Explore the vast range of titles available.

The transition to a decarbonized energy sector, driven by the integration of Renewable Energy Sources (RESs), smart building technology, and the rise of Electric Vehicles (EVs), has highlighted the need for optimized energy system planning. Increasing EV adoption creates additional challenges for charging infrastructure and grid demand, while proactive and informed decisions by residential EV users can help mitigate such challenges. Our work develops a smart residential charging framework that assists residents in making informed decisions about optimal EV charging. The framework integrates a machine-learning-based forecasting engine that consists of two components: a stacking and voting meta-ensemble regressor for predicting EV charging load and a bidirectional LSTM for forecasting national net energy exchange using real-world data from local road traffic, residential charging sessions, and grid net energy exchange flow. The combined forecasting outputs are passed through a data-driven weighting mechanism to generate probabilistic recommendations that identify optimal charging periods, aiming to alleviate grid stress and ensure efficient operation of local charging infrastructure. The framework’s modular design ensures adaptability to local charging infrastructure within or nearby building complexes, making it a versatile tool for enhancing energy efficiency in residential settings.

This paper introduces an advanced framework to enhance power system flexibility through AI‐driven dynamic load management and renewable energy integration. Leveraging a transformer‐based predictive model and MATPOWER simulations on the IEEE 14‐bus system, the study achieves significant improvements in system efficiency and stability. Key contributions include a 44% reduction in total power losses, enhanced voltage stability validated through the Fast Voltage Stability Index (FVSI), and optimized renewable energy utilization. Comparative analyses demonstrate the superiority of AI‐based approaches over traditional models such as ARIMA, with the transformer model achieving significantly lower forecasting errors. The proposed methodology highlights the transformative potential of AI in addressing the challenges of modern power grids, paving the way for more resilient, efficient, and sustainable energy systems. This study presents an AI‐driven framework for power system flexibility, integrating renewable energy and dynamic load management. Using a transformer‐based model and IEEE 14‐bus simulations, it achieves a 44% reduction in power losses, enhanced voltage stability, and superior forecasting accuracy, demonstrating AI's potential for resilient and sustainable energy systems.

The increasing penetration of photovoltaic (PV) systems and the need for reliable backup power solutions have led to the development of hybrid uninterruptible power supply (UPS) systems. These systems integrate PV energy storage with battery backup and grid power to optimize real-time energy management. This paper proposes an advanced energy management strategy and an artificial neural network (ANN)-based control method for PV-integrated hybrid UPS systems. The proposed strategy dynamically determines the optimal power-sharing ratio between battery storage and the grid based on real-time economic parameters, load demand, and battery state of charge (SoC). A centralized ANN-based controller ensures precise control of the LLC converter and rectifier, achieving stable and efficient power distribution. Additionally, a genetic algorithm is implemented to optimize the power sharing ratio, minimizing the LCOE under varying load and electricity pricing conditions. The proposed approach is validated through simulations, demonstrating significant improvements in cost-effectiveness, system stability, and dynamic adaptability compared to conventional control methods. These findings suggest that integrating ANN-based control with optimized energy management can enhance the efficiency and sustainability of hybrid UPS systems, particularly in fluctuating energy markets.

PCMs are attractive for the future generation of buildings, where energy efficiency targets and thermal comfort expectations are increasingly prioritized. Experimental analysis of local thermal processes in these dynamic components and whole-building energy consumption predictions are essential for the proper implementation of PCMs in buildings. This paper discusses the experimental analysis of the thermophysical characteristics of both a latent heat storage material (PCM) and a product containing this PCM. The prototype product under investigation is a panelized PCM technology containing inorganic, salt-hydrate-based PCM. The thermal analysis includes studies of melting and freezing temperatures, enthalpy changes during phase change processes, nucleation intensity, sub-cooling effects, and PCM stability. The PCM’s stability is also investigated, as is the ability of PCM products to control local temperatures and peak load transmission times. Two inorganic PCM formulations based on calcium chloride hexahydrate (CaCl2.6H2O) were prepared and tested in laboratory conditions. Material-scale testing results were compared with outcomes from the system-scale analysis, using both laboratory test methods as well as field exposure in test huts. This work demonstrates that PCM technologies used in buildings can effectively control both the magnitude of thermal storage capacity as well as the time of the peak thermal load. It was found that commonly used material-scale testing methods may not always be beneficial in assessing the dynamic thermal performance characteristics of building technologies containing PCMs.

Revenue management and dynamic pricing are concepts that have immense possibilities for application in the energy sector. Both can be considered as demand-side management tools that can facilitate the offering of different prices at different demand levels. This paper studies literature on various topics related to the dynamic pricing of electricity and lists future research avenues in pricing policies, consumers' willingness to pay and market segmentation in this field. Demand and price forecasting play an important role in determining prices and scheduling load in dynamic pricing environments. This allows different forms of dynamic pricing policies to different markets and customers depending on customers' willingness to pay. Consumers' willingness to pay for electricity services is also necessary in setting price limits depending on the demand and demand response curve. Market segmentation can enhance the effects of such pricing schemes. Appropriate scheduling of electrical load enhances the consumer response to dynamic tariffs.

Fog computing (FC) designates a decentralized computing structure placed among the devices that produce data and cloud. Such flexible structure empowers users to place resources to increase performance. However, limited resources and low delay services obstruct the application of new virtualization technologies in the task scheduling and resource management of fog computing. Scheduling and load balancing (LB) in the cloud computing have been widely studied. However, countless efforts in LB have been proposed in the fog architectures. This presents some enticing challenges to solve the problem of how tasks are routed between different physical devices between fog nodes and cloud. Within fog, due to its mass and heterogeneity of devices, the scheduling is very difficult. There are still few studies that have been conducted. LB is a very interesting and important study area in FC as it aims to achieve high resource utilization. There are various challenges in LB such as security and fault tolerance. The main objective of this paper is to introduce an effective dynamic load balancing technique (EDLB) using convolutional neural network and modified particle swarm optimization, which is composed of three main modules, namely: (i) fog resource monitor (FRM), (ii) CNN-based classifier (CBC), and (iii) optimized dynamic scheduler (ODS). The main purpose of EDLB is to achieve LB in FC environment via dynamic real-time scheduling algorithm. This paper studies the FC architecture for Healthcare system applications. The FRM is responsible for monitoring each server resource and save the server's data into table called fog resources table. The CNN-based classifier (CBC) is responsible for classifying each fog server to suitable or not suitable. The optimized dynamic scheduler (ODS) is responsible for assigning the incoming process to the most appropriate server. Comparing EDLB with other previous LB algorithms, it reduces the response time and achieves high resource utilization. Hence, it is an efficient way to ensure the continuous service. Accordingly, EDLB is simple and efficient in real-time systems in fog computing such as in the case of healthcare system. Although several methods in LB for FC have been introduced, they have many limitations. EDLB overcomes these limitations and achieves high performance in various scenarios. It achieved better makespan, average resource utilization and load balancing level as compared to previously mentioned LB algorithms.

The amount of transported sediment load by streams is a vital but high nonlinear dynamic process in water resources management. In the current paper, two optimum predictive models subjected to artificial neural network (ANN) were developed. The employed inputs were then prioritized using diverse sensitivity analysis (SA) methods to address new updated but more efficient ANN structures. The models were found through the 263 processed datasets of three rivers in Idaho, USA using nine different measured flow and sediment variables (e.g., channel geometry, geomorphology, hydraulic) for a period of 11 years. The used parameters were selected based on the prior knowledge of the conventional analyses in which the effect of suspended load on bed load was also investigated. Analyzed accuracy performances using different criteria exhibited improved predictability in updated models which can lead to an advanced understanding of used parameters. Despite different SA methods being employed in evaluating model parameters, almost similar results were observed and then verified using relevant sensitivity indices. It was demonstrated that the ranked parameters using SA due to covering more uncertainties can be more reliable. Evaluated models using sensitivity indices showed that contribution of suspended load on predicted bed load is not significant.

The cumulative deformation and fatigue failure of roadbeds induced by dynamic loads are fundamental considerations in road traffic design. To gain a more comprehensive understanding of the impact of drainage conditions and loading cycles on the performance of roadbeds composed of granite residual soil in southern China under various loading modes, this study conducted high-cycle dynamic triaxial tests using a DDS-70 dynamic triaxial apparatus. Through analysis of sample deformations, pore pressure development, and changes in critical cyclic stress ratio under different simulated waveforms, it was observed that the simulated waveform significantly influences the dynamic characteristics of the soil, with the half-sine wave proving effective in simulating the complex dynamic stress caused by traffic vehicles. Meanwhile, the study revealed uncertainties in the development of cumulative deformation under undrained conditions, thus indicating a need for dynamic tests to be conducted under drained conditions to more accurately replicate the effects of traffic loads. Additionally, the deformation of samples at 1000 cycles can serve as a crucial reference for estimating final deformation, which is essential for determining sample types and obtaining key parameters of foundation soil. This approach can help reduce testing workload and save time and costs.

With the widespread adoption of zero-carbon smart buildings, integrating multiple smart buildings into an islanded microgrid has become an essential approach for achieving sustainable energy management. However, islanded microgrids face challenges in maintaining frequency stability, particularly in the presence of system parameter uncertainties and dynamic load variations. This paper presents a frequency regulation method based on model-free adaptive dynamic programming (ADP) specifically designed for zero-carbon smart building islanded microgrids. Unlike traditional approaches that rely on precise system models and fixed load parameters, the proposed ADP controller effectively addresses model uncertainties, operational mode switching, and time-varying loads without requiring prior knowledge of the system dynamics. By treating each smart building as an agent within a multi-agent system, the controller utilizes local frequency measurements and communication between buildings to achieve overall frequency synchronization and stability. Simulation experiments demonstrate the effectiveness of the proposed method. The approach outlined in this paper provides robust technical support for the reliable and sustainable operation of future zero-carbon smart building communities.

PurposeTracked hydraulic excavators are versatile and ubiquitous items of off-highway plant and machinery that are utilised throughout the construction industry. Each year, a significant number of excavators overturn whilst conducting a lifting operation, causing damage to property, personnel injury or even fatality. The reasons for the overturn are myriad, including: operational or environmental conditions; machine operator acts or omissions; and/or inadequate site supervision. Furthermore, the safe working load (SWL) figure obtained from manufacturer guidance and utilised in lift plans is based upon undertaking a static load only. The purpose of this paper is to determine whether the SWL is still safe to be used in a lift plan when slewing a freely suspended (dynamic) load, and, if not, whether this may be a further contributory factor to overturn incidents.Design/methodology/approachPrevious research has developed a number of machine stability test regimes but these were largely subjective, impractical to replicate and failed to accurately measure the “dynamic” horizontal centrifugal force resulting from slewing the load. This research contributes towards resolving the stability problem by critically evaluating existing governing standards and legislation, investigating case studies of excavator overturn and simulating the dynamic effects of an excavator when slewing a freely suspended load at high rotations per minute (rpm). To achieve this, both the static load and horizontal centrifugal force from slewing this load were calculated for six randomly selected cases of an excavator, with different arm geometry configurations.FindingsThe results from the six cases are presented and a worked example of one is detailed to demonstrate how the results were derived. The findings reveal that the SWL quoted on an excavator’s lift rating chart considerably underestimates the extra forces experienced by the machine when an additional dynamic load is added to the static load whilst lifting and slewing a freely suspended load.Originality/valueThis work presents the first attempt to accurately model excavator stability by taking consideration of the dynamic forces caused by slewing a freely suspended load and will lead to changes in the way that industry develops and manages lift plans. Future research proposes to vary the weight of load, arm geometry and rpm to predict machine stability characteristics under various operational conditions, and exploit these modelling data to populate pre-programmed sensor-based technology to monitor stability in real time and automatically restrict lift mode operations.