Robust autonomous navigation in dense, unstructured environments such as forests presents a longstanding challenge in robotics due to complex terrain geometry, dynamic occlusions, and unreliable global positioning signals. This paper proposes a hybrid perception-and-control framework that integrates deep semantic segmentation with reinforcement learning to enable intelligent, vision-driven navigation in visually cluttered forest trails. The system combines Mask R-CNN for pixel-level trail segmentation with a Soft Actor-Critic (SAC) agent that learns adaptive navigation policies under continuous action spaces. A Pure Pursuit controller translates visual predictions into smooth motor commands, ensuring path adherence and stability. The model is trained and evaluated in a high-fidelity forest simulation environment featuring natural obstacles, variable lighting, and randomized trail geometries. Extensive experiments demonstrate that our approach achieves a high trail-following success rate (86.7%), low collision frequency, and precise path tracking in challenging navigation scenarios. Comparative and ablation studies further highlight the synergy between learning-based perception and control. The proposed framework offers a scalable and modular solution for deploying autonomous robots in natural terrains without relying on GPS or prior maps, paving the way for applications in environmental monitoring and field robotics.

DC Microgrids are becoming increasingly popular for their efficiency and suitability for integrating renewable energy source and energy storage systems. However, unexpected sensor faults can severely compromise voltage regulation, current sharing, and overall system stability, posing a risk, especially for critical applications. Existing resilient control schemes for DC Microgrids often relies on hardware redundancy, multiple observers, or communication-based fault mitigation, leading to slow fault mitigation, increased cost, complexity, and vulnerability to cyber threat. To address the limitations of existing methods this paper proposes real-time reconfiguration framework to tolerate adverse sensor faults in islanded DC Microgrids. The proposed scheme leverages a single Proportional Integral Unknown Input Observer (PI-UIO) to reconstruct sensor faults and reconfigure a decentralized Passivity Based Control (PBC) at the primary level and a distributed consensus based current sharing controller at the secondary level. Unlike conventional methods, the proposed scheme operates autonomously without communication, thus enhancing the scalability, reliability and resilience against cyberattacks. Moreover, the design of the PI-UIO and PBC is achieved with decentralized parameters to enable seamless plug-and-play integration. Extensive simulation and real time simulation results validate the effectiveness and superiority of the proposed FTC framework compared with the recent methods.

Accurate short-term forecasting of solar photovoltaic (PV) power is essential for grid stability and renewable energy integration, but remains challenging due to the inherent variability and intermittency of solar generation. This paper introduces a hybrid model that combines a Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (biLSTM) network to address this challenge. The proposed CNN-biLSTM model is evaluated against four benchmark models, including Multilayer Perceptron (MLP), Support Vector Regression (SVR), Random Forest (RF), and a unidirectional CNN-LSTM, using historical meteorological and PV power data. Performance is assessed through a comprehensive suite of statistical metrics (R², RMSE, MAE, MAPE, sMAPE, and normalised RMSE). The results demonstrate that the CNN-biLSTM achieves superior accuracy, with the highest coefficient of determination (R2=0.99848) and the lowest error metrics (RMSE=0.5939 W, MAE=0.398 W, and nRMSErange=1.18 %), significantly outperforming all benchmarks. The bidirectional architecture uniquely captures temporal dependencies in both forward and backward directions, enabling more effective modeling of nonlinear solar fluctuations. This work establishes the CNN-biLSTM as a robust and reliable solution for real-world solar energy management systems, enhancing forecasting precision and supporting the stable integration of renewable energy into smart grids.

Recently, phase change material (PCM) has been seen as a promising thermal energy storage (TES) technology for providing energy storage and operation flexibility in buildings. Despite its various applications, there has been a lack of real-time tracking capability of the PCM performance in real-deployed systems due to its complex physics. PCM state of charge (SoC) is a key indicator required for quantifying the remaining energy at any operation condition. Since SoC is not a direct measurement, there is a need for highly accurate prediction models. In this article, we propose solving this challenge by employing sparse identification of nonlinear dynamics (SINDy) to unlock the nonlinear dynamic complexity of PCM-TES. The minor utilization of temperature sensors in real-life applications is mitigated by using an extended Kalman filter (EKF) estimator that tunes, in real-time, any faced model inaccuracy. This framework will make it possible to provide highly accurate estimations for the spatial PCM temperatures based on limited noisy measurements. The proposed approach was successfully applied to experimental data recorded from the operation of a prototypical PCM storage for Domestic Hot water generation. The results show how efficient the proposed EKF-SINDy is in SoC estimation compared to the measurement-only approach.

Air-handling units (AHUs) have become indispensable parts of heating, ventilation, and air conditioning (HVAC) systems. AHUs are also significant energy consumers due to the function of their several actuators. Many recent works focus on improving the control techniques of AHUs to provide better indoor comfort with lower energy consumption. However, due to its inherent structure, it is complex to design an optimal and adaptive control for AHU that fulfills this mission in all operation conditions. Model predictive control (MPC), in this context, has been in focus in many contributions recently. However, designing a multi-input multi-output (MIMO) MPC for AHU optimal control is not a trivial task due to the difficulty of having a high-fidelity mathematical model. This study proposes and validates a data-driven nonlinear MPC with MIMO architecture. The proposed MPC is based on the sparse nonlinear dynamic of AHU built upon operation data of a real AHU installed in the KTH live-in lab. In contrast to the classical approaches, the proposed MPC adjusts simultaneously five different actuators to control the supply temperature. This article presents a simulation study for the performance of the proposed MPC framework under different control configurations.

In most typical situations, thermal energy storage (TES) systems, which incorporate sensible and latent storage capacities, are not effectively utilized within the overall functions of building energy management systems (BEMSs), which usually rely on classical rule-based control (RBC). This study addresses the challenge of overcoming this by featuring model predictive control (MPC). The proposed method is based on modeling a water tank-integrated phase change material (PCM) using data-driven linear approximation generated with sparse regression. Based on the control objective, the proposed MPC can address two control targets, either providing robust and fast-tracking to the TES charging/discharging setpoints or reducing the energy cost related to the building heating needs. The digital simulation of a two-day scenario, using real operation conditions, demonstrates the effectiveness of the proposed MPC framework, showing up to 57 % heating cost reduction compared to the RBC scenario. As the real-time control requirement is critical, the MPC computing time was evaluated to assess its potential for integration into real-world applications within BEMS.

In this work, nickel oxide nanoparticles (NiO NPs) were synthesized sonochemically in the ionic liquid 1,2-(propanediol)-3-methylimidazolium hydrogen sulfate ([PDOHMIM+][HSO4−]) at different loadings (8 wt.%, 15 wt.%, and 30 wt.%), and subsequently coated with polyethylene glycol (PEG). Structural characterization (XRD, FTIR, TEM, TGA) confirmed a cubic NiO spinel phase with an average crystallite size of ~8 nm, which increased to 20–28 nm after PEG coating. Electrical measurements (100 Hz–1 MHz) showed that AC conductivity (σAC) increased with both frequency and NiO content, whereas the dielectric constant (ε′) and loss tangent (tan δ) decreased with frequency. DFT calculations (B3LYP/6–311+G(2d,p)) on the [PDOHMIM+][HSO4−] ion pair showed that there were strong hydrogen bonds, an uneven charge distribution, and stable electrostatic interactions that help keep NiO NPs stable and spread them evenly in the ionic liquid. In general, both experimental and theoretical studies show that PEG-coated [NiO NPs + IL] nanostructures exhibit improved dielectric stability, enhanced interfacial polarization, and tunable electronic properties. 

The increasing importance of coordinated energy management in residential districts has led to a shift from individual end-user optimization to a broader energy community perspective. This transition, however, necessitates efficient data communication and processing tools. In this context, the Internet of Things (IoT) plays a pivotal role by seamlessly connecting energy meters, sensors, data processing units, and controllable energy assets within these districts. This empowers homeowners and utility providers with real-time data and intelligent automation, leading to more efficient energy consumption through predictive analytics. IoT sensors monitor energy usage patterns, weather conditions, and energy market fluctuations, allowing residents to remotely control and optimize their appliances and heating/cooling systems, ultimately reducing energy waste and costs. This paper presents an IoT-powered demand response management simulation study in a building district, validated using data from the Großschönau Municipality in Austria. This community encompasses various building types connected to both electric and local district heating (DH) networks. Data is collected by IoT-enabled sensors and transmitted via the internet for pre-processing and backend services. These services primarily involve an optimization-based coordinated management of energy assets in the community. This study aims to assess, in the simulation phase, the optimal operation scheduling of heat pumps (HP) with energy storage units that connect each building in the energy community to the DH network. The simulation outcomes demonstrate a notable improvement in the community's energy self-efficiency, resulting in lowered energy expenses facilitated by real-time monitoring of energy market data. This approach also leads to a reduction in estimated total CO2 emissions related to HP's operation.

In recent years, there has been a growing acknowledgment of the vital significance of energy flexibilitywithin local energy communities (LECs) as a fundamental strategy to optimize the utilization of adiverse array of available resources. At the district level, where flexibility is indispensable for theefficient operation of controllable assets within centralized substations, energy storage systems (ESSs)emerge as central players in achieving this objective. The primary aims encompass reducing electricitycosts and maximizing the self-consumption of interconnected renewable energy systems (RES) withinLECs, all while ensuring the secure and efficient operation of substation components. This challengeinvolves translating these objectives into a nonlinear optimization problem. Numerous optimizationtechniques have been explored and validated in this pursuit, applied on a real data for the heatingdemand of the ENVIPARK energy district in Turin, Italy. For this regard, a virtual scenario wasconstructed, suggesting the installation of two key energy storage technologies: battery electric storagesystem (BESS) and sensible thermal energy storage (TES). As a long-term assessment, the impact ofenergy flexibility margin, specifically BESS state of charge (SOC) and TES maximum temperature, hasbeen accurately evaluated and quantified. Essentially, adjusting BESS SOC lower limit from 50 % to10 % and the variation interval of the TES maximum temperature from 15 °C to 20 °C led to asubstantial improvement of up to 13.9 % in energy costs. Which underscores the central role of theoptimization-driven energy flexibility in reducing the heating expenses of local energy communities.

This study investigates the thermal and energetic dynamics of primary school classrooms in a Mediterranean climate in Khoualed Abdel Hakeem, Ain Temouchent County, Algeria. The research highlights significant optimizations by focusing on passive strategies such as external shading devices, Window-to-Wall Ratio (WWR), glazing types, and building envelope adjustments. Our simulations, validated rigorously, showcase a remarkable congruence with actual electricity consumption, affirming the reliability and efficacy of our simulation model as a valuable predictive tool. A Vertical Shading Angle (VSA) of 60° proves optimal, resulting in an impressive 11% reduction in Annual Energy Consumption (AEC). A recommended WWR of 30% demonstrates an 11% decrease in AEC and improves thermal and energy efficiency. Double Low Emissivity (Double-Low E) glazing is found to be superior, resulting in a significant 14% decrease in AEC. Achieving a WWR of 50% in shaded areas helps maintain a well-balanced thermal environment, resulting in a 12% reduction in heating and cooling requirements. The integration of passive strategies in the optimized model showcases a remarkable 44% overall reduction in energy consumption. The results highlight the efficacy of passive strategies, promoting energy-conscious and ecologically responsible practices, advocating for their incorporation in educational facilities, and offering valuable insights for sustainable school building design.