Search Results (145)

Local energy systems (LESs) are becoming larger and more heterogeneous as distributed energy resources, electrified loads, and active prosumers proliferate, increasing the need for reliable coordination of operation, markets, and community governance. This Perspective synthesizes recent literature to map how artificial intelligence (AI) supports forecasting and situational awareness, optimization, and real-time control of distributed assets, and community-oriented markets and engagement, while arguing that adoption is limited by system-level credibility rather than model accuracy alone. The analysis highlights interlocking deployment barriers, such as governance-integrated explainability, distributional equity, privacy and data governance, robustness under non-stationarity, and the computational footprint of AI. Building on this diagnosis, the paper proposes principles-as-constraints for sustainable, trustworthy LES AI and a deployment-oriented validation and reporting framework. It recommends evaluating LES AI with deployment-ready evidence, including stress testing under shift and rare events, calibrated uncertainty, constraint-violation and safe-fallback behavior, distributional impact metrics, audit-ready documentation, edge feasibility, and transparent energy/carbon accounting. Progress should be judged by measurable system benefits delivered under verifiable safeguards. Full article

Virtual reality (VR) provides immersive environments that resemble real-world consumption settings, enabling realistic analysis of consumer responses to advertisements. Therefore, VR has been increasingly adopted in marketing. Visual attention is a key indicator of advertising effectiveness, and neuromarketing approaches using eye-tracking are widely used to overcome the limitations of self-report measures by providing objective insights into attentional processes. However, most previous studies have focused on static retail environments, leaving a research gap in understanding advertising effectiveness in dynamic road traffic contexts. Guided by selective attention theory, this study addresses this gap by integrating VR and eye-tracking to examine how advertisement placement under different traffic conditions influences visual attention and recall. A real-time eye-tracking measurement system was developed, and fixation duration, fixation count, and recall were used as evaluation metrics. The results showed significant differences across advertisement placement types. Advertisements positioned in front of buildings during stops elicited the highest levels of visual attention and recall, indicating that attention is greater when users are stationary than when riding. These findings indicate that cognitive resources shift from traffic-related tasks to advertisements as cognitive load decreases, highlighting the effectiveness of integrating VR and eye-tracking to objectively evaluate advertising outcomes in dynamic environments. Full article

Smart grids face significant challenges in coordinating demand-side management (DSM), dynamic pricing, data aggregation, and network feasibility in real time. To address this, we propose H-EMOS-Lite, an adaptive, multi-layer heuristic framework that integrates these components into a unified, real-time optimization loop. Evaluated on fully reproducible generated demand, price, and grid datasets based on realistic residential energy systems, H-EMOS-Lite achieves a 2.1% reduction in peak load and completes a full 24 h (96-interval) optimization for 100 households in under 0.25 s, demonstrating its suitability for near-real-time residential energy systems. The framework outperforms three baselines—Independent DSM, Sequential Optimization, and Particle Swarm Optimization (PSO)—by effectively balancing energy cost, peak load reduction, and temporal smoothness of the aggregate load profile, while avoiding abrupt, unsynchronized load shifts that induce secondary peaks—common in uncoordinated approaches. By embedding physical feasibility and cross-layer feedback directly into the optimization loop, H-EMOS-Lite enables scalable, interpretable, and deployable coordination for smart distribution systems. Full article

Accurate, real-time monitoring of meat freshness is essential for reducing food waste and safeguarding consumer health, yet conventional methods rely on costly, laboratory-grade spectroscopy or destructive analyses. This work presents a low-cost electronic-nose platform that integrates a compact array of metal-oxide gas sensors (Figaro TGS2602, TGS2603, and Sensirion SGP30) with a Gaussian Process Regression (GPR) model to estimate a continuous freshness index under refrigerated storage. The pipeline includes headspace sensing, baseline normalization and smoothing, history-window feature construction, and probabilistic prediction with uncertainty. Using factorial analysis and response-surface optimization, we identify history length and sampling interval as key design variables; longer temporal windows and faster sampling consistently improve accuracy and stability. The optimized configuration (≈143-min history, ≈3-min sampling) reduces mean absolute error from ~0.51 to ~0.05 on the normalized freshness scale and shifts the error distribution within specification limits, with marked gains in process capability and yield. Although it does not match the analytical precision or long-term robustness of spectrometric approaches, the proposed system offers an interpretable and energy-efficient option for short-term, laboratory-scale monitoring under controlled refrigeration conditions. By enabling probabilistic freshness estimation from low-cost sensors, this GPR-driven e-nose demonstrates a proof-of-concept pathway that could, after further validation under realistic cyclic loads and operational disturbances, support more sustainable meat management in future smart refrigeration and cold-chain applications. This study should be regarded as a methodological, laboratory-scale proof-of-concept that does not demonstrate real-world performance or operational deployment. The technical implications described herein are hypothetical and require extensive validation under realistic refrigeration conditions. Full article

This study presents a deep learning-based framework for forecasting energy demand in a quicklime production company, aiming to enhance operational efficiency and enable data-driven decision-making for industrial scalability. Using one year of real electricity consumption data, the methodology integrates temporal and operational variables—such as load profile, active power, shift indicators, and production-related proxies—to capture the dynamics of energy usage throughout the manufacturing process. Several neural network architectures, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Conv1D models, were trained and compared to predict short-term power demand with 10-min resolution. Among these, the GRU model achieved the highest predictive accuracy, with a best performance of RMSE = 2.18 kW, MAE = 0.49 kW, and SMAPE = 3.64% on the test set. The resulting forecasts support cost-efficient scheduling under time-of-use tariffs and provide valuable insights for infrastructure planning, capacity management, and sustainability optimization in energy-intensive industries. Full article

Depth estimation is a critical enabling technology for sustainable intelligent transportation systems (ITSs), as it supports essential functions such as obstacle detection, navigation, and traffic management. However, existing Neural Radiance Field (NeRF)-based monocular depth estimation methods often suffer from high computational costs and poor performance in occluded regions, limiting their applicability in real-world, resource-constrained environments. To address these challenges, this paper proposes a lightweight monocular depth estimation framework that integrates a novel capacity redistribution strategy and an adaptive occlusion-aware training mechanism. By shifting computational load from resource-intensive multi-layer perceptrons (MLPs) to efficient separable convolutional encoder–decoder networks, our method significantly reduces memory usage to 234 MB while maintaining competitive accuracy. Furthermore, a divide-and-conquer training strategy explicitly handles occluded regions, improving reconstruction quality in complex urban scenarios. Experimental evaluations on the KITTI and V2X-Sim datasets demonstrate that our approach not only achieves superior depth estimation performance but also supports real-time operation on edge devices. This work contributes to the sustainable development of ITS by offering a practical, efficient, and scalable solution for environmental perception, with potential benefits for energy efficiency, system affordability, and large-scale deployment. Full article

This paper presents a high-sensitivity microwave sensor based on a modified Complementary Split Ring Resonator (CSRR) architecture, integrated with inductive stubs, for non-invasive blood glucose monitoring. The proposed sensor is designed to enhance the electric field localization and coupling efficiency by introducing inductive elements that strengthen the perturbation effect caused by glucose concentration changes in the blood. Numerical simulations were conducted using a multilayer finger model to evaluate the sensor’s performance under various glucose levels ranging from 0 to 500 mg/dL. The modified sensor exhibits dual-resonance characteristics and outperforms the conventional CSRR in both frequency and amplitude sensitivity. At an optimized stub gap of 2 mm, which effectively minimizes the capacitive coupling effect of the transmission line and thereby improves the quality factor, the sensor achieves a frequency shift sensitivity of 0.086 MHz/mg/dL and an amplitude sensitivity of 0.02 dB/mg/dL, compared to 0.032 MHz/mg/dL and 0.0116 dB/mg/dL observed in the standard CSRR structure. This confirms a significant enhancement in sensing performance and field confinement due to the optimized inductive loading. These results represent significant enhancements of approximately 168% and 72%, respectively. With its compact design, increased sensitivity, and potential for wearable implementation, the proposed sensor offers a promising platform for continuous, real-time, and non-invasive glucose monitoring in biomedical applications. Full article

This paper presents a real-time quarry truck monitoring system that combines deep learning and license plate recognition (LPR) for operational monitoring and weighbridge reconciliation. Rather than estimating load volumes directly from imagery, the system ensures auditable matching between detected trucks and official weight records. Deployed at quarry checkpoints, fixed cameras stream to an edge stack that performs truck detection, line-crossing counts, and per-frame plate Optical Character Recognition (OCR); a temporal voting and format-constrained post-processing step consolidates plate strings for registry matching. The system exposes a dashboard with auditable session bundles (model/version hashes, Region of Interest (ROI)/line geometry, thresholds, logs) to ensure replay and traceability between offline evaluation and live operations. We evaluate detection (precision, recall, mAP@0.5, and mAP@0.5:0.95), tracking (ID metrics), and (LPR) usability, and we quantify operational validity by reconciling estimated shift-level tonnage T against weighbridge tonnage T* using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), R², and Bland–Altman analysis. Results show stable convergence of the detection models, reliable plate usability under varied optics (day, dusk, night, and dust), low-latency processing suitable for commodity hardware, and close agreement with weighbridge references at the shift level. The study demonstrates that vision-based counting coupled with plate linkage can provide regulator-ready KPIs and auditable evidence for production control in quarry operations. Full article

To ensure reliable, efficient and sustainable operation of modern power networks, accurate load forecasting is an important task in system planning and control. It is also a crucial task for the efficient operation of smart grids to maintain a balance between load shifting, load management and power dispatch. In this regard, this research study aims to investigate the efficiency of various machine learning models for whole-house energy consumption prediction and appliance-level load disaggregation using Non-Intrusive Load Monitoring (NILM). The primary objective is to determine which model offers the most accurate forecasts for both individual appliance consumption patterns and the total amount of energy used by the household. The empirical study presents comparative performance analysis of machine learning models, i.e., Random Forest, Decision Tree, K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), Gradient Boosting and Support Vector Regressor (SVR) for load forecasting and load disaggregation. This research is conducted on PRECON: Pakistan Residential Electricity Dataset consisting of 42 Pakistani households. The dataset was recorded originally as one minute per sample, but the proposed study aggregated it to hourly samples to evaluate models’ alignment with the typical sampling rate of smart meters in Pakistan. It enables the models to more accurately depict implementation scenarios in real-world settings. The statistical measures MAE, MSE, RMSE and R² have been employed for performance evaluation. The proposed Random Forest algorithm out-performs all other employed models, with the lowest error values (MAE: 0.1316, MSE: 0.0367, RMSE: 0.1916) and the highest R² score of 0.9865. Furthermore, for detecting appliance events from aggregate power data, ensemble models such as Random Forest performed better than other models for ON/OFF prediction. To evaluate the suitability of machine learning models for real-time, appliance-level energy forecasting using Non-Intrusive Load Monitoring (NILM), this study presents a novel evaluation framework that combines learning speed and edge adaptability with conventional performance metrics (e.g., R², MAE). This paper introduces a NILM-based approach for load forecasting and appliance-level ON/OFF prediction, representing its capacity to improve residential energy efficiency and encourage sustainable energy consumption, while emphasizing operational metrics for implementation in embedded smart grid systems—an area mainly neglected in prior NILM-based research articles. The results provide useful information for improving demand-side energy management, facilitating more effective load disaggregation, and maximizing the energy efficiency and responsiveness of smart grids. Full article

This paper presents a comprehensive framework for real-time energy management in microgrids integrating distributed renewable energy sources and demand response (DR) programs. To address the inherent uncertainties in key operational variables—such as load demand, wind speed, solar irradiance, and electricity market prices—this study employs a probabilistic modeling approach. A two-stage stochastic optimization method, combining mixed-integer linear programming and optimal power flow (OPF), is developed to minimize operational costs while ensuring efficient system operation. Real-time dynamic pricing mechanisms are incorporated to incentivize consumer load shifting and promote energy-efficient consumption patterns. Three microgrid scenarios are analyzed using one year of real historical data: (i) a grid-connected microgrid without DR, (ii) a grid-connected microgrid with 10% and 20% DR-based load shifting, and (iii) an islanded microgrid operating under incentive-based DR contracts. Results demonstrate that incorporating DR strategies significantly reduces both operating costs and reliance on grid imports, especially during peak demand periods. The islanded scenario, while autonomous, incurs higher costs and highlights the challenges of self-sufficiency under uncertainty. Overall, the proposed model illustrates how the integration of real-time pricing with stochastic optimization enhances the flexibility, resilience, and cost-effectiveness of smart microgrid operations, offering actionable insights for the development of future grid-interactive energy systems. Full article

This paper compares two common dispatch policies—Load-Following (LF) and Cycle-Charging (CC)—for a photovoltaic Battery Energy Storage System (PV–BESS) microgrid (MG) with a 12 kW diesel generator, using a full-year of real 15 min PV and load data from an industrial use case in Germany. A forward time-step simulation enforces the battery State-of-Energy (SoE) window (total basis [20, 100] %, DoD = 80%) and computes curtailment, generator use, and unmet energy. Feasible designs satisfy a Loss of Power Supply Probability (LPSP) ≤ 0.03. Economic evaluation follows an Equivalent Annual Cost (EUAC) model with PV and BESS Capital Expenditure/Operation and Maintenance (CAPEX/O&M) (cycle life dependent on DoD and 15-year calendar life), generator costs, and fuel via SFC and diesel price. A value of lost load (VOLL) can be applied to unserved energy, with an optional curtailment penalty. Across the design space, a clear cost valley appears toward moderate storage and modest PV, with the baseline optimum at ≈56 kWp PV and 200 kWh BESS (DoD = 80%). Both policies meet the reliability target (in our runs LPSP ≈ 0), and their SoE trajectories are nearly identical; CC only lifts the SoE slightly after generator-ON events by using headroom to charge, while LF supplies just the residual deficit. Sensitivity analyses show that the optimum is most affected by diesel price and discount rate, with smaller shifts for ±10% changes in SFC. The study provides a transparent, reproducible workflow—grounded in real data—for controller selection and capacity planning. Full article

In line with the global goal of achieving climate neutrality, a flexible energy system capable of accommodating the uncertainties induced by renewable energy sources becomes vitally important. This paper investigates the electricity demand flexibility characteristics and develops demand-response (DR) control strategies for grid-interactive buildings. First, a building’s flexible loads are classified into three types, interruptible loads (ILs), shiftable loads (SLs), and adjustable loads (ALs). The load flexibility characteristics, including real-time response capabilities, the time window range, and the adaptive adjustment ratios, are investigated. Second, DR control strategies and their features, which form the basis for achieving different optimization objectives, are detailed. Finally, three DR optimization objectives are proposed, including maximizing load reduction, maximizing economic benefits, and ensuring stable load reduction and recovery. Through case studies of a residential building and an office building, the results demonstrate the effectiveness of these DR strategies for load reduction and cost savings under different DR objectives. For the residential building, our results showed that over 50% of the electricity load could be shifted, resulting in electricity bill savings of over 17.6%. For office buildings, various DR control strategies involving zone temperature resetting, lighting dimming, and water storage utilization can achieve a total electricity load reduction of 28.1% to 63.6% and electricity bill savings of 7.39% to 26.79%. The findings from this study provide valuable benchmarks for assessing electricity flexibility and DR performance for other buildings. Full article

Agricultural non-point source pollution (AGNPSP) is one of the core challenges facing global water environment management. Existing research mainly focuses on post-event estimation of pollution loads and source analysis, while studies on proactive risk warning for watershed non-point source pollution are relatively limited, especially those that integrate with agricultural production practices. Therefore, this study takes the River Tongyang Watershed as the research object and establishes a fertilization warning and regulation model based on short-term meteorological data. First, it simulates the migration and transformation processes of pollutants within the watershed under different meteorological conditions and analyzes their spatiotemporal evolution characteristics. Then, combined with real-time water quality monitoring data at the lake inlet, it calculates the residual environmental capacity for pollutants in the river water. Finally, based on this environmental capacity and the farmland area, it back-calculates the maximum safe fertilization amount for each plot under different meteorological scenarios to achieve precise fertilization management. When the planned fertilization amount does not exceed this maximum safe value, environmental risks are within a controllable range; if exceeded, fertilization should be proportionally reduced to prevent non-point source pollution. The results indicate that this model can accurately predict the concentration trends of non-point source pollutants and can develop differentiated fertilization strategies based on rainfall scenarios. The “fertilization determined by water” decision-making framework established in this study provides a technically significant pathway for shifting watershed agricultural non-point source pollution management from passive treatment to active prevention. Full article

This study develops an explainable machine learning framework for wildfire prediction across Australia, integrating region-specific models and feature attribution to identify key environmental drivers. Three wildfire indicators, Estimated Fire Area (FA), Mean Fire Brightness Temperature (FBT), and Fire Radiative Power (FRP), were modeled using Lasso, Random Forest, LightGBM, and XGBoost. Performance metrics (RMSEC, RMSECV, RMSEP) confirmed strong calibration and generalization, with Tasmania and Queensland achieving the lowest prediction errors for FA and FRP, respectively. Feature importance and SHAP analyses revealed that soil moisture, solar radiation, precipitation, and humidity variability are dominant predictors. Extremes and variance-based measures proved more influential than mean climatic values, indicating that fire dynamics respond non-linearly to environmental fluctuations. Lasso models captured stable linear dependencies in arid regions, while ensemble models effectively represented complex interactions in tropical climates. The results highlight a hierarchical process where cumulative soil and radiation stress establish fire potential, and short-term meteorological variability drives ignition and spread. Projected climate shifts, declining soil water and increased radiative load, are likely to intensify these drivers. The framework supports interpretable, region-specific mitigation planning and paves the way for incorporating generative AI and multi-source data fusion to enhance real-time wildfire forecasting. Full article

This paper presents an intelligent hybrid framework for short-term energy consumption forecasting and real-time energy management in photovoltaic (PV)-integrated smart homes with Vehicle-to-Home (V2H) systems, tailored to the Tunisian context. The forecasting module employs an Attention-based Long Short-Term Memory (LSTM) neural network, whose hyperparameters (learning rate, hidden units, temporal window size) are optimized using the Harris Hawks Optimization (HHO) algorithm. Simulation results show that the proposed LSTM-HHO model achieves a Root Mean Square Error (RMSE) of 269 Wh, a Mean Absolute Error (MAE) of 187 Wh, and a Mean Absolute Percentage Error (MAPE) of 9.43%, with R² = 0.97, substantially outperforming conventional LSTM (RMSE: 945 Wh, MAPE: 51.05%) and LSTM-PSO (RMSE: 586 Wh, MAPE: 28.72%). These accurate forecasts are exploited by the Energy Management System (EMS) to optimize energy flows through dynamic appliance scheduling, HVAC load shifting, and coordinated operation of home and EV batteries. Compared with baseline operation, PV self-consumption increased by 18.6%, grid reliance decreased by 25%, and household energy costs were reduced by 17.3%. Cost savings are achieved via predictive and adaptive control that prioritizes PV utilization, shifts flexible loads to surplus periods, and hierarchically manages distributed storage (home battery for short-term balancing, EV battery for extended deficits). Overall, the proposed LSTM-HHO-based EMS provides a practical and effective pathway toward smart, sustainable, and cost-efficient residential energy systems, contributing directly to Tunisia’s energy transition goals. Full article