Fault localisation and recovery in multichannel ATM switches

One of the important advantages of multichannel switches is the incorporation of inherent fault tolerance into the switching fabric. For example, if a link which belongs to the multichannel group fails, the remaining links can assume responsibility for some of the traffic on the failed link. On the other hand, faults occurring in the switching elements can lead to erroneous routing and sequencing in the multichannel switch. The authors investigate several fault localisation algorithms in multichannel crossbar ATM switches with a view to early fault recovery. The optimal algorithm gives the best performance in terms of time to localisation but is computationally complex, which makes it difficult to implement. The authors develop an online algorithm which is computationally more efficient than the optimal algorithm. They evaluate its performance through simulation. The simulation results show that performance of the online algorithm is only slightly sub-optimal for both random and bursty traffic. Finally, a fault recovery algorithm is described which utilises the information provided by the fault localisation algorithm. The fault recovery algorithm provides additional rows and columns to allow cells to be routed around the faulty element.