A proactive approach towards always-on availability in broadband cable networks

In this paper, we propose a high availability design of a Cable Modem Termination System (CMTS) clusters system based on the software rejuvenation technique. This proactive system maintenance technique is aimed to reduce system outages and the associated downtime cost due to the 'software aging' phenomenon. Different rejuvenation policies are studied from the perspectives of design, implementations, and availability assessment. To evaluate these policies, stochastic reward net models are developed and solved by Stochastic Petri Net Package (SPNP). Numerical results show that the deployment of software rejuvenation in the system leads to significant improvement in capacity-oriented availability and reduction in downtime cost. The optimization of the rejuvenation interval in the time-based approach and the effect of the prediction coverage in the measurement-based approach are also studied in this paper.