Repository logo

Browsing by Author "Yang, Li"

Now showing 1 - 2 of 2
  • Many suspensions, many problems: a review of self-suspending tasks in real-time systems
    Publication . Chen, Jian-Jia; Nelissen, Geoffrey; Huang, Wen-Hung; Yang, Li; Brandenburg, Björn B.; Bletsas, Konstantinos; Liu, Cong; Richard, Pascal; Ridouard, Frédéric; Audsley, Neil; Rajkumar, Raj; Niz, Dionísio de; von der Brüggen, Georg
    In general computing systems, a job (process/task) may suspend itself whilst it is waiting for some activity to complete, e.g., an accelerator to return data. In real-time systems, such self-suspension can cause substantial performance/schedulability degradation. This observation, first made in 1988, has led to the investigation of the impact of self-suspension on timing predictability, and many relevant results have been published since. Unfortunately, as it has recently come to light, a number of the existing results are flawed. To provide a correct platform on which future research can be built, this paper reviews the state of the art in the design and analysis of scheduling algorithms and schedulability tests for self-suspending tasks in real-time systems. We provide (1) a systematic description of how self-suspending tasks can be handled in both soft and hard real-time systems; (2) an explanation of the existing misconceptions and their potential remedies; (3) an assessment of the influence of such flawed analyses on partitioned multiprocessor fixed-priority scheduling when tasks synchronize access to shared resources; and (4) a discussion of the computational complexity of analyses for different self-suspension task models.
    2018Journal article Open access Show more
  • A token-based dynamic scheduled MAC protocol for health monitoring
    Publication . Yuan, Xiaoming; Li, Changle; Yang, Li; Yue, Wenwei; Zhang, Beibei; Ullah, Sana
    Developments of wireless body area networks (WBANs) facilitate the pervasive health monitoring with mHealth applications. WBANs can support continuous health monitoring for the human body in convenience and high efficiency without any intervention. The monitoring data in health care have the characteristics of various data flows and heterogeneous data arrival rates, the transmission of which must be in timeliness and reliability, especially the burst data. Moreover, the energy-constraint nodes should be provident in energy consumption. Designing MAC protocols with high reliability and energy efficiency for WBANs is the prime consideration. In this paper, we propose a token-based two-round reservation MAC (TTR MAC) protocol based on IEEE 802.15.6 with considering the data features of health monitoring. With analyzing the characteristics of monitoring data, one-round reservation is conducted for periodic data and two-round reservation is generated adaptively for burst data to save energy. Besides, TTR MAC protocol assigns appropriate number of allocation slots to nodes in heterogeneous data arrival rates. Furthermore, a token is introduced on the basis of user priority and health severity index to indicate the transmission order of nodes with burst data, which highly decreases the average delay. In addition, a bit sequence scheduled algorithm is proposed for m-periodic (m>1) monitoring data for network capacity expansion. The simulation results show that TTR MAC protocol achieves higher energy efficiency and longer lifetime compared with IEEE 802.15.6 and other one-round reservation MAC (OR MAC) protocols for both 1-periodic and m-periodic data.
    2016Journal article Open access Show more