China
Africa
Explore chapters and articles related to this topic
A hierarchical priority task scheduling with QoS satisfaction for cloud storage
Published in Amir Hussain, Mirjana Ivanovic, Electronics, Communications and Networks IV, 2015
Qingying Lin, Yuelong Zhao, Wei Chen, Ping Zhong
In this paper, a hierarchical priority task scheduling strategy with QoS satisfaction for cloud storage is proposed. In metadata server layer, a priority task scheduling is used based on Earliest Deadline First (EDF) algorithm to satisfy the delay time requirement of users. In data storage server layer, a Multilevel Queue Scheduling (MQS) algorithm is used to satisfy transmission bandwidth requirements of different levels for users. At the same time, QoS-aware load balancing strategy is used to ensure the quality of service with the highest level of the users. The experimental results show that the strategy can achieve good performance and satisfy the different QoS requirements of users.
A cross-layer design: energy efficient multilevel dynamic feedback scheduling in wireless sensor networks using deadline aware active time quantum for environmental monitoring
Published in International Journal of Electronics, 2019
Mahendran Natarajan, Shankar Subramanian
Nidal et al. (Nasser et al., 2013) suggested a scheme called Dynamic Multilevel Priority packet scheduling for WSN, it works based on zone-based routing protocol and Time Division Multiple Access (TDMA) methodologies. In zone- routing, the sensor nodes arranged in a hierarchical structure based on hop distance from a source node. When the nodes have same hop distance placed in the same hierarchical level. The variable length time slot scheme named as TDMA process and forwards the packets from lower level to a base station through intermediate levels. In DMP, the sensor nodes classify the queue into three different priorities such as high-level priority queue (queue 1) stores real-time data, middle-level priority queue (queue 2) has non-real-time remote data, lower level priority (queue 3) stores non-real time data from node itself. FCFS scheme process the real-time data to reduce the delay. The queue 3 data packets are achieving fairness by pre-empting queue 1 data packets when the queue 3 data packets wait a number of consecutive time slots. It provides better performance than multilevel queue scheduling and FCFS but more resources allocated to higher priority packet processing leads to deadlock.
Two-level priority scheduling framework in a max-plus linear representation
Published in SICE Journal of Control, Measurement, and System Integration, 2021
Kyohei Sagawa, Yoichi Shimakawa, Hiroyuki Goto
Event counter is a key variable in MPL systems to identify the job sequence, for which order change of jobs has not been a central concern in potential applications. In some practical systems, however, such change is structurally possible and can improve the entire system's performance. Thus a new MPL-based methodology that accounts for order change need to be developed. Once a formal method is constructed, generalization is achieved by which the potential applications might range from railway scheduling to computer science, e.g. multilevel queue CPU scheduling.