Networks-on-Chip constitute the interconnection architecture of future, massively parallel multiprocessors that assemble hundreds to thousands of processing cores on a single chip. Their integration is enabled by ongoing miniaturization of chip manufacturing technologies following Moore's Law. It comes with the downside of the circuit elements' increased susceptibility to failure. Research on fault-tolerant Networks-on-Chip tries to mitigate partial failure and its effect on network performance and reliability by exploiting various forms of redundancy at the suitable network layers. The article at hand reviews the failure mechanisms, fault models, diagnosis techniques, and fault-tolerance methods in on-chip networks, and surveys and summarizes the research of the last ten years. It is structured along three communication layers: the data link, the network, and the transport layers. The most important results are summarized and open research problems and challenges are highlighted to guide future research on this topic.

Methods for fault tolerance in networks-on-chip

Compressive sensing (CS) can reduce the number of data transmissions and balance the traffic load throughout networks. However, the total number of transmissions for data collection by using pure CS is still large. The hybrid method of using CS was proposed to reduce the number of transmissions in sensor networks. However, the previous works use the CS method on routing trees. In this paper, we propose a clustering method that uses hybrid CS for sensor networks. The sensor nodes are organized into clusters. Within a cluster, nodes transmit data to cluster head (CH) without using CS. CHs use CS to transmit data to sink. We first propose an analytical model that studies the relationship between the size of clusters and number of transmissions in the hybrid CS method, aiming at finding the optimal size of clusters that can lead to minimum number of transmissions. Then, we propose a centralized clustering algorithm based on the results obtained from the analytical model. Finally, we present a distributed implementation of the clustering method. Extensive simulations confirm that our method can reduce the number of transmissions significantly.

Transmission-Efficient Clustering Method for Wireless Sensor Networks Using Compressive Sensing

Cluster-based routing protocols in wireless sensor networks: A survey based on methodology

Diagnosability of a multiprocessor system is one important study topic in the parallel processing area. As a hypercube variant, the crossed cube has many attractive properties. The diameter, wide diameter and fault diameter of it are all approximately half of those of the hypercube. The power that the crossed cube simulates trees and cycles is stronger than the hypercube. Because of these advantages of the crossed cube, it has attracted much attention from researchers. We show that the n-dimensional crossed cube is n-diagnosable under a major diagnosis model-the comparison diagnosis model proposed by Malek (1980) and Maeng and Malek (1981) if n/spl ges/4. According to this, the polynomial algorithm presented by Sengupta and Dahbura (1992) may be used to diagnose the n-dimensional crossed cube, provided that the number of the faulty nodes in the n-dimensional crossed cube does not exceed n. The conclusion of this paper also indicates that the diagnosability of the n-dimensional crossed cube is the same as that of the n-dimensional hypercube when n>5 and better than that of the n-dimensional hypercube when n=4.

Diagnosability of crossed cubes under the comparison diagnosis model

Unmanned Aerial Vehicles (UAVs) have become increasingly important in assisting 5G and beyond 5G (B5G) mobile networks. Indeed, UAVs have all the potentials to both satisfy the ever-increasing mobile data demands of such mobile networks and provide ubiquitous connectivity to different kinds of wireless devices. However, the UAV assistance paradigm faces a set of crucial issues and challenges. For example, the network management of current UAV-assisted systems is time consuming, complicated, and carried out manually, thus causing a multitude of interoperability issues. To efficiently address all these issues, Software-Defined Network (SDN) and Network Function Virtualization (NFV) are two promising technologies to efficiently manage and improve the UAV assistance for the next generation of mobile networks. In the literature, no clear guidelines are describing the different use cases of SDN and NFV in the context of UAV assistance to terrestrial networks, including mobile networks. Motivated by this fact, in this survey, we guide the reader through a comprehensive discussion of the main characteristics of SDN and NFV technologies. Moreover, we provide a thorough analysis of the different classifications, use cases, and challenges related to UAV-assisted systems. We then discuss SDN/NFV-enabled UAV-assisted systems, along with several case studies and issues, such as the involvement of UAVs in cellular communications, monitoring, and routing, to name a few. We furthermore present a set of open research challenges, high-level insights, and future research directions related to UAV-assisted systems.

/pdf/softwarization-of-uav-networks-a-survey-of-applications-and-45pvurkkbp.pdf

Softwarization of UAV Networks: A Survey of Applications and Future Trends

A. Sengupta and A. Dahbura (1992) discussed how to characterize a diagnosable system under the comparison diagnosis model proposed by J. Maeng and M. Malek (1981) and a polynomial algorithm was given to identify the faulty processors provided that the system's diagnosability is known. However, for a general system, the determination of its diagnosability is not algorithmically easy. This paper proves that, for the important hypercube structured multiprocessor systems (n-cubes), the diagnosability under the comparison model is n when n/spl ges/5. The paper also studies the diagnosability of enhanced hypercube, which is obtained by adding 2/sup n-1/ more links to a regular hypercube of 2/sup n/ processors. It is shown that the augmented communication ability among processors also increases the system's diagnosability under the comparison model. We prove that the diagnosability is n+1 for an enhanced hypercube when n/spl ges/6.

Diagnosability of hypercubes and enhanced hypercubes under the comparison diagnosis model

Structure connectivity and substructure connectivity of hypercubes

An enhanced hypercube is obtained by adding 2/sup n-1/ more links to a regular hypercube of 2/sup n/ processors. It has been shown that enhanced hypercubes have very good improvements over regular hypercubes in many measurements such as mean internode distance, diameter and traffic density. This paper proves that in the aspect of diagnosability, enhanced hypercubes also achieve improvements. Two diagnosis strategies, both using the well-known PMC diagnostic model, are studied: the precise (one-step) strategy proposed by Preparata, Metze and Chien (1967), and the pessimistic strategy proposed by Friedman (1975). Under the precise strategy, the diagnosability is shown to be increased to n+1 in enhanced hypercubes. (In regular hypercubes, the diagnosability is n under this strategy). Under the pessimistic strategy, the diagnosability is shown to be increased to 2n. (In regular hypercubes, the diagnosability under this strategy is 2n-2). Since the failure probability of one node is fairly low nowadays, so that the increase of diagnosability by one or two will considerably enhance the system's self-diagnostic capability, and considering the fact that diagnosability does not "easily" increase as the links in networks do, these improvements are noticeable. >

Diagnosability of enhanced hypercubes

Embedding Hamiltonian Cycles into Folded Hypercubes with Faulty Links

Extra connectivity, diagnosability, and conditional diagnosability are all important measures for a multiprocessor system’s ability to diagnose and tolerate faults. In this paper, we analyze the fault tolerance ability for the alternating group graph, a well-known interconnection network proposed for multiprocessor systems, establish the $h$ -extra connectivity, where $1\le h\le 3$ , and prove that the conditional diagnosability of an $n$ -dimensional alternating group graph, denoted by $AG_n$ , is $8n-27$ ( $n\ge 4$ ) under the PMC model. This is about four times of the $AG_n$ ’s traditional diagnosability. As a byproduct, the strong diagnosability of $AG_n$ is also obtained.

Dajin Wang

Papers

Diagnosability of hypercubes and enhanced hypercubes under the comparison diagnosis model

Structure connectivity and substructure connectivity of hypercubes

Diagnosability of enhanced hypercubes

Embedding Hamiltonian Cycles into Folded Hypercubes with Faulty Links

The Extra Connectivity and Conditional Diagnosability of Alternating Group Networks