sub-micron VLSI technologies in fabrication of Network on Chips (NoCs) makes the reliability to be one of the first order concerns in the design of these products. This paper proposes and evaluates a methodology that adds reliability to NoC routing algorithms with minimal power and performance overheads. The key idea behind this methodology is to use the concept of complement routing in which two routing algorithms with disjoint sets of allowed turns are incorporated. According to this methodology, while a packet is routed by a routing algorithm, a redundant copy of that packet is routed by the complement of that routing algorithm. This is done by exploiting channels with lower... 

Power consumption, performance and reliability are the most important parameters in modern safety-critical distributed real-time embedded systems. This paper evaluates and compares different schedulability conditions in faulttolerant Rate-Monotonic (RM) and Earliest-Deadline-First (EDF) algorithms, with respect to their power efficiency. The primary-backup scheme is used to implement fault tolerance in the algorithms. To evaluate the algorithms, a software tool is developed that can simulate an embedded system consisting of n processors and m periodic tasks. The results show that depending on the different schedulability conditions, the EDF algorithm implemented with the Best-Fit policy is... 

Today, peer-to-peer networks are become more popular among internet users and more than millions peers share high volume of data from anywhere. Sending and receiving these data increase the network traffics terribly. By improving the performance of these networks not only the efficiency of these networks increase but also the overall performance of the internet augments. To achieve high performance and resilience to failures, a peer can make connections with those other peers that are geographically closer to it. There are many solutions that are suggested for locality problem. In this paper, we suggest a Cube Connected Cycle as an overlay network to improve locality with higher performance  

Effectiveness of Peer-to-Peer (P2P) systems highly depends on efficiency and scalability of their search algorithms. Moreover, managing trust is a key issue for wide acceptance of P2P computing. Surprisingly, the majority of the available trust systems ignore the underlying search algorithm and assume it is preexisting. We claim that combining search and trust systems yields significant performance gains in terms of network traffic and query success rate. In this paper, we propose a robust and efficient trust based search framework for unstructured P2P networks. Our framework maintains limited size routing indexes combining search and trust data to guide queries to most reputable nodes. By... 

Today, peer-to-peer networks are become more popular among internet users and more than millions peers share high volume of data from anywhere. Sending and receiving these data increase the network traffics terribly. By improving the performance of these networks not only the efficiency of these networks increase but also the overall performance of the internet augments. To achieve high performance and resilience to failures, a peer can make connections with those other peers that are geographically closer to it. In this paper, we present a novel mechanism for placing peers on the overlay network, which supports locality without increasing network traffic seriously  

This paper presents a new balanced, distributed data structure for storing data with multidimensional keys in a peer-to-peer network. It supports range queries as well as single point queries which are routed in O (log n) hops. Our structure, called SkipTree, is fully decentralized with each node being connected to O (log n) other nodes. We propose modifications to the structures, so that the memory usage for maintaining the link structure at each node is reduced from the worst case of O (n) to O (log n log log n) on the average and O (log2 n) in the worst case. It is also shown that the load balancing is guaranteed to be within a constant factor. Our experimental results verify our... 

The severity of timing delay in the communication channels of Network on Chip (NoC) depends on the transition patterns appearing on the wires. An analytical model can estimate the timing delay in NoC channels in the presence of crosstalk faults. However, recently proposed analytical model does not have enough accuracy and is based on 3-wire delay model. In this paper, an Accurate Crosstalk Model (ACM) based on 5-wire delay model is proposed to estimate the delay of communication channels in the presence of crosstalk faults. ACM is more accurate due to considering more wires in the delay model and also considering the overlaps between locations of transition patterns  

In future smart grids, energy storage systems (EESs) and demand response (DR) are expected to have an important role in balancing load changes arising from life-style of consumers and varying output of some renewable energy resources. However, activating DR and installing ESSs need huge investment forcing system owner to justify their effectiveness prior to any implementation. This paper presents a model to find the optimal capacity of EESs in distribution systems with demand responding to electricity price changes. The model aims at maximizing system owner profit by lessening total electricity provision costs. The model is formulated as a mixed integer non-linear programming problem. Due to... 

Online Social Networks (OSNs) have become widely popular in recent years. In spite of users' interest to join OSNs, sharing vast amounts of personal information and resources in these networks might result in privacy issues for them. In the centralized OSNs, access control policies defined by users are enforced by OSN providers. Moreover, as these shared resources are stored by providers, they can access them. To avoid such problems, various architectures for decentralized OSNs are proposed. But the proposed architectures for P2P OSNs yet do not support any mechanism for collaborative privacy management on the shared content. By increasing the amount of resources such as photos which is... 

Wireless sensor networks (WSNs) usually consist of many tiny sensor nodes and a Sink. Problems like nodes' misbehavior due to malicious, compromised or selfishness intentions, and WSNs' security vulnerabilities against different attacks due to free and unprotected communications, untrusted and broadcasted transmissions, hostile environments and limited resources, degrade the security and overall performance of WSNs. In another direction, most of the traditional security mechanisms are unsuitable for WSNs. One significant security solution against these problems is Trust Management System (TMS); TMS enhances the security by detecting the nodes' abnormal behaviors; it improves the cooperation... 

Topology is widely known as the most important characteristic of networks-on-chip (NoC), since it highly affects overall network performance, cost, and power consumption. In this paper, we propose a reconfigurable architecture and design flow for NoCs on which a customized topology for any target application can be implemented. In this structure, the nodes are grouped into some clusters interconnected by a reconfigurable communication infrastructure. The nodes inside a cluster are connected by a mesh to benefit from the interesting characteristics of the mesh topology, i.e. regular structure and efficient handling of local traffic. A reconfigurable inter-cluster topology then eliminates the... 

The peer to peer (P2P) file sharing applications have allocated a significant amount of today's Internet traffic. Among various P2P file sharing protocols, BitTorrent is the most common and popular one that attracts monthly a quarter of a billion users from all over the world. Similar to other P2P file sharing protocols, BitTorrent is mostly used for illegal sharing of copiright protected files such as movies, music and TV series. To impede this huge amount of illegal file distributions, anti-P2P companies have arisen to stand against these applications (specially the BitTorrent). To this end, they have begun to fire large-scale Internet attacks against BitTorrent networks. In this paper, we... 

Maximum independent set problem is an NP-Hard one with the aim of finding the set of independent vertices with maximum possible cardinality in a graph. In this paper, we investigate a learning automaton based algorithm that finds a maximum independent set in the graph. Initially, a learning automaton is assigned to each vertex of graph. In order to find candidate independent set, a set of distributed learning automata collaborate with each other. The proposed algorithm based on learning automata is guided iteratively to the maximum independent set by updating the action probability vector. In order to study the performance of the proposed algorithm, we conducted some experiments. The... 

During the last years, researchers have proposed solutions to help smartphones offload heavy tasks to remote entities in order to improve execution time and reduce energy consumption. Lately, inspired by the promising results of message forwarding in opportunistic networks, many researchers have proposed strategies for task offloading towards nearby mobile devices. None of these strategies, though, proposes any mechanism that considers selfish users and, most importantly, that motivates and defrays the participating devices who spend their resources. In this paper, we address these problems and propose the design of a framework that integrates an incentive scheme and a reputation mechanism.... 

In this paper, motivated by network inference, we introduce a general framework, called LSR-Weighted, to efficiently recover sparse characteristic of links in weighted networks. The links in many real-world networks are not only binary entities, either present or not, but rather have associated weights that record their strengths relative to one another. Such models are generally described in terms of weighted networks. The LSR-Weighted framework uses a newly emerged paradigm in sparse signal recovery named compressive sensing. We study the problem of recovering sparse link vectors with network topological constraints over weighted networks. We evaluate performance of the proposed framework... 

Predicting latency between nodes on the internet can have a significant impact on the performance of many services that use latency distances among nodes as a decision making input. Coordinate-based approaches are among the family of latency prediction techniques where latency between each pair of nodes is modeled as the virtual distance among those nodes over a virtual system. This article proposes the Decentralized Coordinate System (DCS) as a fully distributed system that does not rely on any infrastructure support from the underlying network. DCS uses a two-phase algorithm: first, each host is assigned rough coordinates, then, the rough estimation is refined in a way that it gradually... 

In software systems development lifecycle making use of software architecture, especially by taking advantage of architecture styles and patterns, is an essential part which increases product's quality. Nowadays, in order to cover complexity of systems, combination of different architecture styles should be used; therefore ambiguous behaviors might occur. Hence, due to the critical need for toolsets capable of selecting suitable styles and patterns, an environment is proposed in this paper which can perfectly cover different aspects of the implementation of decision support system (DSS). The designed environment obviates data implementation concepts and security considerations. Moreover, it... 

In the past few years, the study of complex networks has attracted the attention of researchers. Many real networks, ranging from technological networks such as the Internet to biological networks, have been considered as special types of complex networks. Through application of the network science, important structural properties of such networks have been analyzed and the mechanisms that form such characteristics have been introduced. In this paper, we address the structural characteristics of a technological network called Vehicular Ad hoc Networks (VANETs). Recent studies reveal that the communication graph of VANETs has some interesting characteristics including: the Gaussian degree... 

We consider load balancing in a network of caching servers delivering contents to end users. Randomized load balancing via the so-called power of two choices is a well-known approach in parallel and distributed systems. In this framework, we investigate the tension between storage resources, communication cost, and load balancing performance. To this end, we propose a randomized load balancing scheme which simultaneously considers cache size limitation and proximity in the server redirection process. IEEE  

Cloud manufacturing is an emerging service-oriented manufacturing paradigm that integrates and manages distributed manufacturing resources through which complex manufacturing demands with a high degree of customization can be fulfilled. The process of service selection optimization and scheduling (SSOS) is an important issue for practical implementation of cloud manufacturing. In this paper, we propose new mixed-integer programming (MIP) models for solving the SSOS problem with basic composition structures (i.e., sequential, parallel, loop, and selective). Through incorporation of the proposed MIP models, the SSOS with a mixed composition structure can be tackled. As transportation is...