Neural Network-based Online Fault Diagnosis in Wireless-NoC Systems

Wang, Qi; Ouyang, Yuanxin; Lu, Yingchun; Liang, Hongbin; Zhu, Dakai

doi:10.1007/s10836-021-05966-w

Cited by 4 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trafc fow is the critical information needed to supervise system working conditions. It can be used to support congestion mitigation, faulty node avoidance, and reconfguration mechanism [3][4][5]. Te trafc information can be analyzed in several aspects, e.g., data volume between two communication pairs, wireless packets volume in a certain subnet, and bufer utilization rate in one node.…”

Section: Introductionmentioning

confidence: 99%

Workload-Aware WiNoC Design with Intelligent Reconfigurable Wireless Interface

Wang

Ouyang

Huang

et al. 2023

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

By introducing wireless interfaces in conventional wired routers or hubs, wireless network-on-chip (WiNoC) is proposed to relieve congestion pressure from high volume inter-subnet data transmission. Generally, processing elements on chip receive input data and return feedback through network interface, and data transmission function in Network-on-Chip (NoC) is completed by routers. Hubs equipped with wireless interface are fixed to certain wired routers. While wireless channels may not be fully utilized due to unbalanced workload and constant hub-router connection, e.g., certain nodes processing excess inter-subnet data traffic are far away from hubs. In this paper, we proposed a workload-aware WiNoC design with intelligent reconfigurable wireless interface to improve wireless resources utilization and mitigate congestion. Through multidimensional analysis of traffic flow, a 4-layer neural network is trained offline and applied to analyze workload in each tile, and return three most potential tiles for wireless interface reconfiguration to fully utilize wireless channel and lowing latency. We also implement a historical traffic information-based reconfigurable scheme for comparation. Evaluation results show that in an 8 × 8 hybrid mesh topology, the proposed scheme can achieve 10%–16% reduction in network latency and 5%–11% increment in network throughput compared with fixed-link hub-node connection scheme under several mixed traffic patterns.

show abstract

Section: Introductionmentioning

confidence: 99%

Workload-Aware WiNoC Design with Intelligent Reconfigurable Wireless Interface

Wang

Ouyang

Huang

et al. 2023

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

show abstract

“…The limitation of this approach works only for those nodes that are homogeneous and do not work for the heterogeneous nodes of the network. A fault diagnosis approach based on online neural networks was proposed to detect and locate problematic nodes with permanent problems 43 . This method uses both fully connected and conventional neural networks to locate defect nodes.…”

Section: Classification Of Node Faults In Wsnmentioning

confidence: 99%

“…A fault diagnosis approach based on online neural networks was proposed to detect and locate problematic nodes with permanent problems. 43 This method uses both fully connected and conventional neural networks to locate defect nodes.…”

Section: Machine Learning-based Fault Diagnosis and Classificationmentioning

confidence: 99%

Comprehensive analysis on sensor node fault management schemes in wireless sensor networks

Babu

Kumar

2022

Int J Communication

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) are ad hoc networks that consist of tiny sensor nodes deployed in the sensed environment to monitor the natural phenomenon and send the monitored data to the base station for further processing. Due to the unfriendly deployment of the sensor nodes and their resource-constrained nature, the sensor nodes are subjected to frequent node failure. Detecting sensor node failures and recovering them is a major challenge in WSN. Due to the failure of the nodes in WSN, there exist various problems such as a change in the network topology, communication link failure, a disjoint partition of the network, and failure to transmit the data to the sink. Various authors have proposed various techniques to detect and recover from node failure in the WSN. In this paper, a comprehensive analysis of the various node failure and node recovery techniques has been carried out to highlight the advantages and limitations along with the open research challenges for addressing the failure of the nodes in an effective manner.

show abstract

Dynamic detection of wireless interface faults and fault-tolerant routing algorithm in WiNoC

Ouyang

Chang

et al. 2023

Integration

View full text Add to dashboard Cite

Neural Network-based Online Fault Diagnosis in Wireless-NoC Systems

Cited by 4 publications

References 34 publications

Workload-Aware WiNoC Design with Intelligent Reconfigurable Wireless Interface

Workload-Aware WiNoC Design with Intelligent Reconfigurable Wireless Interface

Comprehensive analysis on sensor node fault management schemes in wireless sensor networks

Dynamic detection of wireless interface faults and fault-tolerant routing algorithm in WiNoC

Contact Info

Product

Resources

About