Equal-cost multi-path routing

About: Equal-cost multi-path routing is a research topic. Over the lifetime, 10472 publications have been published within this topic receiving 249362 citations.

On deadlocks in interconnection networks

Abstract: Deadlock avoidance-based and deadlock recovery-based routing algorithms have been proposed in recent years without full understanding of the likelihood and characteristics of actual deadlocks in interconnection networks. This work models the interrelationships between routing freedom, message blocking, correlated resource dependencies and deadlock formation. We empirically show that increasing routing freedom, as achieved by allowing unrestricted routing over multiple virtual channels, makes deadlocks highly improbable and reduces the likelihood of other types of correlated message blocking behavior that can degrade performance. Our results further substantiate that recovery-based routing algorithms have a higher potential performance advantage over deadlock avoidance-based routing algorithms which, inherently, allow less routing freedom.

Including artificial intelligence in a routing protocol using Software Defined Networks

Abstract: Software defined network (SDN) is one of the most interesting research topic that is currently being investigated. The inclusion of artificial intelligence (AI) can improve the performance of routing protocols. Nowadays the application of AI over routing protocols is only applied to real devices, especially in wireless sensor nodes. In this paper, we present a new proposal to implement an intelligent routing protocol in a SDN topology. The intelligent routing protocol is based on the reinforcement learning process that allows choosing the best data transmission paths according to the best criteria and based on the network status.

Hop-by-hop routing algorithms for premium-class traffic in DiffServ networks

Abstract: For the provision of quality of service (QoS) in the Internet, differentiated service (DiffServ) has been proposed as a cost-effective solution. Traffic is classified into several service classes with different priorities, premium class traffic being the highest. The routing algorithm used by the premium class service has significant effects on the traffic of all other classes as well as its own. Shortest hop-count routing used in the current Internet is no longer sufficient in DiffServ networks. Based on hop-by-hop routing, an optimal routing algorithm must be found for premium class traffic such that (1) it works correctly and efficiently for premium traffic; (2) it reduces negative influences (such as bandwidth starvation, excessive delay jitter, etc.) to other traffic classes. This problem, the optimal premium-class routing (OPR) problem, is NP-complete. To handle the OPR problem, first, we analyze the strength and weaknesses of two existing algorithms (widest-shortest-path algorithm and bandwidth-inversion shortest-path algorithm). Second, we apply to the OPR problem a novel heuristic algorithm, called the enhanced bandwidth-inversion shortest-path (EBSP) algorithm. We prove theoretically the correctness of the EBSP algorithm, i.e., it is a consistent and loop-free hop-by-hop routing algorithm. Our extensive simulations in different network environments show clearly that the EBSP algorithm performs better for premium class traffic in complex, heterogeneous networks than the other two hop-by-hop routing algorithms.

Efficient fully adaptive wormhole routing in n-dimensional meshes

Abstract: An efficient fully adaptive wormhole routing algorithm for n-dimensional meshes is developed. The routing algorithm provides full adaptivity at a cost of one additional virtual channel per physical channel irrespective of the number of dimensions of the network. The algorithm is based on dividing the network graph into two acyclic graphs that contain all of the physical channels in the system. Virtual channels are classified as either waiting or nonwaiting channels. Busy channels that a message waits for to become available are classified as waiting channels, otherwise they are classified as nonwaiting channels. Thus, a message considers nonwaiting channels first to reach its destination. If all non-waiting channels are busy, the message considers waiting channels. Messages acquire waiting channels in two phases. In each phase, waiting channels belonging to one acyclic network graph are traversed. This 2-phase routing algorithm could be either minimal or nonminimal. However, we concentrate on minimal routing. It is demonstrated that this adaptive routing algorithm can utilize the virtual paths (channels) between any two nodes more efficiently than any of the present algorithms with the same hardware requirement. >

Optimal forwarder list selection in opportunistic routing

Abstract: Unlike traditional wireless routing protocols which use a single fixed path, opportunistic routing explicitly takes advantage of the broadcast nature of wireless communications by using a set of forwarders to opportunistically perform packet forwarding. A key issue in the design of opportunistic routing protocols is the forwarder list selection problem. In this paper we establish a general theory for analyzing the forwarder list selection problem, and develop an optimal solution, the minimum transmission selection (MTS) algorithm, which minimizes the expected number of transmissions and it can be incorporated into existing opportunistic routing protocols to select optimal forwarder lists. Our theory and algorithm can also be generalized to optimize other routing objectives such as minimizing the expected transmission time or energy consumption in opportunistic routing. Through extensive simulations, we demonstrate that in more than 90% cases the MTS algorithm outperforms the ETX forwarder selection scheme used in existing opportunistic routing protocols such as ExOR and MORE.