Xiaoqian Yu , Changqing Xia , Xi Jin , Chi Xu , Dong Li , Peng Zeng
{"title":"Integrated network-computing resource allocation and optimized scheduling for cyber physical production system","authors":"Xiaoqian Yu , Changqing Xia , Xi Jin , Chi Xu , Dong Li , Peng Zeng","doi":"10.1016/j.adhoc.2025.103831","DOIUrl":null,"url":null,"abstract":"<div><div>Edge computing plays a crucial role in cyber physical production system (CPPS) by connecting the cloud, thereby enhancing system flexibility, intelligence, and agility. However, current scholarly work predominantly focuses on the tight binding of tasks and platforms to meet the real-time and deterministic requirements of CPPS, but does not fully utilize the flexibility and customization characteristics of CPPS. Therefore, there is an urgent need for intelligent and flexible task platform decoupling in the future to meet various quality of service (QoS) requirements such as flexibility, energy consumption and real-time performance, which also brings the challenge of meeting CPPS requirements. To address this issue, this work studies the decoupled flexible manufacturing dynamical scheduling problem with the aim of jointly optimizing real-time performance and energy consumption. Firstly, a multi-priority feedback queue is designed, which can dynamic adjust priority to ensure real-time performance of tasks. Subsequently, multi-objective optimization models are used to allocate network and computing resources for tasks, taking system latency and energy consumption into account as costs. To narrow the solution space and improve solving speed, a locally optimal resource allocation method is derived. Furthermore, scheduling algorithms for the end-side and edge-side are designed separately. On one hand, considering the energy sensitivity of edge devices, a lightweight scheduling algorithm called terminal double deep Q network (T-DDQN) has been proposed to quickly determine the optimal task execution location. On the other hand, a task offloading strategy named game theory edge device-level task offloading (GTETO) has been introduced to address the load imbalance issues at the edge caused by T-DDQN. Compared to existing algorithms, it can reduce system cost by up to 25.26%, and improve resource utilization of edge devices by 8.34–27.77%.</div></div>","PeriodicalId":55555,"journal":{"name":"Ad Hoc Networks","volume":"173 ","pages":"Article 103831"},"PeriodicalIF":4.4000,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ad Hoc Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1570870525000794","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Edge computing plays a crucial role in cyber physical production system (CPPS) by connecting the cloud, thereby enhancing system flexibility, intelligence, and agility. However, current scholarly work predominantly focuses on the tight binding of tasks and platforms to meet the real-time and deterministic requirements of CPPS, but does not fully utilize the flexibility and customization characteristics of CPPS. Therefore, there is an urgent need for intelligent and flexible task platform decoupling in the future to meet various quality of service (QoS) requirements such as flexibility, energy consumption and real-time performance, which also brings the challenge of meeting CPPS requirements. To address this issue, this work studies the decoupled flexible manufacturing dynamical scheduling problem with the aim of jointly optimizing real-time performance and energy consumption. Firstly, a multi-priority feedback queue is designed, which can dynamic adjust priority to ensure real-time performance of tasks. Subsequently, multi-objective optimization models are used to allocate network and computing resources for tasks, taking system latency and energy consumption into account as costs. To narrow the solution space and improve solving speed, a locally optimal resource allocation method is derived. Furthermore, scheduling algorithms for the end-side and edge-side are designed separately. On one hand, considering the energy sensitivity of edge devices, a lightweight scheduling algorithm called terminal double deep Q network (T-DDQN) has been proposed to quickly determine the optimal task execution location. On the other hand, a task offloading strategy named game theory edge device-level task offloading (GTETO) has been introduced to address the load imbalance issues at the edge caused by T-DDQN. Compared to existing algorithms, it can reduce system cost by up to 25.26%, and improve resource utilization of edge devices by 8.34–27.77%.
期刊介绍:
The Ad Hoc Networks is an international and archival journal providing a publication vehicle for complete coverage of all topics of interest to those involved in ad hoc and sensor networking areas. The Ad Hoc Networks considers original, high quality and unpublished contributions addressing all aspects of ad hoc and sensor networks. Specific areas of interest include, but are not limited to:
Mobile and Wireless Ad Hoc Networks
Sensor Networks
Wireless Local and Personal Area Networks
Home Networks
Ad Hoc Networks of Autonomous Intelligent Systems
Novel Architectures for Ad Hoc and Sensor Networks
Self-organizing Network Architectures and Protocols
Transport Layer Protocols
Routing protocols (unicast, multicast, geocast, etc.)
Media Access Control Techniques
Error Control Schemes
Power-Aware, Low-Power and Energy-Efficient Designs
Synchronization and Scheduling Issues
Mobility Management
Mobility-Tolerant Communication Protocols
Location Tracking and Location-based Services
Resource and Information Management
Security and Fault-Tolerance Issues
Hardware and Software Platforms, Systems, and Testbeds
Experimental and Prototype Results
Quality-of-Service Issues
Cross-Layer Interactions
Scalability Issues
Performance Analysis and Simulation of Protocols.