Jong Myung Rhee

Issues of Fail-Over Switching for Fault-Tolerant Ethernet Implementation

Fail-over switching is a key factor in approaches to fault-tolerant Ethernet (FTE) implementation. This paper presents some key points in the fail-over switching process of popular two-port FTE. A new algorithm of fail-over switching for multi-ports is then presented. This is based on our new hybrid approach. A simulation tool has been developed to aid identification of fail-over switching time. Recommendations on the selection of the design parameters for FTE implementation are provided. These results can be directly applicable to conventional hardware-based approaches.

An adaptive and reliable data-path determination for Fault-Tolerant Ethernet using heartbeat mechanism

In this paper, we introduce an implementation of the heartbeat mechanism to determine the route (called data-path) for communication between two nodes in a subnet. The data-path is adaptive and reliable in order to keep data flowing in the network continuously even if there are faults in the network. This is a utility for Fault-Tolerant Ethernet (FTE) implementation. Our implementation has been designed and developed as an essential module in a new fault-tolerant, large-scale network scheme called scalable autonomous fault-tolerant Ethernet (SAFE). The SAFE scheme has been developed for use in the combat system data network (CSDN). Our module not only detects the network fault but also provides the information for the fault recovery process. The implementation has been also validated through experiments in various network failure scenarios.

A Novel Dual Separate Paths (DSP) Algorithm Providing Fault-Tolerant Communication for Wireless Sensor Networks

Fault tolerance has long been a major concern for sensor communications in fault-tolerant cyber physical systems (CPSs). Network failure problems often occur in wireless sensor networks (WSNs) due to various factors such as the insufficient power of sensor nodes, the dislocation of sensor nodes, the unstable state of wireless links, and unpredictable environmental interference. Fault tolerance is thus one of the key requirements for data communications in WSN applications. This paper proposes a novel path redundancy-based algorithm, called dual separate paths (DSP), that provides fault-tolerant communication with the improvement of the network traffic performance for WSN applications, such as fault-tolerant CPSs. The proposed DSP algorithm establishes two separate paths between a source and a destination in a network based on the network topology information. These paths are node-disjoint paths and have optimal path distances. Unicast frames are delivered from the source to the destination in the network through the dual paths, providing fault-tolerant communication and reducing redundant unicast traffic for the network. The DSP algorithm can be applied to wired and wireless networks, such as WSNs, to provide seamless fault-tolerant communication for mission-critical and life-critical applications such as fault-tolerant CPSs. The analyzed and simulated results show that the DSP-based approach not only provides fault-tolerant communication, but also improves network traffic performance. For the case study in this paper, when the DSP algorithm was applied to high-availability seamless redundancy (HSR) networks, the proposed DSP-based approach reduced the network traffic by 80% to 88% compared with the standard HSR protocol, thus improving network traffic performance.

A novel ring-based dual paths approach for reducing redundant traffic in HSR networks

In this paper, we propose a novel dual paths-based approach, called ring-based dual paths (RDP), to significantly reduce redundant unicast traffic in high-availability seamless redundancy (HSR) networks. RDP establishes dual paths for forwarding unicast frames between nodes in HSR networks. Unlike existing dual paths-based approaches, such as dual virtual paths (DVP) that establish dual paths for each connection pair of HSR terminal nodes, RDP sets up dual paths for each connection pair of HSR rings. Therefore, RDP significantly reduces the number of established dual paths, which, in turn, reduces the overhead in discovering and establishing dual paths, as well as the memory space required to store these paths compared with the existing dual paths-based approaches. The performance of RDP has been analyzed, evaluated, and compared to that of the standard HSR protocol and the DVP approach. Various simulations were conducted to validate the traffic performance analysis. Analytical and simulation results showed that for the sample networks RDP reduced network unicast traffic by 80-88% compared with the standard HSR protocol, thus freeing up network bandwidth and improving network traffic performance.

Quick removing (QR) approach using cut-through switching mode

We previously introduced a quick removing (QR) approach to improve the high-availability seamless redundancy (HSR) protocols traffic performance. The idea of the QR approach is to remove the duplicated frame copies from the network when all the nodes have received one copy of the sent frame and begin to receive the second copy. Therefore, the forwarding of those frame copies until they reach the source node, as occurs in standard HSR, is not needed in QR. In our earlier paper, we adopted the store and forward switching mode, whereas in this paper, we present the HSR nodes behavior and the QR approach performance using a cut-through switching mode. The performance analysis shows a reduction percentage in frame latency that reaches about 49% compared to the store and forward switching mode. Consequently, this will improve network performance, free more bandwidth, and deliver sent frames quickly to their required destinations, which is a firm condition in many industrial and automation applications.

RSAFE: A Robust Software-based Fault-Tolerant Scheme for Large-scale Ethernet Networks

Most conventional software-based approaches for fault tolerant Ethernet (FTE) adopt a heartbeat mechanism for fault detection. However, due to the tradeoff between the number of nodes and the fault detection time, these conventional approaches do not provide scalability for large-scale networks. To solve this scalability issue, we previously proposed the SAFE scheme, which utilizes multiple subnets architecture. In this paper, we present an upgraded version of the SAFE scheme, the rapid SAFE (RSAFE) scheme, which adopts novel algorithms to significantly decrease the fault detection time while maintaining the advantages of the SAFE scheme. Simulation results using OMNeT++ show that the RSAFE scheme achieves excellent fault detection performance compared to the SAFE scheme. Furthermore, new analytical derivations and discussions of the key advantages of both the SAFE and RSAFE schemes are presented based on the multiple subnets architecture.

A Flexible Methodology of Performance Evaluation for Fault-Tolerant Ethernet Implementation Approaches

In this paper, we propose a flexible methodology which is applicable to performance evaluation for various Fault-Tolerant Ethernet (FTE) implementation approaches including two conventional approaches, the software-based and the hardware-based ones. Then, we present performance analysis results in terms of fail-over time for a redundant Ethernet network device by using our methodology.

A Novel Seamless Redundancy Protocol for Ethernet

High availability is crucial for industrial Ethernet networks and Ethernet-based control systems, such as automation networks and substation automation systems. As standard Ethernet does not support fault tolerance capability, the high availability of Ethernet networks can be increased by using redundancy protocols. In this paper, we present a novel seamless redundancy protocol for Ethernet networks called the Redundancy Protocol for Ethernet (RPE). Our proposed RPE not only provides seamless communications with zero switchover time in case of failure, but it also supports any topologies. The RPE is transparent and compatible with standard Ethernet nodes. These features of the RPE make it very useful for time-critical and mission-critical systems, such as substation automation systems, automation networks, and other industrial Ethernet networks.

LPLB: A Novel Approach for Loop Prevention and Load Balancing in Ethernet Ring Networks

Ethernet networks using rapid spanning tree protocol (RSTP) to ensure a loop-free topology and provide redundant links as backup paths in case an active link has failed. However, when a failure occurs, RSTP requires a significant amount of reconfiguration time in order to find an alternative path. RSTP is also limited by the number of nodes in a ring network, and its performance degrades when the number of nodes increases. In this paper, we introduce a new approach, called loop prevention and load balancing (LPLB), which can be applied to Ethernet ring networks. If failure occurs, LPLB only requires a very short amount of time to switch to an alternative path and in most cases; LPLB needs zero recovery time for that switching. In addition, under most situations, no data frames are lost when a node switches to an alternative path. Unlike RSTP and the media redundancy protocol (MRP), LPLB also provides load balancing among network links that in turn improves the network performance and reduces the probability of bottleneck occurrence.

A Leader Management Scheme for Fault-Tolerant Multiple Subnets

There have been a number of Ethernet-based fault-tolerant schemes which provide fast fault detection and recovery in a subnet environment. However, they are not scalable since Ethernet frame cannot be transmitted to the outside of a subnet. Our SAFE (Scalable Autonomous Fault-tolerant Ethernet) scheme divides whole network into several subnets and manages leader nodes in each subnet. Leader nodes communicate each other for inter-subnet fault recovery. In this paper, we study a fault-tolerant leader management scheme for multiple subnet network. When one of leader nodes fails, the other node will be charged with task of previous leader quickly. Proposed scheme is performing in an autonomous way and network can operate continuously without interruption.