QoE-oriented Dependent Task Scheduling under Multi-dimensional QoS Constraints over Distributed Networks

TL;DR

The paper addresses scheduling multiple dependent tasks in distributed networks under multi-dimensional QoS constraints, proposing a QoE cost model that captures latency and data accuracy with hard/soft thresholds and application preferences. It proves the QoE optimization is NP-hard and introduces the Hierarchical Multi-queue Task Scheduling Algorithm (HMTSA), which uses hierarchical queues and dynamic prioritization to select task execution order and placement. The approach demonstrates substantial QoE gains over baseline methods across varying numbers of applications, network configurations, and QoS sensitivities, validated through extensive simulations. The work advances practical resource allocation for beyond-communication services by jointly considering computing, communication, and user experience in a scalable, multi-hop setting.

Abstract

Task scheduling as an effective strategy can improve application performance on computing resource-limited devices over distributed networks. However, existing evaluation mechanisms fail to depict the complexity of diverse applications, which involve dependencies among tasks, computing resource requirements, and multi-dimensional quality of service (QoS) constraints. Furthermore, traditional QoS-oriented task scheduling strategies struggle to meet the performance requirements without considering differences in satisfaction and acceptance of application, leading application failures and resource wastage. To tackle these issues, a quality of experience (QoE) cost model is designed to evaluate application completion, depicting the relationship among application satisfaction, communications, and computing resources in the distributed networks. Specifically, considering the sensitivity and preference of QoS, we model the different dimensional QoS degradation cost functions for dependent tasks, which are then integrated into the QoE cost model. Based on the QoE model, the dependent task scheduling problem is formulated as the minimization of overall QoE cost, aiming to improve the application performance in the distributed networks, which is proven Np-hard. Moreover, a heuristic Hierarchical Multi-queue Task Scheduling Algorithm (HMTSA) is proposed to address the QoE-oriented task scheduling problem among multiple dependent tasks, which utilizes hierarchical multiple queues to determine the optimal task execution order and location according to different dimensional QoS priorities. Finally, extensive experiments demonstrate that the proposed algorithm can significantly improve the satisfaction of applications.

Figures (8)

• Figure 1: The diagram of system model and dependent task scheduling in distributed network.
• Figure 2: The example of QoS cost function, where $B_d(t)$ and $B_e(t)$ are equal to 5. From the perspective of latency, the x-axis represents latency in seconds, and from the data accuracy perspective, the x-axis represents data error rates.
• Figure 3: Illustritive diagram of HMTSA.
• Figure 4: Simulation scenario.
• Figure 5: Impact of number of application. (a) Average completion time versus the number of application. (b) Deadline compliance ratio versus the number of application. (c) Accuracy compliance ratio versus the number of application. (d) Average latency cost versus the number of application. (e) Average accuracy cost versus the number of application. (f) Average QoE cost versus the number of application.