Improve Network Robustness Research Articles

Multi-view depth estimation based on multi-feature aggregation for 3D reconstruction

Robust 3D reconstruction depends critically on the accuracy of depth maps, and multi-view depth estimate is greatly aided by Multi-View Stereo (MVS). Nevertheless, challenges still exist, particularly in accurately estimating depth in regions with low texture and occlusion edges. We introduce MFA-MVSNet, a novel Multi-Feature Aggregation Multi-View Stereo Network that aggregates diverse features in order to address these issues. The Local Feature Extractor (LFE) is incorporated into MFA-MVSNet to adaptively capture local features across various receptive fields. It also incorporates a Multi-feature Fusion Module (MFM) to combine local features with global features extracted by the Global Feature Extractor (GFE). We utilize neural edge information in a CNN-based Depth Refinement Module (DRM) to iteratively filter the depth map to address depth errors in low-textured regions and occlusion edges. To further improve network robustness and training efficiency, we also introduce a Region Perception Loss (RPL) to lessen the impact of both easily matched and mismatched areas. On both the DTU and BlendedMVS datasets, experimental results demonstrate that MFA-MVSNet outperforms recent advanced methods in terms of depth map quality. Additionally, we incorporate MFA-MVSNet into a multi-view 3D reconstruction pipeline, utilizing its depth maps to enhance downstream tasks such as point cloud reconstruction and neural radiance fields (NeRF), leading to improved 3D reconstruction performance.

Enhancing the robustness of interdependent networks by positively correlating a portion of nodes

Cascading failures caused by interdependencies make modern coupled systems extremely fragile to failures. In existing network robustness enhancing methods, maximizing interlayer degree-degree correlations has been proven to be an effective way to improve the robustness of interdependent networks under random failures. Here, we propose a portion of nodes positively correlated strategy (PNC) to improve network robustness by positively correlating a portion of nodes, in which the nodes that are positively correlated are selected in descending order of degree, starting at a cutoff value. Based on percolation theory, we verify the effectiveness of PNC on different networks. And find that, when the nodes with the highest degree are preferentially correlated, i.e. the cutoff value takes the maximum degree, this strategy achieves a state-of-the-art optimization effect. In particular, for interdependent scale-free networks with power-law exponent γ that satisfies 2<γ<3 , we theoretically demonstrate that the highest degree preferentially correlated mode can maximize network robustness by changing the coupling state of the near 0 proportion of nodes. For γ = 3, such a mode can make the network turn into a second-order phase transition at the collapse point. Finally, we discuss the relationship between the robustness of optimized networks and common links in real-world networks.

Robust expansion of networks against cascading failures with reinforcement learning

The network infrastructures, such as the power grids and Internet, are expanding in size due to the increasing needs of our society. This brings about the problem of expanding networks with a guarantee of robustness against network disturbances that may cause catastrophic consequences. In this paper, we study the optimal network expansion in terms of network robustness against cascading failures. Specifically, we consider the network expansion as a Markovian decision process and further propose a reinforcement learning based network expansion method. Simulation results in model networks and real-world networks demonstrate that our expansion method can greatly improve network robustness. Our work provides some insights for the optimal expansion of network infrastructures.

AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection

In this paper, we present a novel Amplitude-Modulated Stochastic Perturbation and Vortex Convolutional Network, AMSP-UOD, designed for underwater object detection. AMSP-UOD specifically addresses the impact of non-ideal imaging factors on detection accuracy in complex underwater environments. To mitigate the influence of noise on object detection performance, we propose AMSP Vortex Convolution (AMSP-VConv) to disrupt the noise distribution, enhance feature extraction capabilities, effectively reduce parameters, and improve network robustness. We design the Feature Association Decoupling Cross Stage Partial (FAD-CSP) module, which strengthens the association of long and short range features, improving the network performance in complex underwater environments. Additionally, our sophisticated post-processing method, based on non-maximum suppression with aspect-ratio similarity thresholds, optimizes detection in dense scenes, such as waterweed and schools of fish, improving object detection accuracy. Extensive experiments on the URPC and RUOD datasets demonstrate that our method outperforms existing state-of-the-art methods in terms of accuracy and noise immunity. AMSP-UOD proposes an innovative solution with the potential for real-world applications. Our code is available at https://github.com/zhoujingchun03/AMSP-UOD.

A mobile node path optimization approach based on Q-learning to defend against cascading failures on static-mobile networks

The research on cascading failures in static networks has become relatively mature, and an increasing number of scholars have started to explore the network scenarios where mobile nodes and static nodes coexist. In order to enhance the resilience of static-mobile networks against cascading failures, an algorithm based on Q-learning for optimizing the path of the mobile node is proposed in this paper. This paper proposes a Q-learning-based algorithm for optimizing the path of the mobile node. To achieve this objective, a cascading failure model is established based on sequential interactions between mobile nodes and static nodes in this study. In this model, the motion paths of the mobile node are generated by the Q-learning algorithm. Based on this approach, extensive experiments are conducted, and the results demonstrate the following findings: 1) By increasing the adjustable load parameters of static nodes in the network, the occurrence of cascading failures is delayed, and the frequency of cascading failures is decreased. 2) Increasing the adjustable load parameter, capacity parameter, and network size of static nodes contributes to the network's resilience against cascading failures. 3) As the communication radius of the mobile node increases, the scale of failures in the static network initially increases and then decreases. 4) Different trajectories of the mobile node have a significant impact on network robustness, and paths generated based on Q-learning algorithm exhibit significantly improved network robustness compared to Gaussian-Markov mobility trajectories. The Q-learning algorithm is compared to the Ant Colony Optimization algorithm in terms of execution time, path length, and network robustness, and the Q-learning algorithm demonstrating favorable performance. These experimental results can be valuable for theoretical research on cascading failures in static-mobile networks.

Robustness paradox of cascading dynamics in interdependent networks

Cascading failure process in interdependent networks has always been an important field of network cascading analysis. Unlike the previous studies, we take people's demand for minimizing travel costs into consideration in this article and propose a network dynamics model based on the cost constraint. On this basis, we pay attention to the characteristics of different layers in the interdependent network, and taking the real-world traffic network for example, we define different load propagation modes for different layers. Then, we carry out the simulation experiment on cascade failure in the artificial network. By changing the structure of the network and the parameters in the model, such as the capability value of the network side and the connectivity of the network, we are able to focus on the effects of traditional protection strategies during the simulation and obtain some interesting conclusions. It is generally believed that increasing the quantity of connections in the network or improving the quality of edges will enhance the network robustness effectively. However, our experimental results show that these methods may actually reduce network robustness in some cases. On the one hand, we find that the resurrection of some special edges in the network is the main reason for the capacity paradox, as these edges will destroy the stable structure of the original network. On the other hand, neither improving the internal connectivity of a single-layer network nor enhancing the coupling strength between interdependent networks will effectively improve network robustness. This is because as the number of edges increases, some critical edges may appear in the network, attracting a large amount of the network load and leading the network robustness to decrease. These conclusions remind us that blindly investing resources in network construction cannot achieve the best protection effect. Only by scientifically designing the network structures and allocating network resources reasonably can the network robustness be effectively improved.

Modelling bus-based substitution capabilities for metro systems using bipartite graphs

Abstract A disruption of metro services can have a negative impact in the performance of a city’s transportation system and hinder mobility needs of travellers. Investigating the vulnerability of metro systems is required for planning mitigation actions, such as bus substitution services. This study develops a model, which consists of a bipartite graph and its projection to represent the bus substitution capabilities for metro networks. The proposed methodology effectively identifies significant substitution elements (bus lines), evaluates the robustness of alternative options in terms of both connectedness and connectivity, and suggests effective strategies for enhancing bus line capacity to improve network robustness. By applying the methodology to a real-world metro network, valuable insights are gained regarding important bus lines and substitution robustness. Study findings suggest that approaches based on the weighted degree exhibit the greatest effectiveness when it comes to connectivity and the overall efficiency of the network. These findings can assist public transport operators in proactively managing disruptions and improving their services.

Robustness of networks with dependency groups considering fluctuating loads and recovery behaviors

Dependency groups describe different characteristics of interactions among nodes, which provide an emerging way to explore the dynamical behaviors of complex networks. To study the effects of dependency groups on the robustness of flow networks, this paper proposes a cascading failure model of networks which combines fluctuating loads and dependency groups. Different from the previous hypothesis that the dependency group is completely invalid once one node in the same dependency group fails, in this paper, the failure and recovery mechanism of dependency groups under certain rules to prevent catastrophic collapses of networks is proposed. To describe the resistance of network to damage caused by cascading failures, we introduce the overload coefficient to characterize the overload state when the node handles excess loads. Considering the network cost should be controlled within a reasonable range while improving network robustness, the cost index based on the relationship between the load and capacity of the node is established. By theoretically analyzing the network cost, the relationship between the network robustness and network cost is discussed when the network cascading process happens. The proposed model is employed to study the dynamics of cascading failures evolution in BA network, ER network and two actual networks. Simulation results reveal the effects of traffic flows and dependency groups on the dynamic loads propagation of cascading failures.

Adding links on minimum degree and longest distance strategies for improving network robustness and efficiency.

Many real-world networks characterized by power-law degree distributions are extremely vulnerable against malicious attacks. Therefore, it is important to obtain effective methods for strengthening the robustness of the existing networks. Previous studies have been discussed some link addition methods for improving the robustness. In particular, two effective strategies for selecting nodes to add links have been proposed: the minimum degree and longest distance strategies. However, it is unclear whether the effects of these strategies on the robustness are independent or not. In this paper, we investigate the contributions of these strategies to improving the robustness by adding links in distinguishing the effects of degrees and distances as much as possible. Through numerical simulation, we find that the robustness is effectively improved by adding links on the minimum degree strategy for both synthetic trees and real networks. As an exception, only when the number of added links is small, the longest distance strategy is the best. Conversely, the robustness is only slightly improved by adding links on the shortest distance strategy in many cases, even combined with the minimum degree strategy. Therefore, enhancing global loops is essential for improving the robustness rather than local loops.

An MAC layer algorithm based on power line-wireless dual media channels and multiplexing

Hybrid networking of power line and wireless communication can complement each other, save construction costs, improve network robustness, and has important value on the Internet of Things and smart grid. For power line and wireless dual-interface devices, a media access control (MAC) layer algorithm for hybrid communication is proposed, in which the stations can compete for two channels simultaneously. When a station obtains two channels at the same time, the station will randomly select a channel for transmission to ensure fairness, and reset the counters when the transmission is successful. In this paper, the performance of the unsaturated traffic model and counter spatial division is considered, and the throughput under coupling conditions is obtained. Finally, the simulation results show that the MAC layer algorithm based on the hybrid communication network can make full use of the advantages of the two channels, improve system throughput, and reduce transmission delay.

Enhancing Robustness and Resilience of Multiplex Networks Against Node-Community Cascading Failures

Many real systems are represented in form of multiplex networks composed of a set of nodes, multiple layers of links, and coupling node relationships across all layers. These systems are very vulnerable to damages during both attacks and recoveries due to potential node cascading failures (NCFs). Although some progress has recently been made in studying network robustness and resilience, the comprehensive impacts of coupling node relationships and community structures on NCFs remain unclear. Accordingly, in this article, we study the robustness and resilience of multiplex networks in the presence of NCFs caused by coupling node relationships and community structures. We first model the failure processes of multiplex networks during both attacks and recoveries as node-community cascading failures (called NCCFs), and then theoretically demonstrate the fragility of multiplex networks to random node damages under NCCFs. Subsequently, to improve network robustness and resilience, we adopt a node protection strategy and propose a cost-aware constrained optimization problem. Finally, we devise a degree-based simulated annealing algorithm for solving this optimization problem. Extensive experiments on both simulated and real multiplex networks show that NCCFs make networks more vulnerable to unpredictable damage than classical NCFs. The results also show the superiority of the proposed algorithm over the state-of-the-art algorithms in improving network robustness and resilience.

Content-Aware Scalable Deep Compressed Sensing

To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality reconstruction. We first adopt a data-driven saliency detector to evaluate the importances of different image regions and propose a saliency-based block ratio aggregation (BRA) strategy for sampling rate allocation. A unified learnable generating matrix is then developed to produce sampling matrix of any CS ratio with an ordered structure. Being equipped with the optimization-inspired recovery subnet guided by saliency information and a multi-block training scheme preventing blocking artifacts, CASNet jointly reconstructs the image blocks sampled at various sampling rates with one single model. To accelerate training convergence and improve network robustness, we propose an SVD-based initialization scheme and a random transformation enhancement (RTE) strategy, which are extensible without introducing extra parameters. All the CASNet components can be combined and learned end-to-end. We further provide a four-stage implementation for evaluation and practical deployments. Experiments demonstrate that CASNet outperforms other CS networks by a large margin, validating the collaboration and mutual supports among its components and strategies.

Learning Discriminative Features by Covering Local Geometric Space for Point Cloud Analysis

At present, effectively aggregating and transferring the local features of point cloud is still an unresolved technological conundrum. In this study, we propose a new space-cover convolutional neural network (SC-CNN) for tasks such as point cloud classification and segmentation. The core of this network is space-cover convolution (SC-Conv), which implements depthwise separable convolution on the point cloud. In addition, a newly designed space-cover operator (SCOP) replaces depthwise convolution. The key to SC-Conv is constructing anisotropic spatial geometry in the local point cloud. The SCOP achieves this by utilizing the positional and feature relationships to learn the high-order relationship expression between points. First, data-driven adaptive learning from the 3-D coordinate relationship between the local points is used to determine the weight of the SCOP. Then, the edge feature of the neighboring point relative to the sampling point is used as the input of the SCOP. Finally, a deformable spatial geometry is constructed in the feature space between local points to aggregate the local high-order features. By stacking SC-Conv to construct SC-CNN with a hierarchical network structure for point cloud analysis, we can better perceive the shape information of point cloud and improve network robustness. Finally, we provide numerous experiments to verify that SC-CNN parallels or even outperforms advanced methods in shape classification, part segmentation, and large-scale indoor scene segmentation tasks. The open-source code was published at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/changshuowang/SC-CNN</uri> .

Ecological Network Analysis of a Virtual Water System in Tibet, China

With the development of the economy and urbanization, the contradiction between water use and supply is growing, and it is necessary to explore the relationship and evolutionary process of water flow in the water system from a systematic perspective. Although previous studies have analyzed the water system from a holistic point of view, a comprehensive system that considers virtual water flows is currently lacking. The present study establishes a seven-compartment virtual water system in Tibet in 2012 by combining ecological network analysis (ENA) with the input–output model. Socio-economic sectors and virtual water flows are expressed as network compartments and pathways. The information-based ENA is used to evaluate the characteristics of the virtual water system in Tibet, including its robustness and trade-offs between network efficiency and redundancy. Network control analysis is introduced to characterize the control and dependence intensities over the system, while ecological relationships between pairwise compartments are calculated using network utility analysis. The results indicate that Tibet’s virtual water system has close to optimal robustness, with higher redundancy and limited efficiency. The agriculture compartment is the main controller, while the energy supply compartment is the most dependent on the virtual water system. The overall systematic relationship that the system has is generally mutualistic and synergistic, the majority of which have a positive relationship, although the control and exploitation relationships are dominant. These results can be used to improve network robustness and are of great significance to the sustainable development of the virtual water system in Tibet.

Mixed strategy for power grid resilience enhancement under cyberattack

ABSTRACT Power infrastructure networks continue to be at risk under natural and anthropogenic hazard events. Cyberattacks targeting power grids aim at magnifying the impacts through damage propagation to other dependent infrastructure network. In this respect, the current study focuses on the “draw-down” phase of power infrastructure network resilience considering different centrality measures to evaluate the robustness of power grids against cyberattacks. The study considers two network representations for the grid based on the network’s topological/connectivity (i.e., unweighted network) and the network’s power flow data (i.e., weighted network). Therefore, the study utilizes the evaluated measures to improve network robustness under cyberattacks, through considering (or not) the proposed mixed strategy. Based on the analyses, network-level vulnerability is quantified considering five different scenarios through evaluating two key performance metrics—Topology and Functionality indices. Nonetheless, applying the proposed mixed strategy to limit the attacker’s access to the network hubs would boost the overall grid robustness.

Identification and Quantification of Node Criticality through EWM\u2013TOPSIS: A Study of Hong Kong\u2019s MTR System

Public transport networks (PTNs) are critical in populated and rapidly densifying cities such as Hong Kong, Beijing, Shanghai, Mumbai, and Tokyo. Public transportation plays an indispensable role in urban resilience with an integrated, complex, and dynamically changeable network structure. Consequently, identifying and quantifying node criticality in complex PTNs is of great practical significance to improve network robustness from damage. Despite the proposition of various node criticality criteria to address this problem, few succeeded in more comprehensive aspects. Therefore, this paper presents an efficient and thorough ranking method, that is, entropy weight method (EWM)–technology for order preference by similarity to an ideal solution (TOPSIS), named EWM–TOPSIS, to evaluate node criticality by taking into account various node features in complex networks. Then we demonstrate it on the Mass Transit Railway (MTR) in Hong Kong by removing and recovering the top k critical nodes in descending order to compare the effectiveness of degree centrality (DC), betweenness centrality (BC), closeness centrality (CC), and the proposed EWM–TOPSIS method. Four evaluation indicators, that is, the frequency of nodes with the same ranking (F), the global network efficiency (E), the size of the largest connected component (LCC), and the average path length (APL), are computed to compare the performance of the four methods and measure network robustness under different designed attack and recovery strategies. The results demonstrate that the EWM–TOPSIS method has more obvious advantages than the others, especially in the early stage.

Rewiring Strategy Based on Directed Betweenness to Mitigate Disruptions of Large-Scale Supply Chain Networks

In current large-scale supply chain networks, unexpected disruptions degrade the supply availability and network connectivity for modern enterprises. How to improve the robustness of supply chain networks is very important for modern enterprises. In this paper, we explore how to improve the robustness of supply chain networks from a topological perspective. Firstly, through the empirical data-driven study, we show that the directed betweenness metric is more suitable than the other topological metrics in evaluating the robustness of supply chain networks. Then, we propose a rewiring algorithm based on directed betweenness to improve network robustness under the impact of disruptions. The experimental results in the large-scale supply chain network show that the rewiring algorithm based on directed betweenness effectively improves the network robustness.

Efficient Identification of Node Importance Based on Agglomeration in Cycle-Related Networks

The identification of node importance in complex networks is of theoretical and practical significance for improving network robustness and invulnerability. In this paper, the importance of each node is evaluated and important nodes are identified in cycles and related networks by node contraction method based on network agglomeration. This novel method considers both the degree and the position of the node for the identifying the importance of the node. The effectiveness and the feasibility of this method was also validated through experiments on different types of complex networks.

Research on channel allocation game algorithm for improving robustness in WSN

In wireless sensor network, robustness is one of the basic network performances, which influences the network lifetime. At the same time, because of the bad environment, the comprehensive failure probability is increased and the cascading failure is caused, which reduces the network robustness. To solve the problem, a failure probability of nodes is described by constructing a model of comprehensive failure according to node energy consumption. Then based on the characteristics of the dynamic changes of variable load, a cascading failure model is proposed. After that, a channel allocation model based on game is constructed by integrating the comprehensive failure probability, cascading failure coefficient, interference and residual energy into utility function to reduce interference and improve network robustness. The theoretical analysis proves the existence of Nash Equilibrium of the channel allocation model. And then, based on the Best Response Dynamics, a game-based channel allocation algorithm for improving robustness with dynamic adjustment is established. The results indicate that the proposed algorithm could converge to Nash Equilibrium. And it has good characteristics of anti-interference, robustness, and so on.

Improving robustness of complex networks by a new capacity allocation strategy

The robustness of infrastructure networks has attracted great attention in recent years. Scholars have studied the robustness of complex networks against cascading failures from different aspects. In this paper, a new capacity allocation strategy is proposed to reduce cascading failures and improve network robustness without changing the network structure. Compared with the typical strategy proposed in Motter–Lai (ML) model, the new strategy can reduce the scale of cascading failure. The new strategy applied in scale-free network is more efficient. In addition, to reasonably evaluate the two strategies, we introduce contribution rate of unit capacity to network robustness as evaluation index. Results show that our new strategy works well, and it is more advantageous in the rational utilization of capacity in scale-free networks. Furthermore, we were surprised to find that the efficient utilization of capacity costs declined as costs rose above a certain threshold, which indicates that it is not wise to restrain cascading failures by increasing capacity costs indefinitely.