PROJECT TITLE :

A Cost-Effective Self-Healing Approach for Reliable Hardware Systems - 2018

ABSTRACT:

In this paper, self-healing concept for hardware systems is investigated and a brand new approach is proposed. Hardware systems have been proposing imitations to biological organisms in the method they offer healing and recovery skills. Digital systems with galvanized homogeneous design have improved capabilities to complete any faults. Self-healing is outlined by the ability of a system to detect faults or failures and fix them. One of the most problems in current self-healing approaches is space overhead and scalability for complicated structures considering they are based mostly on redundancy and spare blocks. This paper proposes a different approach for self-healing primarily based on embryonic structures without a would like for spare cells. The realm overhead is lower compared to alternative approaches looking forward to spare cells. The proposed approach depends on time multiplexing 2 functions in one cell among one clock cycle. The reliability of the proposed technique is studied and compared to traditional system with different failure rates. This approach is capable of healing up to fiftypercent of the cells where every cell can cowl another neighbor failed cell at most. The realm overhead is 9p.c for the proposed approach which is much lower compared to alternative approaches using spare cell. The proposed approach is applied to investigate two case studies; ALU array, and neural network.