Abstract High-performance computing utilizes powerful processor clusters to parallel process big data and solve complex problems at extremely high speeds, relying significantly on interconnection networks. As networks grow in scale and complexity, failures become unavoidable. Interconnection networks demand consistent operation and efficient routing algorithms to enable smooth data transmission among processors. Fault-tolerant routing is essential for assessing network reliability. The application of independent spanning trees (ISTs) is an effective method to enhance network fault tolerance. Regarded as a significant extension of the hypercube, the $3$-ary $n$-cube network $(Q^{3}_{n})$ boasts many advantageous such as low vertex degree, regularity, and straightforward implementation. In this paper, we introduce parallel algorithms for generating $2n$ ISTs on $Q^{3}_{n}$, where $2n$ represents the maximum achievable number, enhancing the efficiency and obtaining additional sets of ISTs and disjoint paths. Building upon previously constructed ISTs, a fault-tolerant routing system is developed, utilizing them as the routing table. Subsequently, the effectiveness of this mechanism is assessed through simulated data, showing an increment in transmission success rates as dimensionality grows, nearing near-perfection at almost $100\%$. These results also reveal that the algorithm we proposed demonstrates better performance than traditional classical algorithms.

With the rapid advancement of digital technologies such as cloud computing, big data, and artificial intelligence, large-scale data centers have become critical infrastructure supporting these technologies, imposing increasingly high demands on data center networks (DCNs). Traditional server-centric DCNs face challenges in large-scale distributed systems, such as difficulty in balancing bandwidth and latency, high expansion costs, and conflicts between fault tolerance and communication efficiency. To address these issues, this paper proposes ECQDC, a novel server-centric DCN based on exchanged crossed cube. Specifically, we present its logical structure ECD(s, t) and study the connectivity and edge connectivity of ECD(s, t). Furthermore,we develop efficient fault-free routing algorithm and faulttolerant routing algorithm for the ECD(s, t). The experimental results demonstrate that, compared with Dijkstra and BFS, the proposed ECDR and ECDFTR algorithms reduce the average running time by over 50% and cut the average path length by approximately 20% relative to BFS, while keeping path lengths close to Dijkstra’s optimal performance. Moreover, it exhibits excellent performance in scalability, fault tolerance, and communication efficiency, making it an ideal network topology for large-scale data center deployment.

In the realm of interconnection networks, reliability analysis is of utmost importance, especially considering the increasing vulnerability of components as the network scales. Fault tolerance is a key aspect in this regard, and extra connectivity and component connectivity are two crucial metrics for its assessment. In this paper, we establish a theoretical framework for multi-component fault tolerance in the augmentedk-aryn-cubeAQn,k, a hypercube-derived interconnection network commonly used in distributed-memory architectures. We derive a general result for ther-component connectivity ofAQn,kas$4n(n - 1) - \lfloor{\frac{{5{{(r - 1)}^2}}}{2}}\rfloor$(n≥ 4,k≥ 4, and 2 ≤r≤n). Furthermore, we extend the result to explore theh-extrar-component connectivity ofAQn,kas (8n− 10)(r−1) −2(r−2) (n≥ 4,k≥ 4,h= 1 and 2≤r≤n). Based on these theoretical results, we propose a novel fault-tolerant path algorithm forAQn,kthat handlesh-extrar-component faults. The algorithm first preprocesses and classifies fault-free components, which efficiently determines whether two fault-free nodes belong to the same component, thereby avoiding ineffective path searches. When two fault-free nodes are in the same component, we employ a hybrid greedy-BFS algorithm to construct fault-free paths between them. To validate the algorithm, we conduct comprehensive simulations onAQn,kwith varying parameters. The experimental results demonstrate that the proposed algorithm achieves constant-time path existence queries after preprocessing, significantly reduces path discovery time in multi-query scenarios compared to conventional methods, and maintains near-optimal path lengths while exhibiting superior scalability as network dimensions increase. Furthermore, the algorithm demonstrates robust and highly efficient performance even under fault conditions significantly exceeding theoretical connectivity limits. Additionally, the greedy strategy effectively resolves the vast majority of pathfinding scenarios, confirming its effectiveness underh-extrar-component fault conditions.

With the rapid advancement of big data processing and artificial intelligence (AI), data center networks (DCNs) must deliver more efficient resource management and data transmission mechanisms. Unfortunately, due to the significant differences in bandwidth requirements, transmission patterns, and temporal characteristics across various traffic types in DCNs (such as short flows, long flows, and bursty flows), traditional buffer allocation strategies fail to adapt flexibly to these disparities. In this paper, we propose Enhanced Buffer Management (EBM), a novel buffer-sharing scheme designed for scenarios that require higher performance from DCNs. Unlike prior approaches, EBM employs a multi-level flow identification and adaptive threshold adjustment mechanism to enhance the flexibility and efficiency of buffer management under varying traffic conditions. Specifically, EBM first performs coarse-grained and fine-grained classification of traffic based on packet size, inter-arrival interval, and other flow characteristics. It then applies an improved threshold computation function to allocate buffer space differentially across traffic classes while maintaining allocation smoothness. Our evaluation results demonstrate that EBM significantly improves performance under realistic workloads. For instance, it reduces the 99th percentile Flow Completion Time (FCT) slowdown by 32.7% for short flows in the web-search workload and by 45.1% for incast flows in the hadoop workload, all without sacrificing overall throughput.

Fault diagnosis is crucial for ensuring the reliability of interconnection networks. Traditional diagnostic models usually assume that edges connected to faulty nodes are fault-free, which is unrealistic in practice where both node and edge failures can occur simultaneously. The recently proposed HPMC* diagnostic model provides a more realistic framework by considering both node and edge failures simultaneously, but existing diagnostic approaches under this model have significant limitations in handling complex fault scenarios. This paper proposes HYBRID-GNN, the first graph neural network-based approach for hybrid fault diagnosis under the HPMC* model. HYBRID-GNN employs an edge-enhanced GraphSAGE with comprehensive feature engineering that extracts diagnostic characteristics from HPMC* syndrome data and enables joint training for node and edge fault prediction. HYBRID-GNN learns complex fault patterns from syndrome data, overcoming traditional diagnosability constraints. Experiments on multiple interconnection network topologies show that HYBRID-GNN matches the traditional algorithm in node fault diagnosis (achieving over 99% accuracy within the hybrid diagnosability bound), while delivering substantially higher performance in link fault diagnosis (with accuracy above 97%). Even beyond the diagnosability bound, HYBRID-GNN remains robust, maintaining over 98% node accuracy and over 83% link precision under high fault rates. Furthermore, results on real-world networks further validate its practical effectiveness, achieving over 99% node accuracy and over 95% link accuracy.

The design and optimization of network topologies play a critical role in ensuring the performance and efficiency of high-performance computing (HPC) systems. Traditional topology designs often fall short in satisfying the stringent requirements of HPC environments, particularly with respect to fault tolerance, latency, and bandwidth. To address these limitations, we propose a novel class of hierarchical networks, termed Hypercube-Structured Hierarchical Networks (HHNs). This architecture generalizes and extends existing architectures such as half hypercube networks and complete cubic networks, while also introducing previously unexplored hierarchical designs. HHNs exhibit several advantages, particularly in high-performance computing. Most notably, their high connectivity enables efficient parallel data processing, and their hierarchical structure supports scalability to accommodate growing computational demands. Furthermore, we present a unicast routing strategy and a broadcast algorithm for HHNs. A fault-tolerant algorithm is also designed based on the construction of disjoint paths. Experimental evaluations demonstrate that HHNs consistently outperform mainstream architectures in critical performance metrics, including scalability, latency, and robustness to failures.

The design of interconnection network topologies significantly impacts the performance and reliability of parallel systems. Enhanced incremental scalability enables networks to expand with reduced hardware overhead. In practice, rather than always adding many nodes at once, a small number of nodes are occasionally added as needed. However, existing topologies struggle to achieve effective incremental scalability. To address this, we propose the incremental scalability exchanged hypercube (ISEH), a novel interconnection network for parallel computing. The significant advantages of ISEH include improved incremental scalability and interconnection flexibility, while maintaining low interconnection complexity. Its diameter remains unchanged as the network size increases linearly and does not exceed the diameter of the exchanged hypercube. First, we present the topological properties of ISEH, including isomorphism, incremental scalability, and diameter. Next, we design an efficient communication method for ISEH to ensure low communication overhead. To support reliable communication, we design algorithms to construct disjoint paths between any two distinct nodes. Furthermore, based on generalized exchangedX-cubes, we propose the incremental scalability generalized exchangedX-cubes, offering better incremental scalability. Finally, we compare the performance of ISEH with other interconnection networks and evaluate the proposed algorithms. The results demonstrate that ISEH achieves a favorable balance among incremental scalability, diameter, and flexibility compared to existing networks.

Malicious attackers frequently aim to partition the network into disjointed segments to facilitate specific attacks. Consequently, enhancing network reliability stands as an effective preventive measure. Connectivity serves as a crucial metric for gauging network reliability, yet classical connectivity inadequately captures a network's fault tolerance in the face of such attacks. To address this, cluster connectivity has been proposed, considering the faults within clusters to improve fault tolerance assessment. In this paper, we establish the cluster connectivity of the half hypercube network HHn. In detail, we show that the K1,1-cluster connectivity of HHnis $\left\lfloor {n/2} \right\rfloor + 1$, where n ≥ 3, and the K1,r- cluster connectivity of HHnis $\left\lceil {\frac{{\left\lceil {n/2} \right\rceil }}{2}} \right\rceil + 1$, where n ≥ 5 and 2 ≤ r ≤ 4, which is almost r times the classical connectivity. This indicates that the network possesses an enhanced capacity to accommodate a greater number of faulty nodes, potentially enabling more effective orchestration of attacks.

In the era of information explosion, the scale of data center networks (DCNs) has expanded exponentially, consequently leading to an inevitable increase in server failures. Therefore, how to ensure the efficient and secure operation of the network has emerged as a critically important research topic. WaveCube is a scalable, fault-tolerant, high-performance optical DCN architecture. In this paper, we first propose a local secure model (LS model) of WaveCube. This model segments fault-free nodes within sub-Wavecube by imposing specific constraints, thereby adeptly circumventing potential communication impediments that could arise due to faulty nodes. Secondly, based on this model, we design a protection routing with secure mechanism to ensure stable communication within WaveCube. Finally, we perform a series of experiments, and the results show that when the number of faulty nodes is less than half of the number of total nodes, the hit rate can reach nearly 100%, while the shortest path rate can achieve up to 90%.

Abstract As a kind of conditional connectivity, component connectivity is an improvement of traditional connectivity, which is conducive to enhance the reliability of the network. To be specific, the $r$-component connectivity of a network $G$, written as $c\kappa _{r}(G)$, is defined as the minimum number of all node cuts whose removal causes the remaining network to have at least $r$ components. Component diagnosability, as another measure of network reliability, is usually related to the number of components in the remaining network. The $r$-component diagnosability, written as $ct_{r}(G)$, is defined as the maximum number of faulty sets such that at least $r$ components in the surviving network and all faulty nodes can be diagnosed. This paper mainly explores the relationship between component connectivity and component diagnosability of some regular networks. Once knowing the component connectivity of such a network, with the help of this relationship, we can easily obtain the component diagnosability of the network. Furthermore, we apply this relationship to some famous regular networks to obtain their component diagnosabilities under the PMC model.

With the continuous attention to the parallel computing system, the reliability of the system, which is mainly measured by two parameters, connectivity and diagnosability, needs to be constantly studied and improved. At present, the component connectivities of some networks have been extensively studied, while the component diagnosabilities of these networks have rarely involved in. In this article, some networks with common characteristics are summarized as a class of regular networks. The definition of this kind of networks is given, and its reliability based on component failures is determined. To be specific, we prove that$c\kappa _{m+1}(G)=m(k-1)-\binom{m}{2}+1$for$1\leq m\leq k-2$and$ct_{m+1}(G)=(m+1)k-\binom{m}{2}-2\ m$for$1\leq m\leq k-2$under the PMC model, where$c\kappa _{m+1}(G)$and$ct_{m+1}(G)$represent the$(m+1)$-component connectivity and the$(m+1)$-component diagnosability of such networks$G$, respectively. Based on this, we design a low time complexity component diagnosis algorithm for this kind of networks. As applications, the above two component reliability parameters of many famous networks are explored. Furthermore, the proposed diagnosis algorithm is simulated on these networks, and the results show that the algorithm has high diagnosis accuracy for various networks.

The fault tolerance of a network can be measured by many parameters. Connectivity is a classic measurement parameter for evaluating the fault tolerance of a network. g-extra connectivity and g-restricted connectivity are generalizations of connectivity, which can better reflect the fault tolerance of a network. Specifically, the g-extra connectivity $\kappa_{g}(G)$ of a graph G is the minimum number of nodes whose removal will disconnect G, and each remaining component has no less than $g+1$ nodes. Furthermore, the g-restricted connectivity $\kappa^{g}(G)$ of G is the minimum number of nodes whose deletion results in a graph being disconnected and the minimum degree of each remaining component is at least g. In general, g-restricted connectivity is not equal to g-extra connectivity of a network. Therefore, many scholars often discuss g-restricted connectivity and g-extra connectivity with regard to different networks separately. In this paper, we show that g-restricted connectivity is equal to g-extra connectivity under some conditions. Then, the relationship we derived can be applied to some known networks such as the data center networks DCell and BCDC, multiprocessor network $(n,k)$-star. In addition, we construct a new network $H(G_{0},G_{1},G_{2};\mathbb{M})$ and prove that our result can be applied to it. In detail, we prove $\kappa^{g}(H(G_{0},G_{1},G_{2};\mathbb{M}))=\kappa_{g}(H(G_{0},G_{1},G_{2};\mathbb{M}))=n+g+1$ for any integers $n\geq 3$ and $ g\displaystyle \leq\lfloor\frac{n-2}{2}\rfloor$.

Fault tolerance plays an important role in the interconnection networks, where permanent and intermittent faults are two kinds of fault situations. Permanent fault diagnosabilities of regular networks have been proposed widely while the intermittent fault diagnosabilities are also noteworthy. In this paper, we give a sufficient and necessary condition for k-regular k-connected graph Gn to be ti-diagnosable without repair in intermittent fault pattern. Detailly, we show that the intermittent fault diagnosability of Gn under the PMC model is k−⌈g−12⌉−2⁠, where g is the maximum number of common neighbors for any two distinct vertices. As applications, intermittent fault diagnosabilities of many famous networks are explored.

Muscle thickness is an important parameter used for quantifying musculoskeletal function. At present, the muscle thickness measurement relies on the manual method, which is subjective, time-consuming, and prone to error. In this paper, a novel automatic calculation method was proposed to achieve the continuous and quantitative measurement for the muscle thickness of biceps brachi in ultrasound images. The proposed method includes three steps: the detection and tracking of the seed point in the superficial aponeurosis, the detection and tracking of the feature line in the deep aponeurosis, and the muscle thickness estimation. The performance of the proposed method was firstly compared to the manual measured results, which demonstrates that they have a good agreement during the experiment and can be used for efficiently estimating the muscle thickness of biceps brachi in the musculoskeletal ultrasound images. Then, the validated method was employed to investigate the relationship between the muscle thickness and the joint angle. The results show that, the elbow flexion and extension angle has an approximately linear relationship with muscle thickness change.

Ultrasound (US) imaging is a promising sensing technique in the field of human-machine interface, and many positive results have been reported in literature on hand gesture recognition or finger angle prediction based on US imaging. However, in most of these studies, linear array ultrasound probes were used to generate US images, which made the US device expensive and bulky. In this paper, a method of extracting forearm muscle information via multiple single-element US transducers is proposed. By using this kind of transducers, a low-cost and small-size human-machine interface can be expected. Preliminary results show that an average recognition accuracy of 96% can be achieved for six motions, including five finger flexions and rest state.