Search

Forecasting electricity usage is essential for boosting operational efficiency and advancing sustainability in buildings. The present work explores how the interval of data acquisition and the choice of modeling technique influence prediction precision for electricity demand in two contrasting building categories: an academic facility providing 15-minute data and an industrial facility providing hourly data. Multiple machine learning algorithms were tested—among them support vector machines (SVMs) with radial and sigmoid kernels, random forests (RFs), and deep neural networks (DNNs)—across various training/validation splits and feature combinations. Findings demonstrate that finer temporal resolution in data collection typically yields better model performance, reflected in lower RMSE, MAPE, and CV metrics, as well as higher R² values. Adding more lagged power consumption variables exerted a considerably stronger beneficial effect on forecast quality than incorporating weather-related variables. Notably, the SVM model equipped with the Radial kernel delivered the most consistent and superior results, proving especially effective at representing intricate nonlinear dependencies. By comparison, the DNN approach, despite acceptable performance on selected measures, exhibited notably higher MAPE values, raising concerns about potential overfitting. Collectively, these observations emphasize the need for deliberate decisions regarding data granularity, predictor variables, and algorithm selection to maximize forecasting reliability and thereby support smarter, more resource-efficient energy management in built environments.

Recent advances in residential automation technologies and the widespread adoption of distributed energy resources (DERs) have dramatically amplified the need for sophisticated energy management strategies that harmonize operational reliability with cost-effectiveness in smart residential microgrids (SRMG). When smart homes fail to coordinate effectively or exchange energy, irregularities in the SRMG load profile emerge, potentially breaching critical technical thresholds. This work presents a fully decentralized architecture for SRMG that accommodates heterogeneous smart homes that actively participate in peer-to-peer (P2P) energy trading. This architecture targets the simultaneous minimization of load profile variability across the microgrid, reduction of household electricity bills, and preservation of occupant comfort levels enabled by P2P exchanges. At the household level, the home energy management (HEM) system is engineered to curtail overall energy expenditure by leveraging available DER capacity to enable P2P transactions and maintain continuous bidirectional links with the SRMG operator (SRMGO). Real-time, ongoing data interchange between SRMGO and HEM units proves indispensable for achieving superior load-profile smoothing in a decentralized setting. The proposed mechanism achieves roughly a 4.25% decrease in load-profile deviations while keeping energy costs unchanged, thereby confirming that decentralized P2P energy exchanges markedly improve both microgrid load balancing and household expenditure stability. Simulations conducted with the general algebraic modeling system (GAMS) software confirm that incorporating P2P energy mechanisms within a decentralized structure satisfactorily meets the SRMG’s technical constraints and the monetary priorities of participating smart homes.

Microgrids provide an effective strategy for delivering energy while keeping expenses to a minimum. Within residential microgrids, individuals with diverse personality traits can collaborate in multiple ways. Additionally, the distinct decision styles arising from these personality differences can have a substantial impact on the success of their joint activities. The present study explores patterns of collaboration among neighbors with a range of personality traits within residential microgrids that form part of a smart-city ecosystem, thereby supporting energy exchange and reducing the total cost of energy provision. The methodology introduced in this work accounts for uncertainties arising from social conduct and organizes joint action through a game-theoretic structure. That structure works toward achieving an efficient and fair division of energy across participating neighbors, simultaneously driving down expenditures, encouraging cooperative behavior, and applying disincentives for non-cooperative conduct in line with each person’s behavioral profile. The suggested technique was tested on a residential benchmark microgrid using the GAMS CPLEX optimizer; two contrasting cases were examined to evaluate how energy storage affects trading decisions. By establishing mean values for discount and penalty rates, the method becomes better suited to diverse microgrid topologies. The analysis further addresses the tension between the utility company’s prices and the most advantageous rates from the neighbors’ perspective. Simulation results indicate that collaborative behavior enables neighbors to meet surplus requirements and can reduce the microgrid’s aggregate operating costs by up to 80%.

Each server in data centers contains multiple fans and various heat-generating components. Factors such as fan speeds, component layout, and workload conditions affect airflow and temperature distribution within the server. Consequently, server thermal management is regarded as a Multi-Input Multi-Output (MIMO) nonlinear control system that cannot be effectively analyzed or controlled using conventional linear system techniques. This study implements a multi-fan thermal control approach for servers by applying a weighting mechanism that assigns distinct weights to each cooling fan, enabling asynchronous adjustment of multiple fans. This is combined with the Evolutionary Strategy (ES) algorithm and carefully designed fitness functions. The proposed system can identify near-optimal weighting combinations within a small number of search iterations, tailored to various workload scenarios. By asynchronously adjusting the fans according to these weightings, the system achieves near-optimal energy efficiency while still satisfying the server’s thermal requirements—specifically, the maximum allowable temperatures for the CPU and PCIe components. Compared with traditional synchronous fan modulation, this asynchronous multi-fan control method reduces the total fan power consumption by an average of 43.1%. It requires searching only 14.2% of all possible weighting combinations across the eight experimental workload scenarios. Moreover, the probability that each identified near-optimal weighting corresponds to the global optimal solution is 47.5%. Experimental results confirm that the proposed asynchronous multi-fan control system successfully meets thermal specifications while delivering near-optimal energy savings for the server. Therefore, the developed approach proves practical and highly effective for substantial energy reduction, without requiring the development of mathematical thermal models or the analysis of extensive datasets. In the future, by fine-tuning the system’s code parameters, it could potentially be adapted to different server architectures. 

The growing integration of renewable sources and the expansion of interconnected grids have heightened power systems’ susceptibility to parametric uncertainties. These include mechanical deterioration, turbine blade damage, reduced system inertia, and deliberate cyber-physical intrusions impacting turbine-governor assemblies, synchronous generators, and interconnecting transmission paths. Left unaddressed, such anomalies can seriously impair frequency and voltage stability, potentially escalating into widespread grid disturbances. While standard observer techniques successfully flag the presence of irregularities, they typically fall short in determining which specific parameter has deviated. The present work introduces a comprehensive and resilient Fault Detection and Isolation (FDI) methodology that can both estimate and accurately localize alterations in several fundamental dynamic parameters: turbine time constant (Tt), governor time constant (Tg), moment of inertia (H), load damping coefficient (D), and inter-area synchronizing coefficients (Tij). The approach combines a mixed H∞/H₂ observer augmented with regional pole-placement constraints—ensuring strong rejection of external disturbances and rapid residual generation—with a subsequent adaptive sliding-mode estimation stage tailored for precise parameter identification and fault classification. Thanks to this cascaded structure, the scheme reliably separates genuine parametric faults from measurement noise and distinguishes among different classes of parameter drift. Extensive simulations on a representative multi-area load frequency control (LFC) benchmark demonstrate the method’s high estimation accuracy and strong robustness across various fault magnitudes and types. In marked contrast to most existing FDI strategies, which are limited to detection, the proposed framework additionally pinpoints the physical or cyber origin of each fault. This added diagnostic capability supplies operators with concrete, decision-ready information and substantially bolsters the fault tolerance and overall dependability of large-scale modern power networks.

The integration of hydrokinetic turbine (HKT) systems relies heavily on power converters, which enable precise control of turbine rotational speed to regulate active power delivered to the grid while providing reactive power compensation. This paper introduces an advanced model predictive control (MPC) strategy designed for maximum power point tracking and output frequency regulation in an HKT system interfaced through a back-to-back converter. The setup comprises a horizontal propeller turbine, a permanent magnet synchronous generator, a rectifier, and an inverter. The proposed control scheme was implemented in MATLAB and validated via simulations, with performance assessed through the system’s state variables. A comparison with a conventional proportional-integral (PI) control method demonstrates that MPC delivers superior transient performance and shorter settling times for high-efficiency operation, while remaining straightforward to implement. Specifically, the MPC controller exhibited a settling time that was 4 times faster than that of the PI controller. 

Designing multi-floor arrangements for biodiesel production facilities that utilize empty fruit bunch (EFB) feedstock represents a computationally intensive, large-scale problem that requires the concurrent assessment of cost, hazard mitigation, and building integrity constraints. The present work proposes a Mixed-Integer Nonlinear Programming (MINLP) formulation tailored to multi-level plant layouts, jointly determining optimal equipment materials, vertical floor allocations, sectional positioning, and passive safeguarding features based on explicit safety quantification. Developed within the General Algebraic Modeling System (GAMS) environment, the model is tackled through a staged decomposition consisting of three sequential phases—(i) choice of construction materials together with load-bearing evaluation, (ii) intra-section multi-floor arrangement, and (iii) full-plant sectional coordination—because solving the full monolithic MINLP violates academic solver license restrictions and does not reach convergence under realistic time constraints. In contrast, the sequential procedure consistently delivers solutions featuring small optimality gaps (overall CPU usage: 22.97 min). Applied to a 1,000 t/d EFB processing scenario involving 57 equipment units distributed across seven functional sections, the resulting layout achieves a 28.9% reduction in total capital expenditure, a 51.97% decrease in required land area, and—when separations follow Dow’s Fire and Explosion Index (F&EI) guidelines including credit for installed devices—a 18.8% drop in Maximum Probable Property Damage (MPPD) before protective measures and a 69.0% reduction once protection is accounted for. This hierarchical decomposition technique shows that highly complex facility layout tasks incorporating formal safety limits can be addressed in a tractable and effective manner, supplying a generalizable methodology suitable for diverse multi-objective design problems encountered in the chemical processing and renewable energy domains.

Reliable short-term forecasting of solar radiation is crucial to ensuring the smooth operation and optimal scheduling of photovoltaic (PV) power systems. At present, cutting-edge encoder–decoder frameworks that leverage satellite remote sensing imagery are the dominant strategy for accomplishing this task. Yet these approaches reveal clear weaknesses, particularly when using longer prediction windows. Under extended horizons, the resulting maps commonly display blurred spatial patterns and noticeable inaccuracies in radiation levels. Such flaws substantially undermine forecast sharpness and trustworthiness, rendering them inadequate for applications requiring very high accuracy. To address these shortcomings, we introduce GAN-Solar — a novel post-processing architecture for improving short-term solar radiation predictions that leverages Generative Adversarial Networks (GANs). The framework adopts a conditional ED-AttUNet as its generator. A carefully designed discriminator equipped with residual blocks, stepwise resolution reduction, and auxiliary conditional signals is trained to separate genuine from synthetic radiation fields. Through this competitive training — steered by a composite loss and a discriminator acting as an adaptive quality metric — the model progressively sharpens prediction fidelity. Evaluations of real summer solar radiation datasets show that GAN-Solar delivers substantial gains in output quality. Compared with the plain ED-AttUNet baseline, it reduces the Root Mean Square Error by about 3.2% and increases the Structural Similarity Index from 0.84 to 0.87. Overall, the method effectively corrects for texture smearing and intensity warping, yielding noticeably crisper, more faithful solar radiation maps.

Ensuring reliable inspection of high-voltage transmission lines remains vital to maintaining smart grids. Nevertheless, human-based inspections are time-consuming, expensive, and dangerous, and even modern detection models frequently fail to detect small insulator flaws concealed within complex outdoor environments. This study proposes YOLOv11-RAH, a compact network architecture designed specifically for edge devices in smart inspection setups. It integrates the YOLOv11 backbone with a recurrent attention head that progressively enhances multi-scale feature representations via depthwise gated convolutions and terminates refinement upon reaching convergence, thereby boosting localization accuracy with almost no increase in inference time. Robustness to changes in perspective, lighting conditions, and object scale is further strengthened by a four-phase data augmentation protocol that includes geometric distortions, photometric adjustments, Mosaic blending, and random cropping. Evaluation was conducted on a merged insulator dataset compiled from two refined public benchmarks plus a fresh private UAV-collected corpus, capturing varied real-world outdoor scenarios and defect patterns. Broad comparative experiments against alternative detection approaches reveal steady performance gains from the proposed architecture. Detailed ablation analyses further verify the value of the novel attention mechanism and the complete augmentation strategy. In particular, YOLOv11-RAH obtains an approximate 5 percentage point gain in mAP compared with the standard YOLOv11n model on the aggregated public sets PTL-AI Furnas and CPLID, as well as on the private UAV collection AIDD, illustrating excellent cross-source generalization. Overall, these outcomes demonstrate that recurrent attention paired with purpose-built augmentation constitutes a practical and robust strategy for fully automated detection of insulator defects in intelligent power-line monitoring systems.

Wind power (WP) is a Renewable Energy Source (RES) that has experienced remarkable growth as society continues to seek environmentally friendly energy alternatives. This study primarily explores Predictive Maintenance (PM) of Wind Turbines (WT). It evaluates the potential advantages of Wind Energy (WE) when integrated with the Internet of Things (IoT) and Wireless Sensor Networks (WSN). The research proposes an IoT-WSN framework for PM, structured into three key stages: the initial stage involves data acquisition via sensors; the second stage involves data transmission via an internet connection; and the third stage involves data analytics performed in a cloud computing environment. For PM analytics, this work presents a Predictive Maintenance Convolutional Long Short-Term Memory (PM-C-LSTM) model that integrates the spatial feature-extraction strengths of a Convolutional Neural Network with the time-series modeling capabilities of LSTM networks. The PM-C-LSTM model combines a CNN for spatial pattern detection with LSTM networks for sequential data processing, without compromising the precision of WT-PM. Additionally, a Failure Sample Generator model is incorporated to quantify soft failure and hard failure elements, thereby enhancing the predictive performance of the Machine Learning (ML) approach. The model was deployed on a Wind Farm (WF) on the Qinghai-Tibet Plateau, using data collected over 16 months. Comparative evaluations against several conventional models, based on multiple performance metrics, demonstrate that the PM-C-LSTM model delivers superior PM capabilities. The experimental results suggest that the combined use of IoT and ML has strong potential to advance PM strategies for WT, ultimately contributing to greater efficiency and sustainability in WE production.

DNA microarray technology relies on a chip containing thousands of DNA probes to simultaneously quantify the activity levels of many genes. The resulting gene expression data, typically arranged in matrix form, serves as the foundation for pattern-recognition techniques that separate samples taken from healthy subjects from those obtained from cancer patients. Nonetheless, extracting genuinely informative biomarkers from such datasets remains extremely difficult due to the curse of dimensionality and the substantial presence of uninformative or noisy genes. This study presents an effective gene selection framework that combines the powerful Minimum Redundancy Maximum Relevance (MRMR) filter with a newly designed hybrid metaheuristic. The proposed optimizer merges an enhanced version of the Marine Predator Algorithm (MPA) with a crossover mechanism, yielding the so-called MPAC algorithm. MPAC is tailored to identify a small yet highly discriminative set of genes that dramatically improves cancer classification accuracy. Classification is performed using the k-nearest neighbors (k-NN) classifier. The main strength of MPAC resides in its marked improvement of the exploration and exploitation capabilities of the original MPA population. It systematically identifies optimal gene subsets suitable as cancer biomarkers while carefully balancing global search (exploration) and local refinement (exploitation). The proposed method was comprehensively benchmarked on nine widely recognized microarray benchmark datasets. Its classification performance was rigorously compared with several standard and recently published optimization-based approaches. Results indicate that MPAC achieves superior accuracy across most datasets and delivers very competitive results on the remaining datasets.

This study addresses the problem of cost-optimal expansion planning for rural radial distribution networks via a mixed-integer nonlinear programming (MINLP) formulation that jointly determines feeder routing and conductor type selection. The developed method was evaluated using standard 9-node and 25-node test networks, with performance benchmarked against minimum spanning tree (MST)-based procedures and two metaheuristic techniques (sine-cosine algorithm and tabu search). The application of the MINLP approach led to significant reductions in overall expenditure. In the 9-node test case, the total cost was reduced from USD 131,819.33 (obtained via MST-TSA) to USD 77,129.34, resulting in savings of USD 54,689.99, equivalent to 41.48%. Energy loss costs alone decreased from USD 111,746.73 to USD 63,764.12, a drop of USD 47,982.61 or 42.94%. In the 25-node network, overall costs fell by more than 65%, from USD 371,516.59 to USD 128,974.72, while energy loss expenses decreased by USD 210,057.16 (61.06%). Although conductor-related capital expenditure increased under the MINLP solution, the strategy generated significant long-run economic benefits by markedly reducing operating expenses. In contrast to conventional strategies that address topology definition and conductor sizing in separate stages, the proposed framework integrates these decisions, thereby ensuring globally optimal configurations. These outcomes highlight the method’s ability to scale and its practical value for strategic, long-horizon planning in sophisticated distribution grids. All numerical experiments were conducted in Julia (v1.10.2), leveraging JuMP (v1.21.1) together with the BONMIN solver.

The emergence of 5G technology is revolutionizing the development of smart cities by providing unparalleled speed, ultra-low latency, and massive device connectivity. These advancements enable seamless integration of IoT devices, real-time monitoring systems, and innovative urban solutions. This paper investigates the role of 5G in addressing key urban challenges—such as network congestion, energy efficiency, and data security—while emphasizing its transformative potential for advancing smart city architectures. Particular attention is given to integrating 5G with real-time digital twins, which bridge the physical and digital worlds to optimize urban operations, improve resource allocation, and enhance public safety. Despite its promise, 5G deployment faces obstacles including high infrastructure costs, substantial energy consumption, and limited signal coverage. This study reviews current trends, existing implementations, and emerging issues surrounding 5G in smart cities, offering perspectives on its limitations and potential mitigation strategies. It underscores the importance of collaboration among stakeholders to fully unlock 5G’s capabilities and develop scalable, secure, and sustainable smart city solutions. 

Precise prediction of load profiles—most notably the accurate identification of peak demand—remains difficult owing to the highly variable and unpredictable patterns of energy use. This work evaluates three forecasting approaches: Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and a hybrid ensemble combining SVR, Gated Recurrent Units (GRU), and Linear Regression (LR) to generate 24-hour-ahead load forecasts. Individual load categories—household (HH), heat pump (HP), and electric vehicle (EV)—were treated together using full one-year consumption records. The research focuses on improving the reliability of load-profile predictions by comparing LSTM, SVR, and the proposed ensemble across HH, HP, and EV demand patterns. An innovative correction procedure is presented that refreshes the forecast every 8 hours, thereby improving forecast trustworthiness. Results underscore the value of deep learning techniques for better anticipating electricity demand, with particular strength in recognizing peak events, which in turn supports smoother and more cost-effective power system management. Both graphical assessments and quantitative validation metrics were analyzed, covering model behavior during off-peak hours, peak hours, and across the complete daily cycle. Across the tested approaches, LSTM delivered marginally stronger overall metrics in the majority of cases and demonstrated especially good performance at detecting peaks. That said, the hybrid model slightly outperformed LSTM when predicting EV-specific power demand, achieving an on-peak mean absolute percentage error (MAPE) of 21.45%, compared with 29.24% (SVR) and 22.02% (LSTM). Even so, graphical inspection clearly illustrated LSTM’s superior peak-capturing ability. This advantage was also evident in the on-peak mean absolute percentage error (MAPE) and symmetric mean absolute percentage error (SMAPE) values, where LSTM improved by roughly 3–5% relative to both SVR and the hybrid model. In the final application, LSTM was used to forecast next-day load profiles based on real measurements collected from four separate grid areas and consistently demonstrated excellent peak-detection capability, with MAPE below 10% across most of those datasets.