嵌入式系统实时任务调度算法与可调度性分析理论研究

"Industrie 4.0" and "Made in China 2025" plans put forward higher demands on real-time task scheduling algorithms and schedulability analysis techniques of embedded system. The real-time task scheduling techniques in embedded system are facing with brand new challenges including stronger real-time, stronger stability and multicore adaptability requirements. Therefore, fast, efficient, stable and multicore adaptability real-time task scheduling algorithms and schedulability analysis techniques have important research values in theory and practices. The core issue of this project is to propose real-time task scheduling algorithms and schedulability analysis techniques for uniprocessor, multicore and mixed-critical systems. The main contents of this project consist of multi-objective task priority assignment algorithms on uniprocessor platforms, real-time task schedulability analysis techniques with low time complexity on uniprocessor platforms, non-preemptive and deferred preemptive partitioned scheduling algorithms on multicore platforms, shared-resource-aware partitioned scheduling algorithms on multicore platforms, schedulability analysis techniques with low time complexity on mixed-critical systems, non-preemptive scheduling algorithms on mixed-critical systems. Our project hopes to gain international reputation with innovation achievements and significantly enhance the competitiveness of our country in a new generation of industrial and information revolution.

“工业4.0”和“中国制造2025”对嵌入式系统实时任务调度算法和可调度性分析理论提出了更高的要求。传统的嵌入式系统实时任务调度技术面临着强实时性、强稳定性和多核适应性等全新的挑战。因此，快速、高效、稳定、多核适应的实时任务调度算法和可调度性分析理论研究具有重要的理论与应用价值。本项目将重点考虑上述因素，以嵌入式系统实时任务调度算法与可调度性分析理论为核心科学问题，研究单核、多核和混合关键系统的实时任务调度算法及可调度分析理论，力争在单核处理器多目标优先级分配算法、低时间复杂度的单核处理器实时任务可调度性分析理论、多核处理器不可抢占和延迟抢占划分调度算法、多核处理器共享资源感知的划分调度算法、低时间复杂度的混合关键系统可调度性分析理论、混合关键系统不可抢占实时任务调度算法等方面取得突破。在国际上形成本领域的研究特色，从而显著增强国家在新一代工业与信息革命中的竞争力。

本项目围绕嵌入式系统实时任务调度算法与可调度性分析理论展开了全面和系统的研究工作，并按照计划完成了全部研究工作。在多目标的单核不可抢占优先级分配算法及可调度性分析、低时间复杂度的不可抢占/延迟抢占优先级分配算法及可调度性分析、多核处理器的不可抢占式/延迟抢占式划分调度算法、多核处理器共享资源感知的划分调度算法等方面取得了预期的研究成果。以上研究成果在国内属于领先水平，部分成果在国际上具有创新性。2017-2020年期间共发表论文38篇，其中SCIE检索29篇（IEEE Transactions 系列5篇，中科院一区5篇，影响因子最高9.936），EI检索6篇。受邀做特邀学术报告5次（国际2次，国内3次），国际学术会议报告3次。申请发明专利5项，其中批准1项，申请4项。培养博士研究生4人，硕士研究生8人。