Network Capacity Research Articles

Deep-reinforcement-learning-based RMSCA for space division multiplexing networks with multi-core fibers [Invited Tutorial

The escalating demands for network capacities catalyze the adoption of space division multiplexing (SDM) technologies. With continuous advances in multi-core fiber (MCF) fabrication, MCF-based SDM networks are positioned as a viable and promising solution to achieve higher transmission capacities in multi-dimensional optical networks. However, with the extensive network resources offered by MCF-based SDM networks comes the challenge of traditional routing, modulation, spectrum, and core allocation (RMSCA) methods to achieve appropriate performance. This paper proposes an RMSCA approach based on deep reinforcement learning (DRL) for MCF-based elastic optical networks (MCF-EONs). Within the solution, a novel state representation with essential network information and a fragmentation-aware reward function were designed to direct the agent in learning effective RMSCA policies. Additionally, we adopted a proximal policy optimization algorithm featuring an action mask to enhance the sampling efficiency of the DRL agent and speed up the training process. The performance of the proposed algorithm was evaluated with two different network topologies with varying traffic loads and fibers with different numbers of cores. The results confirmed that the proposed algorithm outperforms the heuristics and the state-of-the-art DRL-based RMSCA algorithm in reducing the service blocking probability by around 83% and 51%, respectively. Moreover, the proposed algorithm can be applied to networks with and without core switching capability and has an inference complexity compatible with real-world deployment requirements.

Factor graph-based deep reinforcement learning for path selection scheme in full-duplex wireless multihop networks

A wireless multihop network (WMN) is set of wirelessly connected nodes without an aid of centralized infrastructure that can forward any packets via intermediate nodes by a multihop fashion. In the WMN, there are still some issues that need to be resolved, like due to any source node may choose an uncertainty path to send their packets through the multihop fashion and this leads to the performance of network capacity can degrade drastically. To solve this problem, in this research, we propose two novel path selection algorithms called SNR-based learning path selection (NLPS) algorithm and SINR-based learning path selection (INLPS) algorithm, which are incorporated with the deep reinforcement learning (DRL) to select the best multihop path from any source node to a destination node with highest end-to-end (E2E) throughput. Besides that, a factor graph (FG) approach and a nested lattice code (NLC) representation are used to reduce the computation time. According to the numerical studies with the NLC is applied, our simulation results reveal that the proposed NLPS and INLPS algorithms can improve the overall average network capacity up to 3.1 times and 10.5 times compared to FG, respectively. However, the overall average computation time are highly increased for NLPS and INLPS, i.e., about 0.627 s and 1.221 s, respectively compared to FG, which is about 0.006 s. In other words, both NLPS and INLPS algorithms can achieve high network capacity and moderate computation time.

The impact of social networks of historically underrepresented group operators (HUGOs) business recovery

While Historically Underrepresented Group Operators (HUGOs) businesses typically depend on social networks for disaster recovery, this aspect remains inadequately researched. This research investigates whether leveraging particular social networks (bonding, bridging, and linking) to obtain financial and informational access influences small business perceptions of recovery. Data was collected through a survey of 200 businesses in Salt Lake City, UT affected by the COVID-19 pandemic and analyzed using logistic regression. The findings indicate that: (1) small businesses that utilized bonding, bridging, or linking networking experienced negative recovery; however (2) HUGOs that utilized linking networks were more likely to experience a positive recovery than non-HUGOs. The research underscores the importance of diversifying social networking channels for successful HUGO business recovery and points to the need for economic recovery programs that build this networking capacity.

A Bandwidth and Gain Enhanced Hexagonal Patch Antenna using Hexagonal Shape SRR

In the evolving digital era, the primary focus of the telecommunications industry is on the 5G network, expected to deliver high data rates, low latency, large network capacity, and improved connectivity. This article discusses efforts to adopt optimal frequencies for 5G, introducing techniques to enhance the characteristics of microstrip antennas using Double Negative (DNG) metamaterial properties. The hexagonal-shaped Split Ring Resonant (HSRR) metamaterial is considered a potential method to increase the bandwidth and gain of 5G antennas. Simulation of HSRR unit cells shows a positive impact on DNG characteristics. Meanwhile, the antenna design incorporating HSRR superstrate elements significantly increases gain to 4.47 dBi, and the implementation of HSRR structures on the groundplane results in a remarkable 368% increase in bandwidth compared to conventional antennas without metamaterial.

An optimal concentric circular antenna array design using atomic orbital search for communication systems

Abstract In this study, optimum radiation patterns of Concentric Circular Antenna Arrays (CCAAs) are obtained by using the Atomic Orbital Search (AOS) algorithm for communication spectrum. Communication systems stands as a nascent technological innovation poised to revolutionize the landscape of wireless communication systems. It distinguishes itself through its hallmark features, notably an exceptionally high data transmission rate, expanded network capacity, minimal latency, and a commendable quality of service. The most important issue in wireless communication is a precision antenna array design. The success of this design depends on suppressing the maximum sidelobe levels (MSLs) values of the antenna in the far-field radiation region as much as possible. The AOS, which is a rapid and flexible search algorithm, is a novel physics-based algorithm. The amplitudes and inter-element spacing of CCAAs are optimally determined by utilizing AOS to the reduction of the MSLs. In this study, CCAAs with three and four rings are considered. The number of elements of these CCAAs has been determined as 4–6–8, 8–10–12 and 6–12–18–24. The radiation patterns obtained with AOS are compared with the results available in the literature and it is seen that the results of the AOS method are better.

Convex Relaxations of Maximal Load Delivery for Multi-Contingency Analysis of Joint Electric Power and Natural Gas Transmission Networks

Recent increases in gas-fired power generation have engendered increased interdependencies between natural gas and power transmission systems. These interdependencies have amplified existing vulnerabilities in gas and power grids, where disruptions can require the curtailment of load in one or both systems. Although typically operated independently, coordination of these systems during severe disruptions can allow for targeted delivery to lifeline services, including gas delivery for residential heating and power delivery for critical facilities. To address the challenge of estimating maximum joint network capacities under such disruptions, we consider the task of determining feasible steady-state operating points for severely damaged systems while ensuring the maximal delivery of gas and power loads simultaneously, represented mathematically as the nonconvex joint Maximal Load Delivery (MLD) problem. To increase its tractability, we present a mixed-integer convex relaxation of the MLD problem. Then, to demonstrate the relaxation’s effectiveness in determining bounds on network capacities, exact and relaxed MLD formulations are compared across various multi-contingency scenarios on nine joint networks ranging in size from 25 to 1191 nodes. The relaxation-based methodology is observed to accurately and efficiently estimate the impacts of severe joint network disruptions, often converging to the relaxed MLD problem’s globally optimal solution within ten seconds.

The planning method of new energy distribution network in plateau area based on local accommodation

Abstract The planning method of new energy distribution network in plateau area based on local accommodation is studied to improve the local accommodation capacity of new energy distribution network in plateau area. The framework of new energy distribution network planning in the plateau area is constructed, and the distribution network equipment suitable for the plateau environment is selected based on the harsh environment in the plateau area; in the framework of new energy distribution network planning in plateau area, a bi-level planning model considering multi-flexible resource coordinated scheduling and energy storage is established. The upper level planning model takes the maximum accommodation of new energy as the objective, and the lower level planning model takes the optimal daily operation benefit of energy storage under the given configuration as the optimization objective; the probabilistic power flow method and C-PSO are used to solve the bi-level model. The experiment shows that this method ensures the stability of the new energy distribution network in the plateau area, reduces the amount of abandoned wind energy and the operating cost, and improves the local accommodation capacity of the core higher than the distribution network.

Impact of the reconfigurable optical add-drop multiplexer architecture on the design of multi-band C+L+S optical networks

The main advantage of multi-band (MB) networks is to provide more capacity than C-band networks by using other unused bands like the L- and S-bands and, in this way, postpone the announced optical network capacity crunch. However, MB nodes have a more complex structure than C-band nodes, impacting their cost and enhancing their induced physical layer impairments (PLIs). The main goal of this paper is to analyze the impact of several MB node architectures (namely baseline, common-band and compact MB node architectures) on the total network capacity and total network cost-per-bit, using a routing, modulation format, and spectrum assignment (RMSA) network planning tool based on a Monte–Carlo simulation that also incorporates the impact of network PLIs. When the PLIs are neglected, the common-band architecture presents the lowest cost-per-bit compared to the remaining MB architectures, since only lower cost C-band components are used. However, with the PLIs impact, the common-band architecture leads to the lowest total network capacity and highest cost-per-bit due to additional noise coming from all-optical wavelength converters. In particular, the common-band total network capacity is less than half the baseline and compact total network capacities for a blocking probability of 1%, considering the best channel launch power. Also, the common-band cost-per-bit is almost twice the baseline and compact cost-per-bit due to the PLIs-induced degradation.

Information and Planning—Understanding the Capacity of the Aging Network (ACL)

Information and Planning—Understanding the Capacity of the Aging Network (ACL)

The performance analysis of deep learning algorithms for modelling and forecasting the particulate matter (PM10) in the eastern part of Turkey

The main purpose of this study is to select the most reliable nonlinear computational model to predict the particulate matter (PM10) concentrations. Time series data of three years PM10 concentrations were used as input variable. For the prediction, three different types of dynamic nonlinear autoregressive models were built and compared. These models are the Levenberg-Marquardt algorithm, the Bayesian Regulization algorithm, and the Scaled Conjugate Gradient algorithm. For each of these algorythms, various settings were adopted with the subsequent statistical analysis. To analyse the model performance, we used mean prediction error, root mean square error, and correlation coefficient. The lowest root mean square errors were found for the Levenberg-Marquardt algorithm with 15 neurons, for the Bayesian Regularization and for the Scaled Conjugate Gradient algorithm with 20 neurons in hidden layer. In our study, we focused on the long-term forecast of stationary dynamic time series data and on the large amount of data, which is presented as a scientific novelty. Additionally, we determined the main model parameters that most improve quality in terms of training and network capacity. Therefore, the derived forecasting model can be used as a priori for air quality management and regulations aimed on the reducing of pollutant level.

Comprehensive Evaluation of Urban Road Network Capacity Using Fractal Theory in the Context of the Internet of Things

Abstract In order to make a good assessment of road traffic status, this paper proposes a comprehensive evaluation method of urban road network capacity based on soft computing under the background of Internet of Things. The focus of the research is to use a variety of soft computing technologies such as Hausdorff dimension simplification method, branch dimension measurement algorithm, multifractal method, etc., to analyze the overall traffic load and guide the traffic channelization in an optimal way, considering various factors comprehensively. The model helps to optimize infrastructure and reduce road traffic congestion. This avoids traffic congestion, ultimately reducing the carbon footprint and promoting a green environment. This method analyzes the network capacity, network load and corresponding conversion coefficient of all levels of highway. Based on the multi-component linear regression method, this paper evaluates the urban road network capacity, and constructs the urban road network capacity planning model according to the traffic volume constraints and travel time constraints. The test results show that under the application of this method, the road capacity of the planned route exceeds 4000 pcu. The pcu is a passenger vehicle unit that measures the extent to which different types of vehicles have an impact on road capacity. When the capacity of a planned road exceeds 4000 pcu, it means that the road can carry a large number of different types of vehicles at the same time, and the average operating speed of the line can reach 42.3 km/h. After 5 years of planning, the efficiency of road use is still above 75 %. It can be proved that this method can obtain the optimal traffic path through better route planning and avoid traffic congestion and pollution.

ST-TransNet: A Spatiotemporal Transformer Network for Uncertainty Estimation from a Single Deterministic Precipitation Forecast

Abstract The forecast uncertainty, particularly for precipitation, serves as a crucial indicator of the reliability of deterministic forecasts. Traditionally, forecast uncertainty is estimated by ensemble forecasting, which is computationally expensive since the forecast model is run multiple times with perturbations. Recently, deep learning methods have been explored to learn the statistical properties of ensemble prediction systems due to their low computational costs. However, accurately and effectively capturing the uncertainty information in precipitation forecasts remains challenging. In this study, we present a novel spatiotemporal transformer network (ST-TransNet) as an alternative approach to estimate uncertainty with ensemble spread and probabilistic forecasts, by learning from historical ensemble forecasts. ST-TransNet features a hierarchical structure for extracting multiscale features and incorporates a spatiotemporal transformer module with window-based attention to capture correlations in both spatial and temporal dimensions. Additionally, window-based attention can not only extract local precipitation patterns but also reduce computational costs. The proposed ST-TransNet is evaluated on the TIGGE ensemble forecast dataset and Global Precipitation Measurement (GPM) precipitation products. Results show that ST-TransNet outperforms both traditional and deep learning methods across various metrics. Case studies further demonstrate its ability to generate reasonable and accurate spread and probability forecasts from a single deterministic precipitation forecast. It demonstrates the capacity and efficiency of neural networks in estimating precipitation forecast uncertainty.

Distilling Structural Knowledge for Platform-Aware Semantic Segmentation

Knowledge Distillation (KD) aims to distill the dark knowledge of a high-powered teacher network into a student network, which can improve the capacity of student network and has been successfully applied to semantic segmentation. However, the standard knowledge distillation approaches merely represent the supervisory signal of teacher network as the dark knowledge, while ignoring the impact of network architecture during distillation. In this paper, we found that the student network with a more similar architecture against the teacher network obtains more performance gain from distillation. Therefore, a more generalized paradigm for knowledge distillation is to distill both the soft-label and the structure of the teacher network. We propose a novel Structural Distillation (SD) method which introduces the structural similarity constraints into vanilla knowledge distillation. We leverage Neural Architecture Search technique to search optimal student structure for semantic segmentation from a well-designed search space, which mimics the given teacher both in terms of soft-label and network structure. Experiment results make clear that our proposed method outperforms both the NAS with conventional Knowledge Distillation and human-designed methods, and achieves sota performance on the Cityscapes dataset under various platform-aware latency constraints. Furthermore, the best architecture discovered on Cityscapes also transfers well to the PASCAL VOC2012 dataset.

Optimization on land development intensity of new industrial towns based on carrying capacity of multi-modal traffic network

ABSTRACT In the context of China’s new urbanization, the establishment of ‘new industrial towns (NITs)’ has emerged as a pivotal strategy for facilitating urban development. However, the current construction of NITs confronts numerous challenges, including issues such as unreasonable land development intensity (LDI) and overburdened transportation infrastructure. Urgent attention and improvement are required to address the coordination gaps between urban land use and transportation systems. This research explores the traffic carrying capacity (TCC) of NITs at a multi-modal super-network level, developing a bi-level programming model for LDI optimization and proposing an improved genetic algorithm (GA) to solve it. Taking the NIT in Laiwu District, Jinan, China as a case study area, the results demonstrate that our approach maximizes the utilization of space–time resources in both bus and car networks, particularly benefiting the latter during morning peak hours, thereby achieving a more balanced supply-demand traffic equilibrium.

Eight years into the horizon of aspirational maternal and newborn health pledges: a nationwide cross-sectional exploration of the Burundian EmONC network capacity and budget deficits

ObjectiveThe Burundian emergency obstetric and neonatal care (EmONC) programme, which was initiated in 2017 and supported by a specific policy, does not appear to reverse maternal and newborn mortality trends....

Unraveling the root causes of faults in mobile communications: A comparative analysis of different model explainability techniques

The escalating demand and complexity of monitoring services handled by Network Operations Centers (NOCs) have led Mobile Network Operators (MNOs) to prioritize automated solutions for network fault detection and diagnosis. Consequently, various Machine Learning (ML)-based Root Cause Analysis (RCA) systems have been developed, however their lack of explainability poses a challenge due to the predominantly black-box nature of ML models. This paper addresses this issue by presenting a supervised clustering methodology capable of integrating both glass-box and black-box models, the latter complemented by post-hoc explainability techniques. While black-box models excel in predictive capabilities, necessitating post-hoc techniques for explainability, glass-box models prioritize transparent decision-making, fostering a clearer understanding of the model’s behavior. This work delineates a methodology for performing RCA of faults in the User Downlink (DL) Average Throughput Key Performance Indicator (KPI), simultaneously comparing the performance of black-box models (Light Gradient-Boosting Machine (LightGBM) and Extreme Gradient Boosting (XGBoost)) with glass-box models (Logistic Regression (LR) and Explainable Boosting Machine (EBM)). Results revealed that the LightGBM black-box algorithm coupled with the SHapley Additive exPlanations (SHAP) method demonstrated superior performance in fault detection and diagnosis, without compromising the overall explainability. Consequently, it was possible to identify faults related to radio conditions, low network usage in specific user groups, low network capacity, and mobility issues. The paper concludes with practical mitigation strategies for each identified fault cluster.

Blockchain empowerment: Investigating integration with software-defined networks and its impact on IoT privacy

The swift expansion of Internet of Things (IoT) devices has brought forth exceptional prospects for automation and data-driven decisions. Software-Defined Networking (SDN) is an instance of network architecture that divides network devices into a control plane and a data plane. SDN provides a dynamic and adaptable method of managing the growing complexity of IoT devices with its programmable design and centralized control. A network's capacity to handle an increasing number of IoT devices is facilitated by SDN's improved scalability. Custom network policies and services that are suited to the distinctive requirements of various IoT applications it can be established because of SDN's programmability. SDN and blockchain integration can improve network transaction and configuration security. Here, blockchain technology is decentralized. There is not just one point of failure, which lowers the possibility of malicious attacks and illegal access. The study demonstrates that IoT environments can be enhanced more efficiently, transparently and safely by integrating blockchain technology with SDN. A summary of SDN is presented and then block-chain technologies are examined with a focus on consensus protocols. After that, it explores the difficulties of implementing blockchain-based SDN into practice, concentrating on security issues. Furthermore, this study explores the mutual effects of IoT and blockchain, emphasizing the complementary relationship between the two developing technologies. This review highlights that block-chain as well as SDNs could work together to strengthen IoT privacy and establish a more robust digital future.

Common TSO-DSO market framework with no upfront priority to utilize DER flexibility

Grid integration of distributed energy resources (DERs) is vital to provide flexibility services, required to ensure efficient system operations at both transmission and distribution levels. To prevent negative interactions between transmission system operators (TSO) and distribution system operators (DSOs) while procuring flexibility services from DERs, it is imperative to prioritize them. However, for system's cost-effectiveness allocating DER flexibility to the operator with the highest need is preferable rather than giving upfront priority. To address this, a novel coordinated decision-making approach for a common TSO-DSO market is proposed. This approach considers global balancing for the TSO and distribution congestion management for the DSO as objectives, using them as deciding factor to allocate DER flexibility to the system operator with the greatest need to fulfil its objective. Results show proposed method enhances DSO's flexibility transfer to TSO and maintains reactive power at T-D interface. Gap between TSO's DER flexibility needs and availability, influenced by congestion and line losses, is critical for prioritization. Specifically, network capacity and line losses constitute 18.79 % and 3.42 % of offered DER flexibility, respectively. Reactive power deployment improves Q/P ratio, reducing standard deviation from 0.19 to 0.018. Framework reduces conflicts, provides clear flexibility allocation rules without upfront priority.

Evaluating the Relationship Between Nonprofit Capacities and Organizational Effectiveness During a Global Pandemic

Guided by the contingency model of capacity effectiveness, we examine the relationship between organizational capacities and performance indicators during COVID-19. We conceptualized operational capacity and board leadership capacity as process oriented to ensure organizations’ effective functioning and to demonstrate accountability. Technological capacity and networking capacity were defined as resource oriented to help accomplish organizational goals. We used two effectiveness indicators to capture the input-output success measured by goal attainment and an organization’s ability to learn and adapt to improve its performances based on evaluation data (i.e., professional data use). Survey data collected from nonprofits located in a southeastern U.S. state showed that generally nonprofits were not performing well due to operation challenges. Operational capacity and technological capacity were negatively related to goal attainment; however, these two capacities and board leadership capacity were all positively related to professional data use. Implications describe how to turn a crisis into an opportunity to build resilience.

Estimating coverage and capacity of high frequency mobile networks in ultradense urban areas

High frequency communications (mmWave and TeraHz) in urban areas require a higher density of base stations compared to pre-5G mobile networks, but open the way to a quantum leap in increased throughput and reduced latency. However, we currently have no indication of how much we need to densify the deployment, and on the trade-off between the density of base stations and the performance improvement. This paper studies the problem of base stations placement to guarantee coverage to vehicles and pedestrians in urban areas when using high frequency communications. Our novel methodology takes advantage of vehicular traffic simulations and precise urban maps to generate a realistic demand model for vehicles and pedestrians in urban areas. We use a bounded error heuristic to find the maximal coverage that can be achieved with a given density of base stations, primarily using line-of-sight communications. We implemented the heuristic using CUDA libraries on Nvidia GPUs and evaluated the coverage in an urban area in the city of Luxembourg, for which vehicular traffic patterns are available. We focus on coverage and capacity analysis for the mmWave frequency, but the results are easily extended to TeraHz communications. Our results are the first to show that a reasonably low density (15 base stations per km2) is sufficient to provide coverage for vehicles in urban environments. However, optimizing on vehicles or on pedestrians are competing objectives: the operator needs to choose which one to target based on its business model when designing the network infrastructure. Our algorithms, code and open data can be used to perform this task and reproduce our results in different settings.