Networks Of Different Sizes Research Articles

Enabling Proportionally-Fair Mobility Management With Reinforcement Learning in 5G Networks

Mobility management in 5G is challenging, and at higher frequencies, a larger number of cells is needed to provide similar coverage to that in 4G. Consequently, Base Stations (BSs) are placed much more densely and users experience frequent handovers, reducing network capacity. Advanced handover techniques are needed in 5G to perform smooth network operation. In this paper, we formulate an optimization problem, whose goal is to strive for fairness in data rates among users and to reduce handovers. To accomplish that, we consider jointly the decisions when to handover and to which BS a user is to be assigned. This is an integer nonlinear program, and by relaxing it, we obtain an upper bound. Further, due to its NP-hardness, we propose a centralized and a multi-agent Deep Q Network (DQN)-based algorithm, which both find near-optimal user-to-BS assignments. We evaluate our Reinforcement Learning-based solutions for networks of different sizes and users with different velocities. We compare our approaches with baselines and show that they outperform them considerably in terms of fairness and radio link failures while being within 95% of the optimum. Our DQN algorithms also reduce the handover rate by up to 93% and avoid ping-pong handovers almost completely.

Modeling airport networks for theoretical policy analyses

More than in almost any other transport industry, air transport is globally connected. This paper provides an overview over theoretical studies considering network structures involving two or more airports. Beyond conveying study results, the goal is to offer guidance on how to \emph{theoretically} cover and analyze specific issues in the most effective way. Effectiveness is measured in terms of the complexity needed to address the specific issues. The selected issues discussed in this paper include ownership structures and privatization, congestion, beggar-thy-neighbor, and competition. We demonstrate that the analysis of these issues requires networks of different sizes and structures. We measure the airport size by the number of airports involved. We determine the network structure by (i) the number of regions and by distinguishing between regions which are just passively present or actively involved in policy making, and (ii) the involvement of local and non-local passengers.

Cost-Aware Optimization of Optical Add-Drop Multiplexers Placement in Packet-Optical xHaul Access Networks

This work concentrates on the problem of optimizing the cost of a passive wavelength division multiplexing (WDM) optical network used as a transport network for carrying the xHaul packet traffic between a set of remote radio sites and a central hub in a 5G radio access network (RAN). In this scope, we investigate the flexible use of optical add-drop multiplexers (OADMs) for the aggregation of traffic from a number of remote sites, where the type/capacity of optical devices—OADMs and optical multiplexers (MUXs)—is selected in accordance with the traffic demand. The approach is referred to as Flex-O. To this end, we formulate the xHaul network planning problem consisting in the joint provisioning of transmission paths (TPs) between the remote sites and the hub with optimized selection and placement of OADMs on the paths and proper selection of MUXs at the ends of the TPs. The problem formulation takes into accounts the optical power budget that limits the maximum transmission distance in a function of the amount and type of optical devices installed on the TPs. The network planning problem is modeled and solved as a mixed-integer linear programming (MILP) optimization problem. Several network scenarios are analyzed to evaluate the cost savings from the flexible (optimized) use of OADMs. The scenarios differ in terms of the availability of OADMs and the capacity of the WDM devices applied on the TPs. The numerical experiments performed in three mesh networks of different size show that the cost savings of up to between 35 and 45% can be achieved if the selection of OADMs is optimized comparing to the networks in which either single-type OADMs are used or the OADMs are not applied.

Lightweight Field Insect Recognition and Classification Model Based on Improved Deep Learning under Complex Background

Insect monitoring in the field is an extremely important part of the agricultural production system. Recent advances in computer technology have provided the technical foundation for automatic field insect monitoring. In insect automatic monitoring, insect recognition and classification based on images is one of the most active research areas. Rapid advancements in computer vision technology based on deep learning have provided new ideas for implementing automatic field insect monitoring. Firstly, the field insect images are preprocessed and input to the lightweight algorithm for feature extraction, and the prediction networks of different sizes are output by multiscale feature fusion; then, the joint cross-merge ratio is introduced for automatic identification and classification of field insects. Compared with other algorithms, the simulation results show that the proposed algorithm has higher accuracy, less time consumption, and stronger robustness. It effectively solves the insect accumulation and background interference problems and can identify field insects online in real time.

A fast user actual privilege reasoning framework based on privilege dependency graph reduction

AbstractIt is a key point to find out the actual privileges of network users in network security risk assessment. The Privilege dependency graph (PDG) provides an effective way to reason the actual privileges of network users from their initial privileges. The existing User Actual Privilege reasoning method is time‐consuming and not suitable for large‐scale networks. This paper introduces a fast User Actual Privilege reasoning framework based on PDG reduction. The core idea is to reduce the size of the graph as much as possible before the actual privilege reasoning. Three different nodes merged scenarios are proposed and discussed, as well as the influences of different execution sequences and execution times. Networks of different sizes were simulated to validate the effectiveness and scalability of their method. The experimental results show that the proposed method can decrease the time of User Actual Privilege reasoning by over 25% in large‐scale networks.

TOPOLOGICAL LEARNING FOR BRAIN NETWORKS.

This paper proposes a novel topological learning framework that integrates networks of different sizes and topology through persistent homology. Such challenging task is made possible through the introduction of a computationally efficient topological loss. The use of the proposed loss bypasses the intrinsic computational bottleneck associated with matching networks. We validate the method in extensive statistical simulations to assess its effectiveness when discriminating networks with different topology. The method is further demonstrated in a twin brain imaging study where we determine if brain networks are genetically heritable. The challenge here is due to the difficulty of overlaying the topologically different functional brain networks obtained from resting-state functional MRI onto the template structural brain network obtained through diffusion MRI.

A Novel Autoencoder-Based Feature Selection Method for Drug-Target Interaction Prediction with Human-Interpretable Feature Weights

Drug-target interaction prediction provides important information that could be exploited for drug discovery, drug design, and drug repurposing. Chemogenomic approaches for predicting drug-target interaction assume that similar receptors bind to similar ligands. Capturing this similarity in so-called “fingerprints” and combining the target and ligand fingerprints provide an efficient way to search for protein-ligand pairs that are more likely to interact. In this study, we constructed drug and target fingerprints by employing features extracted from the DrugBank. However, the number of extracted features is quite large, necessitating an effective feature selection mechanism since some features can be redundant or irrelevant to drug-target interaction prediction problems. Although such feature selection methods are readily available in the literature, usually they act as black boxes and do not provide any quantitative information about why a specific feature is preferred over another. To alleviate this lack of human interpretability, we proposed a novel feature selection method in which we used an autoencoder as a symmetric learning method and compared the proposed method to some popular feature selection algorithms, such as Kbest, Variance Threshold, and Decision Tree. The results of a detailed performance study, in which we trained six Multi-Layer Perceptron (MLP) Networks of different sizes and configurations for prediction, demonstrate that the proposed method yields superior results compared to the aforementioned methods.

Identification of Important Nodes in Multilayer Heterogeneous Networks Incorporating Multirelational Information

Centrality is an effective method to identify important nodes in complex networks, but it is still a challenge to find influential nodes by making full use of multiple relationships and global network topological features in complex networks. To address these problems, this article proposes an importance identification method for multilayer heterogeneous network node by incorporating multirelational information (MLC). This method studies the relational characteristics of heterogeneous nodes in detail and divides the heterogeneous nodes into different layers according to the node types, which can be further divided into core and auxiliary layers. The importance of the auxiliary layer is quantified by designing the interlayer influence and determining the interlayer influence weights of different connectivity influences; the centrality score of heterogeneous nodes under multiconnectivity relationships is fused using the transmission characteristics of internode relationships in the auxiliary layer, which in turn measures the importance of nodes in the core layer. To evaluate the proposed algorithm, we conduct experiments on five real multilayer heterogeneous networks of different sizes. The results show that MLC can make full use of different types of internode association relationship information, effectively fuse network structure information such as the neighbor weights of core and auxiliary layer nodes, and outperform the existing techniques in identifying important nodes.

Exact and Heuristics Algorithms for Screen Line Problem in Large Size Networks: Shortest Path-Based Column Generation Approach

In this study, we present exact and heuristics algorithms for a traffic sensors location problem called the screen line problem. It is a problem of how to locate traffic sensors on a transportation network where all the origin/destination node pairs are fully separated. The problem experiences two main complexity dimensions that obstruct finding an efficient solution algorithm for large-scale networks: its mathematical formulation, which is proved in the literature to be NP-hard, and an inherent combinatorial complexity due to the need for a network complete path enumeration. In this study, the problem is reformulated as a set covering problem. Thereafter, the dual formulation is recalled showing that the shortest path-based column generation method would yield as many paths as necessary and hence circumvent the intractability of the full path enumeration task. This path generation technique enables applying both the proposed heuristics and exact methods to the problem. In addition, the gap value between the heuristics and the exact algorithms is set to be examined statistically. For evaluation, three networks of different sizes were used to track the scalability of proposed algorithms. The methodology showed high efficiency to deal with up to 10,000 demand node pairs in addition to the capability of producing practical solutions with respect to normal traffic flow conditions. The proposed heuristics algorithm stipulates a gap value of less than 25% with more than 99% confidence.

Are there differences between governing and managing strategic networks of different sizes and ages?

Abstract This paper aims to analyze how governance and management of strategic networks (SNs) composed of small firms differ according to network size and length of existence. We analyzed 20 Brazilian SNs, comparing oldest to youngest and largest to smallest. The results show that large SNs have a more robust management structure, automated process control system, and centralized strategic decision-making power. Only small and younger SNs are not centralized and lack incentive mechanisms for members. Moreover, older SNs have a centralized strategic formulation and implementation process, whereas younger SNs have a more inclusive and participatory one. The results confirm previous studies and offer a fine-grained comprehension of the governance of SNs according to the number of members. The findings contribute to the nascent network governance theory and offer insights to network managers who have to reconfigure the governance as the number of members grows.

Double-Consensus-Based Distributed Energy Management in a Virtual Power Plant

The penetration of distributed generators increases the significance of virtual power plants (VPP) in the electricity market paradigm. The conventional VPP energy management system relies on a trustable centralized coordinator, which is vulnerable to single-point failure and requires a high-bandwidth communication network. This article proposes a robust, fully distributed consensus-based algorithm (RFDCA) for optimal dispatch of VPP participants in power systems with a practical communication network, which considers noise, communication delay, and a dynamically switching communication topology. The profit maximization problem is decomposed into subproblems using dual decomposition and solved using a double consensus approach, which uses a monotonically decreasing consensus gain function to suppress the adverse effects of communication delay and noise. One of the main advantages of this method is that the VPP participants need not share their private information with anyone, thereby preserving their privacy. Another advantage of the proposed approach is that it can deal with networks of different sizes and topologies. Simulations are carried out on standard 15-node VPP and IEEE 39-bus test systems to illustrate the efficacy of the RFDCA approach. The algorithm removes the need for a central controller in the VPP system, and the faster convergence of the algorithm extends its application in real-time energy management.

A novel method of heterogeneous combat network disintegration based on deep reinforcement learning

Modern war is highly dependent on intelligent, unmanned combat systems. Since many intelligent, unmanned combat systems have network attributes, it is meaningful to research combat systems from the perspective of complex network. Heterogeneous network provides a suitable model to describe real combat network. Previous studies of combat network only concentrate on homogeneous networks. However, on the real battlefield, military networks are composed of a large number of heterogeneous nodes and edges with different functions. In the paper, a superior, intelligent, heterogeneous combat network disintegration strategy (HDGED) are obtained by DQN, which embeds heterogeneous networks into a low-dimensional representation vector as input, rather than ignore the differences of the nodes and their connections. A method of heterogeneous graph embedding is first introduced, which adopts type encoding and aggregation. Besides, a normalized combat capability index was designed, which could assess the performance of the dynamic heterogeneous combat networks. On this basis, HDGED was experimented on networks with uneven node combat capabilities and the results show that HDGED has improved disintegration effectiveness for heterogeneous networks of different sizes compared with traditional methods. Our work provides a new approach to realize the disintegration of heterogeneous combat networks by deep reinforcement learning, which is of great significance for optimizing the command operation process, and deserves further study.

Optimization of vehicle automatic navigation path based on remote sensing and GIS

ObjectiveTaking a general view of the continuous convenience of modern social life, according to the rapid development of traffic network and communication network, this paper studies the vehicle path optimization problem. MethodsThis paper attempts to design a set of optimal vehicle path from the five aspects of algorithm development stage, algorithm solution idea, data storage mode, analysis data format and algorithm search strategy. According to the relevant theory of urban vehicle path, a mathematical model of vehicle path problem with time window restriction is constructed. Aiming at this model, a*, hierarchical algorithm, ant colony algorithm and genetic algorithm are used Line analysis and discussion, and according to the relevant algorithm examples in the literature to verify the model and algorithm. ResultIt is concluded that the combination of a*, ant colony algorithm and genetic algorithm is more suitable for the optimization of vehicle routing, and the hierarchical algorithm, road quality, congestion and other real-time traffic obstacles are improved to establish the vehicle routing optimization system in the traffic network and communication network. During the experiment, five road networks of different sizes were used successively. The modulus of these road networks increased sequentially, and the ratio of the number of road sections to the number of road network nodes was about 1698. And the conclusion drawn through experimental verification and algorithm verification proves the reliability and effectiveness of the system, has certain application value, and promotes the development of society.

Seismic damage assessment of highway bridges by means of soft computing techniques

Seismic risk assessment in bridge networks is of great interest in reducing earthquake adverse effects in structures and the society. Among existing methods for risk and loss assessment, Hazus methodology is widely accepted and used. The method includes several steps and calculations, being thus rather complex and time-consuming, especially if several bridges with diverse characteristics are to be examined. The present study investigates the potential of using soft computing techniques for determining the seismic hazard and expected losses as an alternative to the Hazus methodology. In particular, a number of representative datasets have been developed on the basis of Hazus and a number of methods have been formulated and tested regarding their capacity to effectively simulate the process. The methods that are examined range from regression curve-fitting to artificial neural networks of different size and characteristics. Alternative statistical tests have been used to evaluate the developed model capabilities. Evaluation results indicate that appropriately designed ANN methods can attain high accuracy and stable results among different datasets (training, testing, and validation). The analysis indicates the potential of using similar techniques to simulate seismic risk assessment based on actual data from earthquake events that have taken place in the past.

Optimal Allocation of Capacitors in Radial Distribution Networks Using Shannon's Entropy

Capacitor banks, when optimally placed in an electrical network improve power quality and reliability. For determining the capacitors’ optimal location, the prevailing index methods mainly focus on single criterion, e.g., either of voltage stability, loss reduction, system loadability, and neglect some of the equally critical quantities while proving the solution. For obtaining a pragmatically feasible techno-commercial solution, it is advantageous to consider multiple criteria. This article proposes a novel approach for optimal capacitor allocation, which allows to choose as many objective functions (criteria) as desired. In the proposed approach, initially, the load flow study is executed to obtain the network's quantities for an uncompensated network. Subsequently, optimal locations of capacitor banks are identified through the proposed indexing method based on the application of Shannon's Entropy. The capacitor banks’ optimal sizes are determined using the particle swarm optimization algorithm. The cost function is formulated as the minimization of sum of active power loss cost and the incurred annual capacitors cost subject to different operational constraints. The proposed approach is compared with that of the previously published methods by applying on radial distribution networks of different sizes (IEEE-12 bus, 34-bus and 108-bus) and the proposed approach is found to be superior.

A heuristic approach to integrate train timetabling, platforming, and railway network maintenance scheduling decisions

Train timetabling, platforming, and network maintenance scheduling are three highly interdependent problems that are crucial in the planning of railway operations, and each is normally addressed separately. In this paper, we simultaneously optimize these problems for a high-speed railway network that is comprised of multiple railway lines and stations. We model the railway network on a mesoscopic level and formulate a 0–1 binary integer programming model that minimizes the total train weighted running cost and any deviation from ideal maintenance task start times. A heuristic procedure, which dynamically updates the available time windows for each of the trains, is used to control the number of train paths in the mathematical model. The mathematical model is repeatedly solved, and at each iteration we gradually modify the set of train paths available. Four different strategies to modify train time windows are used in the train path modification step and their selection depends on the solution to the mathematical model. Computational results for three networks of different sizes conclusively demonstrate that there is not only benefit in integrating these problems, with improvements of as much as 30%, but also that the proposed solution approach is highly effective. Compared to the commercial solver CPLEX, the proposed approach is able to more quickly find better quality solutions within a given time limit.

Solving Bilevel AC OPF Problems by Smoothing the Complementary Conditions – Part II: Solution Techniques and Case Study

This is a second part of the research on AC optimal power flow being used in the lower level of the bilevel strategic bidding or investment models. As an example of a suitable upper-level problem, we observe a strategic bidding of energy storage and propose a novel formulation based on the smoothing technique. After presenting the idea and scope of our work, as well as the model itself and the solution algorithm in the companion paper (Part I), this paper presents a number of existing solution techniques and the proposed one based on smoothing the complementary conditions. The superiority of the proposed algorithm and smoothing techniques is demonstrated in terms of accuracy and computational tractability over multiple transmission networks of different sizes and different OPF models. The results indicate that the proposed approach outperforms all other options in both metrics by a significant margin. This is especially noticeable in the metric of accuracy where out of total 422 optimizations over 9 meshed networks the greatest AC OPF error is 0.023% that is further reduced to 3.3e-4% in the second iteration of our algorithm.

Maintenance Strategies for Networked Assets*

The purpose of this paper is to analyse the effect of different maintenance strategies for a network of assets whose condition deteriorates progressively along the time. We propose both an agent-based model that considers the dynamics of data traffic and asset deterioration in a data packet transport network; and a network-wide maintenance planning optimisation algorithm. Several network topologies are used to evaluate the maintenance strategies and determine the magnitude of the differences. Simulation results, in networks of different sizes and configurations, suggest that there are cases when a network-wide maintenance strategy could be up to 38% more effective in reducing the impact of the unavailability of assets due to maintenance, while keeping the lowest cost, compared to analysed alternatives.

Multi-objective biogeography-based optimization and reinforcement learning hybridization for network-on chip reliability improvement

Reliability is increasingly a major concern in network-on-a-chip (NoC) design, alongside increased performance demands from new applications and the need for continued miniaturization of silicon technology. In this article, we look at the task migration mechanism, used to recover from permanent processing element (PE) failures in NoCs, by remapping tasks performed on faulty cores to spare ones.An innovative reliability-aware task mapping technique is presented, based on a hybridization between Multi-Objective Optimization (MOO) and Reinforcement Learning (RL). It takes place in two steps. In the first, a set of optimal remapping solutions for different failure scenarios is generated at design-time, using a Biogeography-Based Multi-Objective Optimization algorithm, while considering communication energy and migration costs. In the second step, an artificial neural network agent is trained to select the best remapping solution, from those generated at design-time, to recover from execution failures at run-time.Experiments were carried out to evaluate our technique for different sizes of networks and on different benchmarks. The results obtained show that the technique based on the hybridization MOO_RL brings a great improvement in the reliability of the NoC and achieves a good compromise between reliability and performance. It also guarantees a reduction of the overhead caused by the storage space of the remapping solutions, compared to the existing solutions.

Artificial intelligence as a tool to aid in the differentiation of equine ophthalmic diseases with an emphasis on equine uveitis.

Due to recent developments in artificial intelligence, deep learning, and smart-device-technology, diagnostic software may be developed which can be executed offline as an app on smartphones using their high-resolution cameras and increasing processing power to directly analyse photos taken on the device. A software tool was developed to aid in the diagnosis of equine ophthalmic diseases, especially uveitis. Prospective comparison of software and clinical diagnoses. A deep learning approach for image classification was used to train software by analysing photographs of equine eyes to make a statement on whether the horse was displaying signs of uveitis or other ophthalmic diseases. Four basis networks of different sizes (MobileNetV2, InceptionV3, VGG16, VGG19) with modified top-layers were evaluated. Convolutional Neural Networks (CNN) were trained on 2346 pictures of equine eyes, which were augmented to 9384 images. 261 separate unmodified images were used to evaluate the performance of the trained network. Cross validation showed accuracy of 99.82% on training data and 96.66% on validation data when distinguishing between three categories (uveitis, other ophthalmic diseases, healthy). One source of selection bias for the artificial intelligence presumably was the increased pupil size, which was mainly present in horses with ophthalmic diseases due to the use of mydriatics, and was not homogeneously dispersed in all categories of the dataset. Our system for detection of equine uveitis is unique and novel and can differentiate between uveitis and other equine ophthalmic diseases. Its development also serves as a proof-of-concept for image-based detection of ophthalmic diseases in general and as a basis for its further use and expansion.