Optimal Network Research Articles

Evolution beats random chance: Performance-dependent network evolution for enhanced computational capacity

The quest to understand relationships in networks across scientific disciplines has intensified. However, the optimal network architecture remains elusive, particularly for complex information processing. Therefore, we investigate how optimal and specific network structures form to efficiently solve distinct tasks using a framework of performance-dependent network evolution, leveraging reservoir computing principles. Our study demonstrates that task-specific minimal network structures obtained through this framework consistently outperform networks generated by alternative growth strategies and Erdős-Rényi random networks. Evolved networks exhibit unexpected sparsity and adhere to scaling laws in node-density space while showcasing a distinctive asymmetry in input and information readout node distribution. Consequently, we propose a heuristic for quantifying task complexity from performance-dependently evolved networks, offering valuable insights into the evolutionary dynamics of the network structure-function relationship. Our findings advance the fundamental understanding of process-specific network evolution and shed light on the design and optimization of complex information processing mechanisms, notably in machine learning. Published by the American Physical Society 2025

Energy efficiency potential determination for an oil treatment and stabilization unit at the field

Relevance. The desire to increase the energy efficiency of industrial enterprises and reduce greenhouse gas emissions from their activities. Reducing specific energy consumption at large oil refineries and petrochemical plants is not new and is quite widely used. Dozens of monographs and thousands of articles are devoted to these areas. But it should be taken into account that in the oil refining industry, all crude oil, even that which does not reach the refinery, necessarily passes through oil preparation and stabilization units at the fields. Therefore, in order to create energy-efficient and environmentally friendly processes throughout the entire oil refining chain, it is necessary to increase the energy efficiency of the oil preparation and stabilization units located at the fields. There are very few research works on thermal energy integration of oil preparation and stabilization units. Aim. Determination of target design and energy values for an energy-efficient retrofit project of the heat exchange network for the surveyed oil preparation and stabilization units and of its energy efficiency potential. Methods. Pinch analysis methods are used to determine the target values of an energy-efficient retrofit project. Mathematical modeling of heat exchange processes in the heat exchange network and economic analysis were performed using the Pinch 2.02 software; the Aspen HYSYS software package was used to create a simulation engineering model of the oil preparation and stabilization units. Results. When determining the target values of the heat exchange network retrofit project, the cost of energy and heat exchange equipment, the cost of collectors for splitting process streams, and technical restrictions on the placement of heat exchanger sections were taken into account. The inclusion of fuel gas in the process stream table has allowed the definition of target parameters for the optimal unit heat exchange network design to evolve. In the process of evolution of target values, the energy efficiency potential of the surveyed oil preparation and stabilization units was determined, which shows the possibility of reducing specific energy consumption by 77%. Upon implementation of the heat exchange network retrofit project and achievement of target parameters, the following economic results will be obtained: IRR=42%, NPV=7425780 USD, DPP 4 years. Also, CO2 emissions can be reduced by 30 thousand tons per year. It should be noted that the evolution of target designation and all target values for the reconstruction project were obtained before the implementation of the heat exchange network oil preparation and stabilization units project itself.

Algorithm for determining the operating parameters of an electrical network in the problem of optimal reconfiguration in real time

Relevance. The need to develop technical solutions to reduce electrical energy losses in medium-voltage distribution electrical networks of oil and gas fields. Aim. Development of an algorithm for determining the parameters of the operating mode of an electrical network, applicable in a system of optimal control of the network configuration in order to reduce the level of electricity losses in the network. Methods. Mathematical modeling methods and combinatorial optimization methods. The nodal voltage method and the Newton–Raphson method are used to calculate the network operating mode. The mode is corrected using a sensitivity matrix. Results and conclusions. The authors have developed an algorithm for determining the parameters of the electric network operating mode when determining its optimal configuration. Optimization of the optimal configuration is performed based on the criterion of minimum active power losses in lines, taking into account the limitations on the power reserve of the feeding transformer substations and the number of normal breaks on one line. The developed algorithm is based on solving nonlinear systems of equations of nodal voltages using the Newton–Raphson method, as well as on correcting the parameters of the previously calculated operating mode using the sensitivity matrix. The optimal network configuration is determined by solving the combinatorial optimization problem using the branch and bound method. The operation of the algorithm is illustrated by the example of a network section containing two overhead power lines with two power sources and three feeding transformer substations. Based on the results of the analysis of all possible network configurations determined by combinations of normal breaks, it is concluded that the use of the algorithm will reduce the level of active power losses by up to 23.8%, which will increase the efficiency of the electric grid complex.

Implementation of the BIRCH algorithm to construct a data-adaptive network design for regional gravity field modeling via SRBF

This study presents a new methodology to establish an optimal network for the spherical radial basis functions (SRBFs) by employing the Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) algorithm. In the proposed methodology, sub-cluster centers obtained by the BIRCH algorithm are replaced with the center of the SRBFs. Since the horizontal positions of the observations are utilized in the clustering, the SRBFs are distributed adaptively to the data. The algorithm’s performance and the effects of the BIRCH parameters are investigated in detail with real and simulated data sets in the Auvergne and Colorado areas, respectively. The bandwidth of each SRBF is determined by the generalized cross-validation (GCV) technique. The turning point algorithm is employed to reduce long-wavelength errors that occur due to the always positivity of the selected Legendre coefficients in the spatial domain. The outcomes of the numerical tests show that only one parameter (threshold) is enough to construct a proper data-adaptive network design for SRBFs. Compared to existing algorithms, fewer SRBFs are required to achieve the same accuracy on the control points while saving more than 95% of the time in the network design. Furthermore, the proposed methodology improves the condition number of the normal equation matrix. That makes it possible to estimate unknown coefficients without regularization in the least-square procedure depending on the selected threshold parameter. Therefore, the BIRCH algorithm is very effective and suitable to establish an optimal data-adaptive network design, especially in large data sets.

Design of an Optimal Convolutional Neural Network Architecture for MRI Brain Tumor Classification by Exploiting Particle Swarm Optimization

The classification of brain tumors using MRI scans is critical for accurate diagnosis and effective treatment planning, though it poses significant challenges due to the complex and varied characteristics of tumors, including irregular shapes, diverse sizes, and subtle textural differences. Traditional convolutional neural network (CNN) models, whether handcrafted or pretrained, frequently fall short in capturing these intricate details comprehensively. To address this complexity, an automated approach employing Particle Swarm Optimization (PSO) has been applied to create a CNN architecture specifically adapted for MRI-based brain tumor classification. PSO systematically searches for an optimal configuration of architectural parameters—such as the types and numbers of layers, filter quantities and sizes, and neuron numbers in fully connected layers—with the objective of enhancing classification accuracy. This performance-driven method avoids the inefficiencies of manual design and iterative trial and error. Experimental results indicate that the PSO-optimized CNN achieves a classification accuracy of 99.19%, demonstrating significant potential for improving diagnostic precision in complex medical imaging applications and underscoring the value of automated architecture search in advancing critical healthcare technology.

A Review of Distribution Network Expansion Planning

Distribution Networks Expansion Planning (DNEP) is very complex and involves improving the system to meet the increasing demand using the most cost-effective strategy. Among the planned choices are the extension of substations, upgrade of distribution feeders, installation of additional Distributed Energy Resources (DERs), installation of Capacitor Banks (CBs) and many other methods. Distribution planners in contemporary networks must have faith in the reversibility of investments where Renewable Energy Resources (RERs) inject clean and cost-effective for DNEP to meet growing demand and environmental requirements. The comprehensive review of DNEP carried out in this paper covers all possible objective functions and problem constraints. With the rise of electric vehicles (EVs), there is a growing need to assess the impact of EV charging on distribution networks. Understanding how EV loads affect the network helps plan future expansions to efficiently accommodate the charging infrastructure. Integrating DERs, such as solar panels, wind turbines, and energy storage systems, is changing how electricity is generated, distributed, and consumed. Assessing the integration of DERs into distribution networks is crucial for optimal network planning and operation. In addition, CBs are essential for power factor correction and voltage regulation in distribution networks. Including CBs in expansion planning helps improve network efficiency, reliability, and overall power quality. By analyzing the impact of EV loads, DERs, and CBs in DNEP, researchers and planners can develop more accurate models and strategies for designing sustainable and resilient power systems to efficiently meet the growing energy demands.

Optimal network sizes for most robust Turing patterns

Many cellular patterns exhibit a reaction-diffusion component, suggesting that Turing instability may contribute to pattern formation. However, biological gene-regulatory pathways are more complex than simple Turing activator-inhibitor models and generally do not require fine-tuning of parameters as dictated by the Turing conditions. To address these issues, we employ random matrix theory to analyze the Jacobian matrices of larger networks with robust statistical properties. Our analysis reveals that Turing patterns are more likely to occur by chance than previously thought and that the most robust Turing networks have an optimal size, consisting of only a handful of molecular species, thus significantly increasing their identifiability in biological systems. Broadly speaking, this optimal size emerges from a trade-off between the highest stability in small networks and the greatest instability with diffusion in large networks. Furthermore, we find that with multiple immobile nodes, differential diffusion ceases to be important for Turing patterns. Our findings may inform future synthetic biology approaches and provide insights into bridging the gap to complex developmental pathways.

Energy‐Efficient Communication Using Auto‐Associative Polynomial Convolutional Neural Network in WSN

ABSTRACTSeveral changes have been implemented over the years to provide better resource management and service delivery for artificial wireless sensor networks (WSNs) that rely on the Internet of Things (IoT). Here, 5G networks offer high data rates with ultra‐low latency and robust reliability, which is essential for managing the substantial data volumes generated by IoT devices in 5G WSNs. IoT needs an optimal communication network to transmit data among different devices. The whole network is categorized as heterogeneous clusters in clustering. The cluster head (CH) selection achieves proficient data communication to the sink node through the chosen CH. In this manuscript, an energy‐efficient communication using auto‐associative polynomial convolutional neural network in 5G WSN (EEC‐HAPCNN) is proposed for improved data transmission through the selected route. Initially, clustering is done by parallel adaptive canopy k‐means clustering (PaC‐k‐M) algorithm. Then, Tasmanian devil optimization algorithm (TDOA) selects the CH required for facilitating the high capacity and low latency features of 5G. The data are given to sink node through the selected CH utilizing hierarchical auto‐associative polynomial convolutional neural network (HAPCNN) for efficient routing in 5G wireless communication network. The proposed EEC‐HAPCNN method is implemented in NS‐3 (network simulator 3). The proposed approach is examined using performance metrics like throughput, energy consumption, network lifetime, and number of nodes alive. The proposed EEC‐HAPCNN method provides 17.45%, 17.63%, and 18.43% lesser energy consumption and 17.64%, 17.64%, 18.54%, and 19.33% greater network life time compared with existing DBN‐MRFO‐5G‐WSN, IDCNN‐t‐DSBO, DACP‐WSN‐ANN, EEO‐IWSN‐ML, and EECA‐ML‐WSN techniques.

A novel approach for the design of minimum-cost open-pit haulage network

ABSTRACT This article presents new methods for designing optimal in-pit haulage networks in open-pit mines. The problem is modelled as a modified minimum-cost Steiner tree, accounting for excavation requirements. We propose two heuristic approaches, the Minimum Spanning Tree Heuristic (MSTH) and the Shortest Path Heuristic (SPH), and apply them to various block models. Results show that SPH generally produces more cost-effective networks, while MSTH achieves faster execution times, performing 44% faster on average. MSTH outperforms SPH in select cases but is costlier in others, demonstrating the trade-offs between speed and cost efficiency.

Defining bank branch trade areas for optimal distribution networks in mergers and acquisitions

PurposeThis study introduces a methodology that combines geographic information technologies and consumer behaviour principles to define, delineate and quantify the trade area (TA) of a bank branch within the context of mergers and acquisitions (M&A). The goal is to design an optimal distribution network tailored to the needs of financial institutions involved in M&A activities.Design/methodology/approachThe paper presents a procedure for TA delimitation, grounded in a theoretical model supported by marketing and consumer behaviour theories, focusing on proximity, purchase frequency and product type.FindingsAddressing a gap in the literature, this study highlights TA delineation as a key element in marketing strategy, exploring its role in establishing optimal distribution networks, particularly for financial institutions engaged in M&A.Research limitations/implicationsFor simplicity, the study focuses on a single bank branch, rather than a broader dataset.Practical implicationsThe proposed methodology enables more accurate delineation of TAs in M&A processes, mitigating the negative effects often overlooked by banks during mergers and acquisitions.Social implicationsThis approach helps reduce the risk of financial exclusion for vulnerable clients, promoting social and economic equity and fostering a fairer, more cohesive society.Originality/valueThis study is innovative in integrating geographic information science (GIS) metrics into location science, proposing fragmentation analysis to quantify the spatial structure and configuration of TAs. This approach departs from traditional practices, as these specific metrics have not been collectively applied in previous research.

GTD‐CER: Game‐Theoretic Dynamic Clustering for Enhanced Efficiency and Reliability in Wireless Sensor Networks

ABSTRACTEfficient cluster formation is a significant issue in wireless sensor networks (WSNs) for optimizing energy consumption, enhancing data reliability, and prolonging network lifetime. This paper proposes a dynamic cluster formation scheme modeled as a noncooperative game, where each sensor node acts as a player making strategic decisions on whether to become a cluster head (CH) or remain a member node (MN). In this role selection decision‐making phase, nodes evaluate their potential utility function, which incorporates energy consumption, data reliability, and data forwarding efficiency. Nodes dynamically switch roles based on their utility to achieve an optimal network configuration. Simulations conducted using the NS‐3 network simulator demonstrate that the proposed game theory‐based clustering scheme significantly improves network performance. We analyze key measures like energy consumption, packet delivery ratio (PDR), and data forwarding, and the results shows that the proposed scheme reduces energy consumption by 25%, improves PDR by 15%, and extends the network lifetime by 20%, compared to traditional methods. The dynamic role‐switching mechanism prolongs network lifetime by preventing the rapid depletion of node energy, ensuring stable and efficient network operations. It significantly enhances network performance, stability, and longevity.

Design of an Algorithm for Rapid Estimation of the Unit Cost of Concrete in Construction Projects

The estimation of the concrete unit cost in construction engineering plays a vital role in controlling construction costs and ensuring timely project completion. To achieve this, a fast estimation algorithm for concrete unit costs is proposed. To ensure accurate estimation and reduce the computational burden on the convolutional neural network (CNN) for rapid estimation, the factors influencing concrete costs are identified and arranged using the interpretive structural modeling (ISM) method. The factors affecting the concrete unit cost of high-rise construction are selected as the input data sequence for the CNN model. The feature map of the input data is extracted through the convolution layer. After applying the pooling operation to the feature map, the processed data is passed into the fully connected layer through the final pooling layer, where the final calculation is performed to obtain the estimated concrete unit cost. Experimental results indicate that to ensure fast convergence and minimize estimation errors in CNN estimation, optimal network parameters are determined through multiple experiments. The best configuration includes a [Formula: see text] convolution kernel and 11 convolutional cores. This algorithm, which uses the ISM method to select influential factors, achieves high accuracy in estimating the concrete unit cost. In actual engineering applications, the error between the estimated and actual results is minimal, with a maximum difference of only 1 yuan.

Bayesian predictive system for assessing the damage intensity of residential masonry buildings under the impact of continuous ground deformation

The paper introduces a method for predicting damage intensity in masonry residential buildings situated in mining areas, focusing on the impact of large-scale continuous ground deformation. The research utilizes in situ data collected in a database, encompassing structural and material features, as well as information on maintenance quality and building durability. In addition to this information, the database collected data on the intensity of continuous deformation of the mining area at the location of the building, as well as the range and intensity of damage identified in buildings. The information included in the database was the result of many years of observations of buildings during the disclosure of impacts from mining exploitation and was based on: the results of in-situ building inventory, analysis of available building documentation and information provided by mining companies. The archived data were categorized variables labeled. The transformation of the data to a labeled value was dictated directly by the assumptions of the GOBNILP algorithm. Ultimately, a predictive model, represented by an optimal Bayesian network structure, is established. The optimisation of the network structure is achieved through the adaptation of the GOBNILP Bayesian network learning algorithm from data. This optimisation process is executed through the Gurobi Optimizer. It is worth noting that this interdisciplinary approach represents one of the first applications of such a methodology in the field of civil and environmental engineering. The results obtained can therefore be of significant value given the fact that the methodology of detecting the structure of Bayesian networks from data is still developing intensively in other scientific fields. In the course of the analyses, metric scores are examined, and various network structures are assessed based on their complexity. Great values of classification accuracies over 91% were obtained. This meticulous evaluation allows for the selection of the optimal Bayesian network that best generalises the knowledge acquired during the learning process. The paper also demonstrates the potential application of the obtained model in diagnosing damage causes and predicting future occurrences, highlighting the versatility of the proposed approach for addressing issues in the field.

Research on agent optimal decision algorithm improvement and network design based on hierarchical reinforcement learning

Research on agent optimal decision algorithm improvement and network design based on hierarchical reinforcement learning

Optimal Bayesian Neural Network based Decision Support System for Mitotic Nuclei Detection on Histopathologic Imaging

Optimal Bayesian Neural Network based Decision Support System for Mitotic Nuclei Detection on Histopathologic Imaging

Altered Connectome Topology in Newborns at Risk for Cognitive Developmental Delay: A Cross-Etiologic Study.

The human brain connectome is characterized by the duality of highly modular structure and efficient integration, supporting information processing. Newborns with congenital heart disease (CHD), prematurity, or spina bifida aperta (SBA) constitute a population at risk for altered brain development and developmental delay (DD). We hypothesize that, independent of etiology, alterations of connectomic organization reflect neural circuitry impairments in cognitive DD. Our study aim is to address this knowledge gap by using a multi-etiologic neonatal dataset to reveal potential commonalities and distinctions in the structural brain connectome and their associations with DD. We used diffusion tensor imaging of 187 newborns (42 controls, 51 with CHD, 51 with prematurity, and 43 with SBA). Structural weighted connectomes were constructed using constrained spherical deconvolution-based probabilistic tractography and the Edinburgh Neonatal Atlas. Assessment of brain network topology encompassed the analysis of global graph features, network-based statistics, and low-dimensional representation of global and local graph features. The Cognitive Composite Score of the Bayley scales of Infant and Toddler Development 3rd edition was used as outcome measure at corrected 2 years for the preterm born individuals and SBA patients, and at 1 year for the healthy controls and CHD. We detected differences in the connectomic structure of newborns across the four groups after visualizing the connectomes in a two-dimensional space defined by network integration and segregation. Further, analysis of covariance analyses revealed differences in global efficiency (p < 0.0001), modularity (p < 0.0001), mean rich club coefficient (p = 0.017), and small-worldness (p = 0.016) between groups after adjustment for postmenstrual age at scan and gestational age at birth. Moreover, small-worldness was significantly associated with poorer cognitive outcome, specifically in the CHD cohort (r = -0.41, p = 0.005). Our cross-etiologic study identified divergent structural brain connectome profiles linked to deviations from optimal network integration and segregation in newborns at risk for DD. Small-worldness emerges as a key feature, associating with early cognitive outcomes, especially within the CHD cohort, emphasizing small-worldness' crucial role in shaping neurodevelopmental trajectories. Neonatal connectomic alterations associated with DD may serve as a marker identifying newborns at-risk for DD and provide early therapeutic interventions. Trial Registration: ClinicalTrials.gov identifier: NCT00313946.

Application of a one-dimensional convolutional neural network in defect size inversion of oil and gas pipelines

The strong non-linearity and low prediction accuracy of defect depth inversion often lead to challenges in magnetic flux leakage (MFL) detection and evaluation. If a one-dimensional convolutional neural network (1D-CNN) model could automatically extract the features of the original MFL signal and its simple and compact configuration, then real-time and low-cost hardware implementation should be achievable in the future. Therefore, in this work, a pipeline defect size inversion method based on a 1D-CNN model is proposed and the optimal network hierarchy is explored. In order to fully fuse the three-axis MFL signal and input it into the 1D-CNN for defect size inversion, three signal input strategies suitable for MFL defect detection based on the 1D-CNN are proposed and the quantitative results of the different three-axis MFL signal input strategies for an artificial defect dataset are compared and analysed. Experimental results indicate that using a lateral connection between the three-axis MFL signals can effectively achieve high-precision quantification of defect size and especially the quantification of defect depth. In addition, the comprehensive comparison and analysis with other network structures and traditional algorithms also verify that the 1D-CNN method still has advantages in accuracy and time complexity.

Optimal Network Reconfiguration and Scheduling with Hardware-in-the-Loop Validation for Improved Microgrid Resilience

Optimal Network Reconfiguration and Scheduling with Hardware-in-the-Loop Validation for Improved Microgrid Resilience

Crayfish optimisation algorithm for strategic planning of distributed generation and capacitor bank with network reconfiguration on radial distribution network

This study presents a cutting-edge strategy for the effective integration of distributed generation (DG) and capacitor banks (CB) with optimal network reconfiguration inside the radial distribution network. The crayfish optimisation algorithm is employed to identify the optimal configuration for network and optimal allocation of compensating devices. The main aim of this planning methodology is to elevate the system performance by curtailing power losses and improving voltage profiles. The potency of this approach is validated through simulation studies on the 118-bus standard distribution systems with several load models, such as constant current, constant power, constant impedance and ZIP load models. Furthermore, a comprehensive examination of several case studies underscores the benefits of the suggested approach. The simulation results demonstrate that integrating DG units operating at optimal power factor, along with coordinated operation of CB and network reconfiguration, can substantially enhance distribution system performance. This simultaneous approach, applied to a constant power load model, led to an 86.90% reduction in active power loss, an 86.42% reduction in reactive power loss and an increase in the minimum bus voltage level of the system from 0.8688 to 0.9815 p. u.

Secure cloud computing: leveraging GNN and leader K-means for intrusion detection optimization

Over the past two decades, cloud computing has experienced exponential growth, becoming a critical resource for organizations and individuals alike. However, this rapid adoption has introduced significant security challenges, particularly in intrusion detection, where traditional systems often struggle with low detection accuracy and high processing times. To address these limitations, this research proposes an optimized Intrusion Detection System (IDS) that leverages Graph Neural Networks and the Leader K-means clustering algorithm. The primary aim of the study is to enhance both the accuracy and efficiency of intrusion detection within cloud environments. Key contributions of this work include the integration of the Leader K-means algorithm for effective data clustering, improving the IDS’s ability to differentiate between normal and malicious activities. Additionally, the study introduces an optimized Grasshopper Optimization algorithm, which enhances the performance of the Optimal Neural Network, further refining detection accuracy. For added data security, the system incorporates Advanced Encryption Standard encryption and steganography, ensuring robust protection of sensitive information. The proposed solution has been implemented on the Java platform with CloudSim support, and the findings demonstrate a significant improvement in both detection accuracy and processing efficiency compared to existing methods. This research presents a comprehensive solution to the ongoing security challenges in cloud computing, offering a valuable contribution to the field.