Securing 5G network slicing for the smart grid network

The proliferation of distributed energy resources requires advanced coordination mechanisms for Local Energy Markets (LEMs) to maintain grid stability and economic efficiency, a challenge ill-suited to traditional centralized control. A significant research gap exists due to the lack of simulation frameworks that cohesively integrate realistic, decentralized market dynamics, physical grid constraints, and advanced Multi-Agent Reinforcement Learning (MARL) capabilities, especially for studying emergent coordination under partial observability. This paper introduces a novel, open-source MARL simulation framework for studying implicit cooperation in LEMs, modeled as a decentralized partially observable Markov decision process and implemented as a Gymnasium environment for MARL. Our framework features a modular market platform with plug-and-play clearing mechanisms, physically constrained agent models (including battery storage), a realistic grid network, and a comprehensive analytics suite to evaluate emergent coordination. The main contribution is a novel method to foster implicit cooperation, where agents’ observations and rewards are enhanced with system-level key performance indicators to enable them to independently learn strategies that benefit the entire system and aim for collectively beneficial outcomes without explicit communication. Through representative case studies (available in a dedicated GitHub repository in https://github.com/salazarna/marlem ), we show the framework’s ability to analyze how different market configurations (such as varying storage deployment) impact system performance. This illustrates its potential to facilitate emergent coordination, improve market efficiency, and strengthen grid stability. The proposed simulation framework is a flexible, extensible, and reproducible tool for researchers and practitioners to design, test, and validate strategies for future intelligent, decentralized energy systems. • A novel, open-source, Gymnasium-compliant multi-agent reinforcement learning (MARL) framework for Local Energy Markets (LEMs) is presented. • Uniquely unifies modular, auction-based market mechanisms and high-fidelity physical grid constraints (losses, congestion) in a single testbed. • A novel mechanism to foster and quantify implicit cooperation in MARL agents via shared key performance indicators signals in observations and rewards. • Framework enables the first true, like-for-like comparison of fully centralized (CTCE), fully decentralized (DTDE), and hybrid (CTDE) MARL paradigms for LEMs. • Illustrative results showcase the framework’s capability: strategic asset deployment (batteries) can reduce price volatility and increase P2P trading.

Introduction Recent years have witnessed an increasing number of Internet of Things devices (IoTDs) deployed in power grids to monitor bidirectional information and power transfer, transforming them into smart grids. The densification of IoTDs in smart grids demands communication solutions that are simultaneously secure against eavesdropping and energy-efficient for sustainable operation. Methods This article proposes an unmanned aerial vehicle (UAV) and reconfigurable intelligent surface (RIS)-assisted framework in smart grids that maximizes worst-case secrecy energy efficiency via joint optimization of the UAV’s trajectory, beamforming, and phase shifts of RIS. A twin attention-driven deep reinforcement learning algorithm, TAMRRTD3, is developed, featuring attention-based state representation and regret-aware reward design to enhance learning accuracy and convergence. Results and Discussion Simulation results indicate that the proposed algorithm achieves a faster convergence rate and enhanced secrecy energy efficiency than the benchmark algorithms.

Grid networks are electrical distribution infrastructures that are typically represented as essential for society, however, constructing new power lines often creates conflict. Developing a critical-spatial approach to social acceptance, this research defined such conflicts as underpinned by spatially-embedded and multi-scalar power asymmetries between different stakeholders and organisations. Attending to the spatial dimensions of power, we extend the critical social acceptance literature in three ways. First, by investigating how stakeholders, technologies and discourses are embedded across spaces, places and scales. Second, by assessing the performative dimensions of imaginaries used to legitimise or contest power line proposals. Third, by adopting a methodological approach that integrated participatory GIS into semi structured interviews. We use the Munga-Hamra power line proposal in Sweden as a case study. Thematic analysis revealed how the powerline was legitimated by an ‘elite’ coalition of private and public sector stakeholders who ‘localised’ a national socio-technical imaginary in regional and local imaginaries of industrial growth. The power line was contested by a coalition of rural stakeholders including affected landowners, residents and tourism businesses who invoked imaginaries of a ‘rural idyll’ to argue for undergrounding the line. Both coalitions legitimated their positions by ‘othering’ imaginaries held by the adversary coalition (e.g., urban vs. rural). Moreover, we identified a third set of ‘neutral’ actors who strategically avoided adversarial positions and coalition membership. The findings illustrate the valuable contributions that critical-spatial approaches to social acceptance research can make; and the significance of attending to stakeholders with overlooked ‘neutral’ positionalities within such conflicts.

Digitalization plays a critical role in the transformation of electricity distribution systems, enabling greater efficiency, flexibility, and integration of renewable energy sources. However, Distribution System Operators (DSOs) often face regulatory and economic barriers that hinder investments in digital technologies. This study adopts a qualitative System Dynamics (SD) approach to explore the complex, feedback-driven interactions between regulatory incentive structures and DSOs’ investment decisions in digitalization. Focusing on the Australian regulatory framework, the SD model was developed and validated through expert interviews with representatives from National Regulatory Authorities, academia, and industry. The analysis identifies elevencritical feedback loops that either reinforce or obstruct digital investment decisions. These loops reveal how incentive structures, cost-recovery rules, information asymmetries, and risk perceptions interact to create self-reinforcing dynamics that often favor conventional grid expansion over digital alternatives. The model provides a structured mapping of regulatory feedback mechanisms, and serves as a diagnostic tool to support policy design by highlighting where regulatory interventions can be most effective. The findings show that incentive structures, investment choices, and grid-performance outcomes are linked through feedback dynamics that shape long-term infrastructure trajectories, potentially locking systems into conventional asset expansion or enabling digitally driven modernization. This study lays the groundwork for future research by offering a structured method to trace and compare regulatory-investment dynamics, and by providing actionable insights for designing more coherent incentive schemes that support DSOs’ digitalization efforts in diverse regulatory settings. • Economic incentives to drive power grid digitalization are currently insufficient. • A system dynamics model is used to unveil regulatory factors hindering digitalization. • Impacts of CAPEX-OPEX, performance and innovation schemes on investments are analyzed. • Eleven key feedback loops impacting digitalization are identified and validated. • Regulatory tools are proposed to redirect incentives and support digitalization.

In the era of information, cybersecurity of communication networks of power grids has received increasing attention. In this paper, the important attributes are extracted from the alarm data of the multiple sources of the communication network of power grids. Based on these attributes, after time series construction, using multi-step deep learning and data dimensionality reduction techniques, spatiotemporal feature maps of the data are created. The security posture attributes of the communication network components of power grids are discretized using the 3σ criterion, and the Bayesian network is constructed to infer and generate the probability of security postures of network components. The results show that when attacks occur, the correlation of alerts varies between [0.56, 0.89], which shows considerable accuracy. The maximum security posture score of nodes exceeds 200 in all attack phases, showing a decreasing trend.

Renewable energy has emerged as a critical component in the global pursuit of sustainable development and carbon neutrality. Despite its potential, the inherent challenges associated with renewable energy sources, such as intermittency, variability, and storage limitations, necessitate innovative solutions to enhance efficiency and reliability. The growing world demand for energy requires the incorporation of renewable energy into smart grids to create effective and efficient power systems. Through the utilization of sophisticated machine learning and combining traditional time-series methods and machine learning model tools, we conclude that the use of AI facilitates a speedy generation of better forecasting and dependency on renewable energy resources. As the demand for energy in the world continues to grow, the integration of renewable energy into smart grids has become essential for building efficient and sustainable power grid networks. In the study, artificial intelligence has become a transformative tool. Using machine learning techniques along with traditional techniques has promoted greater confidence and dependency on renewable energy resources. Overall, our findings support the statement that AI-based renewable energy systems can help integrate the transition to more sustainable energy resources by enhancing grid performance, reducing carbon footprints, and improving energy access. This study also reveals the significant role of AI in enhancing global sustainable goals for energy systems. This research also contributes to policymaking by evaluating AI’s potential in shaping sustainable energy strategies, ensuring a reliable transition to clean energy.

The evolution of conventional power systems into smart grids demands intelligent and efficient energy management solutions. Accurate load forecasting is essential for optimal generation scheduling, demand-side management, and system reliability. However, traditional methods often fail to capture the nonlinear and time-varying nature of electrical loads. This work proposes a machine learning–based approach for local load forecasting and grid stability enhancement. Techniques such as Artificial Neural Networks (ANN) and Support Vector Machines (SVM) are utilized to analyze historical load and weather data for improved prediction accuracy. In addition, a predictive control strategy is implemented to maintain system stability by mitigating voltage fluctuations, frequency deviations, and load imbalances. The proposed model dynamically adjusts control actions such as demand response and load shedding. Simulation results demonstrate reduced forecasting errors (MAE, RMSE) and improved voltage and frequency regulation, ensuring enhanced reliability, efficiency, and stable operation of modern smart grid systems. Keywords: Smart Grid; Machine Learning; Load Forecasting; Grid Stability; Predictive Control.

The effective routing of entanglement over a quantum network is a fundamental problem in quantum communication. The distribution and reshaping of multipartite entanglement over a quantum network requires scalable protocols that adapt to the underlying topology. Graph states provide a convenient framework for this challenging task, as they encode global entanglement in a structured way that can be locally manipulated to produce a variety of target states, without requiring additional long-distance quantum operations. In this paper, we propose graph-state-based routing protocols for sharing GHZ states, achieving larger sizes than those achieved in the existing works for given network topologies. For this improvement, we consider tree structures connecting the users participating in the final GHZ states, as opposed to the linear configurations used in the earlier works. In particular, for grid networks, we show special constructions of such trees that achieve larger GHZ states than the prior works. Moreover, if the user nodes along which the entanglement is to be routed are pre-specified, a strategy is proposed to accomplish this routing.

This research presents a comprehensive framework for optimizing Electric Vehicle (EV) charging infrastructure along the Lake Michigan circuit (LMC) in Michigan to support ecotourism, considering both slow charging at destinations and fast charging along the corridor. The framework identifies the optimum location and number of Level 2 chargers and Direct Current Fast Chargers (DCFC), using heuristic algorithms. The study evaluates infrastructure planning based on four key objectives: (1) minimizing overall charging infrastructure costs, (2) reducing grid network upgrade costs, (3) providing an acceptable level of service to long-distance travelers using DCFCs by minimizing queuing delays and deviations from their intended routes, and (4) minimizing unserved charging demand at Level 2 chargers, which reduces redirection to DCFC and consequently mitigates battery degradation. The integration of Level 2 and DCFC networks facilitates strategic investment by effectively managing charging demand, allowing unserved Level 2 demand to be accommodated at DCFC stations while adhering to budgetary constraints. The results show that increasing the budget from $15 to $20 million reduces user inconvenience by 47%, while a further increase to $25 million yields an additional 18% reduction. Additionally, increasing users’ value of time from $13 to $36 per hour results in a 50% reduction in average queuing time.

Abstract Expanding electricity access cost-effectively requires strategies that account for spatial heterogeneity in demand, resource availability, and proximity to infrastructure. However, many existing studies oversimplify electrification planning by applying binary rural-urban categorizations and neglecting productive and institutional electricity loads. This study developed a long-term electrification plan at the settlement level, utilizing the Open-Source Spatial Electrification Tool to identify the least-cost solutions among grid extension, mini-grids (MGs), and standalone solar (SA PV) systems. Settlements were delineated by aggregating the High-Resolution Settlement Layer (~30 m resolution) and then enriched it with georeferenced resource data (solar irradiation, wind speeds, hydropower potential) and existing grid networks. Using a myopic optimization approach across three distinct periods (2021–2030, 2030–2040, and 2040–2050), the study analyzed multiple scenarios developed by combining varying electricity demand and grid generation costs. Under a low grid generation cost scenario, grid extension is the least-cost option for more than 82% of the population by 2030, though its share declines slightly in later periods. Under a high grid generation cost scenario, MGs become competitive for about 26% of the population by 2050. SA PV systems emerge as the least-cost option for over 16% of the population in both scenarios by 2030 but become less competitive in later periods. The findings emphasize the need for integrated national planning that combines grid expansion with MG deployment, while gradually phasing out SA PV systems. This approach accelerates the deployment of solutions tailored to local contexts, directly contributing to the achievement of Sustainable Development Goal 7.

Urban traffic congestion leads to frequent vehicle start-stop events and low-speed operation, which is one of the primary drivers of carbon emission growth. To address the problems of multi-objective conflict, training instability, and inadequate carbon emission modeling in existing traffic signal control methods for carbon emission optimization, this paper proposes a deep reinforcement learning signal control algorithm for carbon emission optimization. This method constructs a carbon-emission-aware dynamic reward mechanism and achieves collaborative optimization of traffic efficiency and emission reduction objectives through adaptive weight adjustment; Lagrange multiplier method is introduced to embed the carbon emission threshold as an explicit constraint into the strategy learning process to ensure that the emission level is controlled within an acceptable range; For multi-intersection scenarios, a distributed collaborative control framework based on parameter sharing and neighborhood information interaction is designed to enhance the model's ability to perceive the spatial propagation characteristics of traffic flow. Based on the SUMO simulation platform, experimental validation is conducted in three scenarios: a single intersection, a 4×4 grid network, and a real-world urban road network. The results show that compared with PPO algorithm, the average carbon emissions of this method are reduced by 11.3% to 12.8%, average delay is reduced by 15.7%, average speed is increased by 9.6%, and the comprehensive performance index is improved by 12.2%; During the training process, the fluctuation of strategy is reduced by about 50%, and the degradation rate of generalization performance is reduced by 34.2% compared with the comparison method. This study provides an effective intelligent solution for low-carbon-oriented urban traffic signal control.

Freight-dominant port collection and distribution road networks exhibit strong spatial congestion, early spillback, and heterogeneous vehicle dynamics that challenge conventional traffic signal control strategies. Although Max-Pressure (MP) signal control provides strong decentralized stability properties, its classical queue-based formulation lacks sensitivity to incipient spatial congestion and performs poorly when heavy-duty vehicles (HDVs) dominate traffic composition. This paper proposes a gain-modulated Max-Pressure (Gain-MP) control framework, in which conventional pressure computation is augmented by an occupancy-dependent feedback gain that dynamically adjusts phase priorities according to real-time spatial congestion states and current right-of-way conditions. Without altering the decentralized structure of MP, the proposed method introduces a nonlinear feedback mechanism that enhances system responsiveness to congestion formation while suppressing excessive phase switching. The approach is evaluated using microscopic simulation on a signalized grid network representing port access corridors under time-varying demand and high HDV penetration. Results demonstrate that the dynamic Gain-MP controller performs better than classical queue-based MP, PCU-weighted MP, and fixed-time control. Moreover, constant-demand experiments indicate that the dynamic Gain-MP controller maintains bounded vehicle accumulation over a wider empirical demand range than the benchmark MP-based methods under the tested settings.

Energy consumption forecasting is crucial to enhance energy distribution, planning, and smart grid control. Energy and especially electricity demands are perpetually varying because of urbanization, climate change, and due to digitalization, which makes the prediction of the consumption patterns of utility consumption even more difficult, as utility providers struggle to maintain the maximum precision in their forecasts. Current conventional approaches to forecasting, like ARIMA, often fail to give accurate results, either because they do not perfectly capture spatial aspects of energy data, or do not model long-term temporal aspects of energy data. In addition, newer methods in deep learning, like LSTM and GRU, may also prove unable to capture long-term temporal trends as well. In addition to that, poor model tuning and minimal feature engineering make the models less reliable and less generalizable. They did not have any attention mechanisms, in addition to weak hyperparameter tuning, which led to increased errors in making predictions and higher training times. As a way to overcome such gaps, in this research, a recently conceived hybrid deep learning framework has been deployed, which is a unification of Convolutional Neural Network (CNN) to accomplish feature extraction, Bidirectional LSTM (BiLSTM) to learn a sequence, and Genetic Algorithm (GA) to optimize hyperparameters, which is referred to as CBG-EnergyNet. The model takes advantage of real-world energy data collection and uses complete data preprocessing, sliding windows calculation of the function that uses the features, and large optimization topics such as Adam and Bayesian tuning as well. A number of performance indicators were used to test the proposed model and compared to such models as ARIMA, LSTM, GRU, and CNN-LSTM. CBG-EnergyNet: MAE: 7.83, RMSE: 10.12, MAPE: 7.05%, R 2 Score: 0,93, Training Time: 11.5 s. The outcomes are sufficient evidence that this model helps demonstrate better performance than the measures of the existing methods in all key metrics. The CBG-EnergyNet model presents a very important breakthrough in energy consumption prediction since the combination of spatial and temporal learning proposes a very considerable improvement in estimation performance of energy consumption predictions by optimizing hyperparameters. It provides high accuracy and is hence a very important practical tool for energy planning in the real world, especially in a smart grid network and the system of demand-side management as well. The potential of the model is an opportunity to be applied in large-scale energy in the future due to its generalizability as well as the limited computational demands.

Urban road networks frequently operate in an oversaturated state during peak hours, where traditional traffic signal control strategies, predominantly grounded in the assumption of fully rational user behavior, fail to capture the bounded rationality inherent in drivers’ route choice decisions under congestion. To address this gap, this paper proposed a novel integrated framework that couples evolutionary game theory (EGT) with dynamic signal control, leveraging the Macroscopic Fundamental Diagram (MFD) for real-time feedback between network-wide traffic states and individual decision-making. Specifically, we model drivers within a control zone as a population choosing between two bounded-rational strategies: “waiting straight” versus “detouring”. A replicator dynamics model governs the evolution of strategy adoption, with payoffs dynamically modulated by the MFD to reflect congestion-dependent travel costs. This behavioral layer is embedded within a receding horizon control (RHC) architecture that optimizes green splits and cycle lengths in real time to minimize total zone-wide delay, solved via Particle Swarm Optimization (PSO). Extensive simulations were conducted on a 6 × 6 grid network in SUMO under high-demand conditions (network saturation, approx. 0.92). Results demonstrate that the proposed method reduces average vehicle delay by 18.7% (from 142.8 s to 116.8 s), decreases queue spillback occurrences by 32.4%, and achieves convergence to an evolutionarily stable state (ESS) within 25 minutes, outperforming fixed-time, adaptive MAXBAND, and multi-agent deep reinforcement learning (MADDPG) baselines. This work establishes a closed-loop paradigm for behavior-aware, state-responsive traffic management in severely congested urban environments.

Consequent upon the inestimably magnificent rise in the necessity to considerably minimize the worrisome menace of global dependency on fossil fuels (such as coal, oil and gas), combat the pollution caused by green house gas emission emanating from same and lead a crusade against energy insecurity; the renewable energy sources (RES) became a panacea to the incessant imbalance between the ever- increasing demand and meagre supply of energy throughout the entire universe. Nevertheless, the output of RES is characterized with some unpleasant traits which include intermittency coupled with variability and unpredictability since it is largely constrained by annual weather pattern thereby inflicting a very severe injury on transient and steady state stability, reliability and profitability index. Thus, the certainty that this attributes do not only possess a gigantic capability to render synchronization futile but also initiate regular system collapse in the grid network cannot be over-emphasized, especially if the necessary precautionary measures are not taken into consideration. Therefore, this research work provides a compact review on the impacts of integration of large scale renewable energy sources into grid-connected power system. The methodology would involve an elucidative investigation of the associated benefits and obstacles after which possible mitigations to the challenges are accorded an extensive analysis while useful inferences are drawn meticulously leading to qualitative conclusions and useful recommendations from the results and findings so obtained.

Power transformers are critical assets in regional electricity infrastructure, and their unexpected failures frequently trigger cascading outages with severe economic consequences. Traditional fault diagnosis approaches, including dissolved gas analysis (DGA) and periodic physical inspections, remain inadequate for proactive real-time monitoring across large and topologically complex grid networks. This paper proposes a spatiotemporal graph network (STGN) framework that jointly models the topological structure of a regional power grid and the temporal dynamics of transformer operational data to achieve early failure prediction. The architecture integrates spatio-temporal convolutional blocks, each comprising temporal gated convolution layers flanking a spatial graph convolution layer with gated linear unit activations, to capture both spatial propagation patterns between interconnected devices and time-varying deterioration signals at individual nodes. Panoramic state information, including dissolved gas concentrations, load data, and qualitative maintenance records, is encoded through sequential LSTM processing to support multi-horizon failure probability estimation. Experiments on a real-world regional transmission dataset demonstrate a precision of 91.4%, recall of 89.7%, and F1 score of 90.5%, surpassing support vector machine, LSTM, and standard convolutional neural network baselines by margins of 8 to 17 percentage points. Performance comparison across Correlation, CSI, FAR, and POD metrics at multiple prediction horizons confirms the sustained accuracy advantage of the spatiotemporal formulation over non-graph baselines.

With the rapid development of wireless communication networks, the frequency assignment problem for wireless networks has been transformed into a graph labeling problem: specifically, each base station is represented by a vertex in an undirected graph, and vertices that may cause interference are connected by edges, with adjacent vertices unable to use the same frequency. However, determining the frequency assignment for an arbitrary graph is an NP-hard problem. Therefore, based on an exploration of grid network models, this paper focuses on the labeling problem of the cylindrical gird network with fan subgraph model [Formula: see text] where [Formula: see text] and [Formula: see text], that is, the Cartesian product of the [Formula: see text]-order fan graph and the [Formula: see text]-order cycle. First, we present lower bounds of radio labeling and several results for this class of network models. Second, we label the vertices of this special graph and determine the optimal number. Finally, through numerical comparisons and application examples, experimental data demonstrate that compared to existing Cartesian product models of cycle and cycle, complete graph and cycle, the topological model designed in this paper has higher optimization under the same number of vertices. Specifically, the Cartesian product model of the fan graph and cycle requires fewer radio labelings.

Assessing the holistic performance of power networks under hazardous events is critical to ensuring a reliable and resilient power supply. While various research efforts have been made to achieve this objective, significant gaps remain. First, much of the existing literature emphasises either component-level or system-level performance, with relatively fewer studies explicitly integrating both perspectives in a unified framework. Second, given the computational intensity of resilience assessment, the development of efficient algorithms is essential to enable timely and effective post-disruption recovery strategies. Third, few studies provide detailed methodologies for developing GIS-based frameworks with graphical user interfaces that support practical decision-making. To address these research gaps, this study makes the following contributions. First, we introduce a novel component importance measure, termed the Conditional Probability Deaggregation Measure (CPDM), which facilitates comprehensive assessment at both the component and system levels. Second, we propose the ‘keepx’ algorithm, designed to identify optimal recovery sequences efficiently, thereby enabling effective evaluation of the resilience performance of power grids during the post-disruption recovery process. Third, we incorporate a GIS-based platform to operationalise a modular framework for resilience assessment of power grid networks. While not intended as a standalone novelty, the GIS integration enhances the practical applicability of the framework by enabling spatial visualisation and supporting decision-making for both researchers and practitioners. Application of the framework to the IEEE 9-bus system subject to seismic hazards demonstrates the framework’s practical utility, offering stakeholders proactive insights to enhance the power grid’s resilience.

In order to create a safe and healthy working environment in mines, an issue that urgently needs to be addressed is the rapid discharge of high concentrations of toxic and harmful pollutants after blasting. This paper proposes a deep well rapid purification system based on the combination of nanobubble water spray and water bath/wire mesh carbon, and conducts single-variable optimization tests on the parameters of micro-nano bubble water and the atomizing nozzle. The wet spray fiber grid and carbon adsorption network form in sequence and verify the purification experiment under the clear optimal parameters. The results show that the micro-nano bubble water is used as the spray medium, and a high-pressure nozzle with a diameter of 0.4 mm is also used. The water supply pressure of the nozzle is 3.0 MPa, the wet spray fiber grid uses a double-layer 10-mesh metal wire, and the carbon adsorption network uses 5 mm activated carbon fiber cotton as the optimal parameter for the deep well rapid purification system. Under these conditions, the efficiency of total dust and exhalation dust reduction is 72.90% and 79.17%, respectively, and the purification efficiency of CO, H2S, and SO2 reaches 84.39%, 78.75%, and 55.54%, respectively. This study provides reference data for efficient pollution reduction in mines and has high practical value.