Network Operations Research Articles

Core network traffic prediction based on vertical federated learning and split learning

Wireless traffic prediction is vital for intelligent cellular network operations, such as load-aware resource management and predictive control. Traditional centralized training addresses this but poses issues like excessive data transmission, disregarding delays, and user privacy. Traditional federated learning methods can meet the requirement of jointly training models while protecting the privacy of all parties’ data. However, challenges arise when the local data features among participating parties exhibit inconsistency, making the training process difficult to sustain. Our study introduces an innovative framework for wireless traffic prediction based on split learning (SL) and vertical federated learning. Multiple edge clients collaboratively train high-quality prediction models by utilizing diverse traffic data while maintaining the confidentiality of raw data locally. Each participant individually trains dimension-specific prediction models with their respective data, and the outcomes are aggregated through collaboration. A partially global model is formed and shared among clients to address statistical heterogeneity in distributed machine learning. Extensive experiments on real-world datasets demonstrate our method’s superiority over current approaches, showcasing its potential for network traffic prediction and accurate forecasting.

Accelerating spiking neural network simulations with PymoNNto and PymoNNtorch.

Spiking neural network simulations are a central tool in Computational Neuroscience, Artificial Intelligence, and Neuromorphic Engineering research. A broad range of simulators and software frameworks for such simulations exist with different target application areas. Among these, PymoNNto is a recent Python-based toolbox for spiking neural network simulations that emphasizes the embedding of custom code in a modular and flexible way. While PymoNNto already supports GPU implementations, its backend relies on NumPy operations. Here we introduce PymoNNtorch, which is natively implemented with PyTorch while retaining PymoNNto's modular design. Furthermore, we demonstrate how changes to the implementations of common network operations in combination with PymoNNtorch's native GPU support can offer speed-up over conventional simulators like NEST, ANNarchy, and Brian 2 in certain situations. Overall, we show how PymoNNto's modular and flexible design in combination with PymoNNtorch's GPU acceleration and optimized indexing operations facilitate research and development of spiking neural networks in the Python programming language.

A bi-objective sustainable vehicle routing optimization model for solid waste networks with internet of things

Waste production is growing in most communities due to population expansion. Given the stated issue, managing the Solid Waste (SW) created worldwide would be vital. Effective Waste Management (WM) is essential to preserving the environment and lowering pollution. It aids in resource preservation, greenhouse gas emission reduction, and ecosystem protection. Additionally, the promotion of public health and sanitation is significantly aided by WM procedures. This study presents an integrated procedure to enhance the operations of a WM network for recycling SW. We propose a mathematical model to find the optimal sustainable vehicle routes, allocation, and Sequence Scheduling (SS) problem in the recycling industry to reduce costs and CO2 emissions and increase job opportunities. The fundamental innovation of this work is considering waste-vehicle and waste-technology compatibility and Internet of Things (IoT) systems in the model to decrease CO2 emissions and identify compatible waste for recycling centers to produce more final products. An LP-metric and an Epsilon Constraint (EC) approach are used to solve the suggested model. By comparing the two approaches, we have found EC performs better in results and CPU time. As a result, various test problems of different sizes are offered. Accordingly, sensitivity analyses are recommended to assess the suggested model’s effectiveness. Using vehicles compatible with waste reduces CO2 emissions. Utilizing IoT technology and optimization methods makes it feasible to save costs (20%), have a less destructive impact on the environment (36%), and ultimately increase the sustainability of the WM process.

Fuel Burn Method Assessment Using Automatic Dependent Surveillance–Broadcast and European Reanalysis Data: Limited Flight Sample Analysis

Fuel burn during the actual route flown is an important indicator of aircraft operational efficiency. This study aims to assess and systematically evaluate the method for fuel consumed during flights using data from the automatic dependent surveillance–broadcast (ADS-B), European reanalysis (ERA5) meteorological dataset, and BADA 3 performance. A literature background and comprehensive methodology are provided for fuel estimation using track data. The airborne part of the trajectory was used to estimate the total trip fuel consumed during several flights of a commercial airliner. The calculated fuel burn is compared with measured fuel consumption from the flight data recorder (FDR). The results show that fuel consumption for the entire airborne part of the trajectory can be estimated with an average error of 1.2% and with a standard deviation of 1.3%. Detailed results of fuel burn for individual flight phases, from the initial climb to the approach, are also presented. In addition, this paper also discusses the sources of errors and the potential applications of the method for network operations and environmental monitoring.

A deep clustering framework for load pattern segmentation

In recent years, the widespread use of smart meters in power networks has generated a wealth of data from electricity customers. However, much of this real-world smart meter dataset lacks labeled data, posing a significant challenge that can be addressed by clustering. Traditional clustering methods often struggle in high-dimensional spaces, leading to less accurate results and increased computational demands. In response to these challenges, this research introduces a framework that utilizes a deep-learning-based clustering approach to address the issue of accurate customer clustering based on usage patterns in unlabeled data. Using an autoencoder, our approach integrates dimensionality reduction and clustering into an end-to-end unsupervised learning framework. Our algorithm significantly improves load profiling by tackling challenges related to nonlinear decision boundaries at the autoencoder bottleneck. Unlike traditional approaches, we propose separating the optimization of reconstruction and cluster loss, bridging the gap between clustering quality and reconstruction efficiency. We rigorously analyze the performance of our approach by comparing classical and state-of-the-art algorithms using two real-world smart meter data. We provide a comprehensive comparative analysis of our method against five common dimension reduction techniques used in high-dimensional clustering. The experimental analysis concludes that the proposed algorithm significantly enhances load profiling more than others, as confirmed through detailed load curve analysis and clustering validity indexes. This comprehensive assessment highlights the effectiveness and versatility of our proposed methodology when compared to others. Moreover, this research advances load profiling in smart grid analytics, providing practical insights for utilities and stakeholders looking to optimize power network operations.

SCDetect: A SeisComP Module for Real-Time Waveform Cross-Correlation-Based Earthquake Detection

Abstract Enhanced earthquake catalogs based on waveform cross correlation (template matching) have become routine when studying regional or sequence specific seismicity. Currently, there is no existing open-source cross-correlation software that is designed to be fully integrated in real-time operations of seismic networks. To fill this gap, we introduce SCDetect, a software that implements real-time earthquake detection based on waveform cross correlation in the time domain. SCDetect with the extension module scdetect-cc is an open-source SeisComP package written in C++. scdetect-cc can be used to process both archived waveform data (playback mode), and real-time data. In the real-time application, waveforms are fetched through one of the SeisComP RecordStream interfaces, and its output (picks, origin times, amplitudes, and magnitudes) are sent to the SeisComP messaging system. The new origins are associated either with existing events detected by other pick-based SeisComP modules, or create new events. Optionally, the hypocenter location can be refined by downstream application of existing SeisComP modules. scdetect-cc offers two magnitude estimation methods that are based on the amplitudes of the template earthquakes and the new detections. In the real-time application, scdetect-cc can be scaled to handle thousands of templates without overloading the application or becoming too latent, unable to keep up with the data flow. In the playback mode, we applied scdetect-cc to three recent earthquake sequences occurring in Switzerland and surrounding regions between 2019 and 2020. Two scenarios are tested to simulate its performance in real time. The first scenario cross correlates the signals of the nearest station, whereas the second requires four stations. In both cases, we successfully detected most of the cataloged events and added hundreds of new detections. Overall, scdetect-cc is a computationally efficient and highly customizable tool to detect earthquakes for regional networks that implement the SeisComP system for earthquake monitoring.

TLPGNN : A Lightweight Two-Level Parallelism Paradigm for Graph Neural Network Computation on Single and Multiple GPUs

Graph Neural Networks (GNNs) are an emerging class of deep learning models specifically designed for graph-structured data. They have been effectively employed in a variety of real-world applications, including recommendation systems, drug development, and analysis of social networks. The GNN computation includes regular neural network operations and general graph convolution operations, which take most of the total computation time. Though several recent works have been proposed to accelerate the computation for GNNs, they face the limitations of heavy pre-processing, low efficiency atomic operations, and unnecessary kernel launches. In this paper, we design TLPGNN , a lightweight two-level parallelism paradigm for GNN computation. First, we conduct a systematic analysis of the hardware resource usage of GNN workloads to understand the characteristics of GNN workloads deeply. With the insightful observations, we then divide the GNN computation into two levels, i.e., vertex parallelism for the first level and feature parallelism for the second. Next, we employ a novel hybrid dynamic workload assignment to address the imbalanced workload distribution. Furthermore, we fuse the kernels to reduce the number of kernel launches and cache the frequently accessed data into registers to avoid unnecessary memory traffic. To scale TLPGNN to multi-GPU environments, we propose an edge-aware row-wise 1-D partition method to ensure a balanced workload distribution across different GPU devices. Experimental results on various benchmark datasets demonstrate the superiority of our approach, achieving substantial performance improvement over state-of-the-art GNN computation systems, including Deep Graph Library (DGL), GNNAdvisor, and FeatGraph, with speedups of 6.1 ×, 7.7 ×, and 3.0 ×, respectively, on average. Evaluations of multiple-GPU TLPGNN also demonstrate that our solution achieves both linear scalability and a well-balanced workload distribution.

Auto-metric Graph Neural Network based Blockchain Technology for Secured Dynamic Optimal Routing in MANET

Mobile ad hoc network (MANET) routing is a generous tactic used for allocating packets to the base station (BS). During the operations of routing, occurrence of malicious node embellishes the mobile ad hoc network operations. For that reason, a trusted distributed routing protocol is obliged that maintains the routing buttressing and the proficiency of mobile ad hoc network. To overcome these challenging issues, Auto-Metric Graph Neural Network based Blockchain technology is proposed in this manuscript for Secured Dynamic Optimal Routing in MANET (BC-SDOR-MANET-AGNN). The proposed approach is simulated in NS-2 tool. The proposed BC-SDOR-MANET-AGNN approach attains 76.26%, 65.57%, 42.9% minimal delay during 25% malicious routing environment, 73.06%, 63.82%, 38.84% less delay during 50% malicious routing environment when analyzed to the existing models, like enhanced hybrid secure multipath routing protocol for MANET (BC-SDOR-MANET-GAHC), an improved ad hoc on-demand distance vector routing security approach based on BC technology in MANET (BC-SDOR-MANET-AODV-MQS) and block chain-based better approach for the mobile ad-hoc networking protocol using ensemble algorithm (BC-SDOR-MANET-E-BATMAN) methods.

Benders decomposition for robust distribution network design and operations in online retailing

The increasingly flourishing e-commerce has prompted e-retailers to implement a two-layer distribution network consisting of regional and forward distribution centers (FDCs) to reduce the fulfillment cost. This is done at the expense of incurring construction cost and complicating the inventory management, thus may not achieve a cost-effective goal. In this paper, we study a joint network design and operations problem that first chooses the locations and assortments for FDCs before the horizon starts, then decides the replenishment, allocation, and fulfillment quantities adaptively as random demands reveal over periods. We formulate a multi-period stochastic model and propose a robustness based Benders decomposition algorithm, which first applies a linear decision rule to get a mixed-integer robust counterpart model, then solves it using a Benders decomposition. Numerical experiments suggest that our algorithm produces good-quality solutions efficiently and robustly under distributional ambiguity. A case study using real data from JD.com demonstrates the applicability of our algorithm, which yields substantial cost savings over a decentralized policy and a status quo policy. Some managerial and practical insights are derived from the results.

A Mixed‐Integer Linear Programming Framework for Optimization of Water Network Operations Problems

AbstractWater distribution systems (WDSs) are critical infrastructure used to convey water from sources to consumers. The mathematical framework governing the distribution of flows and heads in extended period simulations of WDSs lends itself to application in a wide range of optimization problems. Applying the classical mixed integer linear programming (MILP) approach to model WDSs hydraulics within an optimization framework can contribute to higher solution accuracy with lower computational effort. However, adapting WDSs models to conform to a MILP formulation has proven challenging because of the intrinsic non‐linearity of system hydraulics and the complexity associated with modeling hydraulic devices that influence the state of the WDS. This paper introduces MILPNet, an adjustable framework for WDSs that can be used to build and solve an extensive array of MILP optimization problems. MILPNet includes constraints that represent the mass balance and energy conservation equations, hydraulic devices, control rules, and status checks. To conform to MILP structure, MILPNet employs piece‐wise linear approximation and integer programming. MILPNet was implemented and tested using Gurobi Python API. Modeling accuracy was shown to be comparable to EPANET, a public domain software for hydraulic modeling, and sensitivity analyses were conducted to examine the impacts of the modeling assumptions on the performance of MILPNet. Additionally, application of the framework was demonstrated using pump scheduling optimization examples in single and rolling horizon scenarios. Our results show that MILPNet can facilitate the construction and solution of optimization problems for a range of applications in WDSs operations.

Acceptance Analysis of Cyclops Application in Telkomsel Pamasuka Area Using Innovation Diffusion Theory (IDT) and Technology Acceptance Model (TAM)

Purpose: In this thesis, we will examine how much employee acceptance in the Pa Masuka Area, especially “Network” and “Sales', which totals around 522 people to the CYCLOPS application using the Innovation Diffusion Theory (IDT) and Technology Acceptance Model (TAM) methods, then an online survey is conducted.
 Research methodology: Data analysis was performed using a Structural Equation Modeling (SEM) model.
 Results: Digitization of processes at Telkomsel continues to be carried out to increase the effectiveness of employee work, including in the Pausuka Area, especially in the Area Network Operations Sub-Directorate of Pausuka which is responsible for 18,000 sites serving 30 million customers based on April 2023 data.CYCLOPS is a supporting application for digitizing processes that makes it easier for employees, especially the "Network" and "Sales" sections, to observe network conditions (Live Monitoring), find out the potential for network development, make improvements that are right on target according to set priorities to carry out network quality tests.

Deep ensemble of classifier for intrusion detection in WSN and improved attack mitigation process

SummaryAttacks have a significant negative impact on the wireless sensor network's network operations. They target to weaken the network layer, if they are not completely eradicated, the networks' ability to execute their desired function becomes collapsed. While intended to monitor such unexpected attacks, anomaly‐based intrusion detection systems (AIDS) have a high risk of false positives. This article intends to propose a Deep Ensemble Intrusion detection with a Self‐adaptive Sewing Training‐Based Optimization (DIED‐SASTO) model that includes the following steps: (a) preprocessing, (b) feature extraction, (c) optimal feature selection, and (d) detection. Initially, an improved class imbalance processing will take place to solve the imbalance problem during the preprocessing step. Subsequently, the features are extracted including higher‐order statistical features, improved entropy, and correlation‐based features during the feature extraction step. From the extracted feature set, as the curse of dimensionality becomes a serious challenge, it is significant to choose the optimal features. In the optimal feature selection process, a new Self‐adaptive Sewing Training‐Based Optimization (SASTO) is used. In addition, the intrusion detection will be employed based on the selected optimal features and trained using deep ensemble models like Deep maxout, Deep Belief Network (DBN), and Bidirectional Long short‐term memory (Bi‐LSTM). Once the presence of an attack is detected, it is mandatory to mitigate the attacker node form the network. For Attack Mitigation, improved entropy will be progressed. The effectiveness of the DIED‐SASTO is evaluated over conventional methods in terms of various metrics.

Safeguarding Software-Defined Networks: Comprehensive Frameworks and Best Practices for Security Threat Mitigation

Abstract: The proliferation of IoT devices such as sensors, actuators, sensors, and other endpoints has resulted in a significant surge in data generation. Ensuring the security and efficiency of data transmission necessitates the implementation of an internet design that possesses the capability to scale as required. This study investigates the potential impact of SDN on enhancing the performance of IoT networks. This study examines the ability to adapt network resources in real-time to meet the demands of IoT applications. It is imperative to address the security vulnerabilities in the SDN architecture to ensure secure and reliable network operations. This paper thoroughly examines the challenges, various security solutions, and recommended practices for effectively protecting SDN infrastructures. This study comprehensively analyzes the pertinent scholarly works, conducts a comparative analysis of diverse security approaches, and assesses their respective advantages and limitations. The need for further investigation into the security aspects of SDN is also acknowledged. This article highlights the importance of enhancing security practices, implementing continuous monitoring, and identifying potential threats. Additionally, it presents case studies that exemplify real-world security challenges associated with SDN. Further, this study incorporates security solutions into SDN frameworks, emphasizing the significance of meticulous strategic preparation, comprehensive testing, and ongoing upkeep to ensure seamless interoperability with current systems. This study is significant as it contributes to the expanding literature on security in SDN. The comprehensive examination of existing literature, meticulous analysis, thorough review of security approaches, identification of issues and limitations, and exploration of potential avenues for future research in this work render it a valuable resource for researchers and practitioners investigating SDN security. The primary objective of this study is to improve the reproducibility and pragmatic assessment of security measures in SDN settings. This study provides comprehensive information on implementation, testbed settings, datasets, and experimental procedures to promote transparency and repeatability. The study presents findings from extensive testing and benchmarking, showcasing the effectiveness of security solutions in addressing different types of threats. The study focuses on achieving a harmonious equilibrium between accuracy and efficient utilization of resources. The primary objective of this study is to improve the reproducibility and pragmatic assessment of security measures in SDN settings. This study includes comprehensive information on implementation, testbed configuration, datasets, and experimental procedures to promote transparency and reproducibility. The study presents empirical evidence and analysis to support the effectiveness of security solutions in addressing different types of threats. It specifically focuses on achieving a trade-off between accuracy and efficient use of resources.

IfNot: An approach towards mitigating interest flooding attacks in Named Data Networking of Things

Named Data Networking (NDN) has emerged as a model to accommodate content distribution, security, and mobility. Recently, NDN has been applied to the Internet of Things (IoT), referred to as Named Data Networking of Things (NDNoT). In the rapidly evolving landscape of the NDNoT securing data transmission is paramount. The main purpose and contribution of the research presented in this paper is to safeguard the security vulnerabilities of data transmission in NDNoT. This paper specifically addresses the critical issue of interest flooding attacks in NDNoT. These attacks can disrupt network operations posing far-reaching threats to data integrity and availability. To mitigate these attacks and threats the paper introduces the IfNoT mechanism and evaluates its performance through comprehensive simulations in a realistic and recognized simulator, called Cooja. IfNot identifies the potential interest flooding attacker nodes in the NDNoT environment. It reduces the impact of the attack and the undesirable interest traffic caused by such an attack, which optimizes the network resource utilization at a maximum level. The study also explores the influence of key parameters provided by the IfNoT mechanism. Moreover, the study also identifies optimum settings for these parameters to enhance network utilization. When evaluated using various metrics, including success rate, average latency, and total interest traffic, under different conditions and parameter settings, IfNoT was able to counter the interest flooding attacks effectively. IfNoT mechanism is able to increase success ratio up to 28%, decrease average latency up to 31%, and decrease total interest traffic up to 58%.

Cyber-Secure SDN: A CNN-Based Approach for Efficient Detection and Mitigation of DDoS attacks

Software Defined Networking (SDN) has become popular due to its flexibility and agility in network management, enabling rapid adaptation to changing business requirements, enhancing network performance, and reducing operational costs. However, the ubiquity of internet-based services has given rise to an alarming increase in cyber-attacks, posing serious threats to the security and stability of modern networks. Among these attacks, Distributed Denial of Service (DDoS) attacks have emerged as one of the most devastating, capable of disrupting critical services. Recent studies have shown that Deep Learning (DL) techniques with Software-defined networking have the potential to mitigate these threats effectively. However, existing solutions suffer from issues such as reliance on pre-defined rules and signatures, computational efficiency, low detection rates, and inefficient notification mechanisms, making them ineffective in detecting DDoS attacks. This paper proposes an efficient approach (BRS + CNN) using Balanced Random Sampling (BRS) and Convolutional Neural Networks (CNNs) to detect DDoS attacks in SDN environments. We have applied various mitigation techniques to mitigate these threats, such as filtering, rate limiting, and iptables rule for blocking spoofed IPs. In addition, we introduce a monitoring system that utilizes rate-limiting to oversee blocked IP addresses, ensuring that legitimate traffic is processed efficiently. The proposed model achieves high performance in binary and multi-classification, with an accuracy of over 99.99% for binary classification and 98.64% for multi-classification. Our proposed DDoS detection system not only detects the attack but also sends detailed contextual information to a designated email address. We compare our model with existing literature and demonstrate its superiority using Area Under The Curve (AUC) analysis. Moreover, we evaluated the efficiency and effectiveness of our proposed DDoS mitigation system by conducting a series of experiments across three distinct scenarios: Attack-Free, Attack-No Mitigation, and Attack-Mitigation. These results demonstrate the robustness of our proposed mitigation system in effectively combating DDoS attacks while also safeguarding the seamless continuity of regular network operations.

Efficient virtual power plant management strategy and Leontief-game pricing mechanism towards real-time economic dispatch support: A case study of large-scale 5G base stations

Amidst high penetration of renewable energy, virtual power plant (VPP) technology emerges as a viable solution to bolster power system controllability. This paper integrates a novel flexible load, 5G base stations (gNBs) with their backup energy storage systems (BESSs), into a VPP for power system real-time economic dispatch (RTED). Leveraging BESSs dispatchable capacity, the VPP offers power support and gains economic incentives, where the dispatchable capacity is estimated based on distribution network reliability and gNB availability requirements. Then, an efficient and refined VPP management strategy is proposed, where numerous gNBs are aggregated into limited number of virtual generators (VGs). The VPP dispatchable capacity can be efficiently and accurately evaluated via VGs states. Each VG is assigned a control cost function, enabling optimal control decisions resembling power system RTED, to minimize overall VPP control costs. Finally, a power support and incentive determination mechanism is presented based on the Leontief union bargaining model, ensuring reciprocal transactions between VPP and power system. To solve the Leontief model and address information privacy issues between the two parties, a distributed iterative algorithm is developed. Simulations based on actual data and IEEE 118-bus system illustrate that the proposed approach can smoothen intra-day load profiles, achieving mutual economic benefits for the power system and VPP without compromising the security of 5G network operations.

SIM+: A comprehensive implementation-agnostic information model assisting AI-driven optimization for beyond 5G networks

Forthcoming beyond 5G (B5G) network systems are expected to introduce a new era in the mobile networks, supporting new and challenging use cases and applications. This new era will provide ubiquitous connection of up to billions of devices that are estimated to generate vast amounts of data, paving the way towards a data-driven network system design. In such network design, Artificial Intelligence (AI) will act as a key enabler with regard to network system automation and optimizations. One of the biggest challenges for AI in such complex and dynamic network environments, is the interoperability in terms of seamless exchange and analysis of information between two or more systems. Technological interoperability requires that the format in which data is generated or stored is standardized and that interconnected systems are aware of the nature of transmitted information and are able to analyze it. This paper proposes a novel, comprehensive Information Model (IM), named as SIM+, that extends all across the network, describing different network entities, attributes, capabilities and operations in an implementation-agnostic and standardized way towards assisting AI-driven optimizations. Seven key abstraction layers have been identified in an attempt to hide infrastructure complexities. The adaptability of the proposed SIM+ is showcased through its application in two state-of-the-art AI-driven solutions.

Practicality of in-kernel/user-space packet processing empowered by lightweight neural network and decision tree

Integrating machine learning (ML) into kernel packet processing, such as extended Berkeley Packet Filter (eBPF) and eXpress Data Path (XDP), represents a promising strategy for achieving fast and intelligent networking on generic hardware. This includes tasks like automating network operations and discerning traffic classification, exemplified by intrusion detection systems (IDS) combining Decision Tree (DT) and eBPF. However, the potential of ML-empowered packet processing remains to be fully explored. To ensure the integrity and security of kernel operations, eBPF/XDP programs must adhere to stringent constraints such as the maximum number of jump instructions, maximum stack space, and exclusion of floating-point arithmetic. These constraints pose challenges for implementing more intricate ML techniques (e.g., neural networks (NNs)) within eBPF/XDP programs. In such scenarios, AF_XDP provides an alternative solution by allowing XDP programs to redirect packets to user-space applications, bypassing the network stack. This paper initiates an exploration into fast packet classification through two distinct approaches: (1) an in-kernel approach employing eBPF/XDP and (2) a user-space approach assisted by AF_XDP. Specifically, to tackle the eBPF constraints, the in-kernel NN classifier adopts (1) quantization of trained model in the user space, (2) executing the integer-arithmetic-only NN within the kernel space, and (3) sequential layer operations through tail calls. These approaches are evaluated based on factors including packet processing speed, resource efficiency, and detection performance. Notably, our experimental findings demonstrate that (1) Classifiers relying solely on integer arithmetic, such as NN and DT, significantly reduce inference time while maintaining binary classification performance; (2) The lightweight NN classifier can improve the detection performance for most of attacks in case of the multi-class classification compared to the lightweight DT classifier; (3) In single-core scenarios, the DT-empowered in-kernel method can almost achieve the maximum packets per second (pps), i.e., about 800,000pps, whereas the NN-empowered one exhibits lower pps (i.e., about 450,000pps); (4) In multi-core scenarios, the NN-empowered packet processing can almost achieve the maximum pps with two or more cores in the AF_XDP approach and four or more cores in the in-kernel approaches.

Enhancing network-constrained P2P energy sharing through virtual communities

Peer-to-peer (P2P) exchanges provide opportunities for prosumers to meet their energy needs cost-effectively with the effective utilization of renewable energy sources (RES). Along with the benefits, P2P energy trading also raises issues in distribution network operations. The proposed framework has the potential to handle transactions in regard to network constraints by leveraging the benefits of dynamic utilization-based charges for network usages and power pricing structures. This work proposes a novel P2P energy trading framework comprising virtual communities (VCs) made by grouping buildings located on a particular bus. A cooperative game is formulated for inter- and intra- bus energy trading. A battery energy storage system (BESS) is present in each VC, and a stochastic model is used for coping with the uncertainties related to RESs. In this work, each player’s individual problem is decoupled to achieve equilibrium in a decentralized manner to avoid security and privacy issues. This research focuses on the significant reduction in the net energy cost of the buildings in the presence of uncertain renewable energy generations by taking advantage of the load variability of buildings present on the same and different buses without violating any network constraints and raising any privacy concerns. The proposed framework reduces the building cost by 21.87%.

Non-revenue Water Reduction

SCADA systems are essential for water management in smart cities. They provide real-time monitoring, control, early detection of issues, efficiency improvements, enhanced resilience, and data-driven decision support. By leveraging SCADA technology, water utilities can optimize operations, reduce water losses, ensure a reliable supply, and contribute to sustainable water management in smart cities. Non Revenue Water (NRW) refers to water that is produced and lost before it reaches consumers or generates revenue for water service companies (WSCs). The summary highlights the importance of reducing non-potable water as it leads to increased water availability and revenues for WSCs. This is done by installing flow meters and water pressure measuring devices on the water sources or the entrances and exits of the isolated area, then calculating the amount of water feeding the area and the amount of water accounted for, and from it the amount of non-accountable water can be calculated, and work to reduce it by detecting leakage - Detecting stealth connections and installing water meters that work efficiently. The reduction of commercial losses, which includes issues like inaccurate billing or theft, can significantly improve revenue generation. Similarly, reducing physical/real losses, such as leaks or inefficient distribution systems, allows WSCs to postpone capital investments needed for water source development. To address this issue, departments such as Network Operations, Geographic Information Systems (GIS), Hydraulic Analysis, and the commercial sector must collaborate to estimate and identify the different components contributing to NRW and water loss reduction.