Thermal Aware Lifetime Reliability Optimization for Automotive Distributed Computing Applications

Abstract

As the automotive industry is moving towards electric and self-driving vehicles, how to ensure the high degree of reliability for electronic control systems (ECS) has emerged as a serious concern. Temperature plays a vital role in the reliability of ECS because vehicles are subjected to high chip temperature due to harsh operating conditions and high integrated circuit (IC) on-chip power density. In this paper, we study the problem on how to optimize the lifetime reliability and guarantee the chip's peak temperature of ECS by judiciously allocating the application to ECS. We first propose a simple mathematical programming based thermal aware approach, assuming temperature can reach a stable status immediately. We then present a genetic algorithm approach based on effective and computationally efficient methods for peak temperature identification and system-wide lifetime reliability calculation, by taking advantage of the periodicity of vehicle applications. Our experimental results, based on both synthetic test cases and practical benchmarks demonstrate the significant improvement in lifetime reliability and CPU time for automotive ECS achieved by our proposed algorithms compared to the state-of-the-art results.