Search

Environmental pollution and the rapid decline in the availability of fossil fuels are the major concerns of the electric power industry in recent years. Effective utilization of electrical energy is the need of the hour in building the nation towards sustainable development. This study presents the energy consumption analysis and management performed in a diary firm located in Tamil Nadu, India. Initially, the energy usage of the firm is estimated based on its electricity bills, meter readings, and survey followed by detailed energy consumption analysis and evaluation. The study employs guidelines provided by the Indian Bureau of Energy Efficiency for energy management. The detailed analysis performed finds scopes for improvement in efficient energy usage. Numerical analysis shows that implementation of proposed action plans that include installation of automatic power factor correction, replacement of overheating equipment, and replacement of lighting systems with energy-efficient lighting would save annual energy of 123.96 kWh which in turn results in the reduction of annual CO2 emission by 117.76 tonnes. Furthermore, this paper also proposes a novel optimal process scheduling which optimally schedules different processes in the firm without affecting productivity. This makes an additional savings of INR 4,23,360 per annum in the energy cost by minimizing the maximum demand of the firm with zero investment. A comparison of the proposed approach with existing methodologies available in the literature shows the effectiveness of the proposed technique. [ABSTRACT FROM AUTHOR]

The Smart Grid AMI is at the forefront of modernizing energy management for efficient energy distribution and maintaining grid reliability. However, the seamless flow of data within AMI introduces critical security challenges, necessitating innovative approaches to ensure secure data transmission. This paper addresses these challenges by proposing a Quantum Key Distribution (QKD) based on Multi-Objective Optimization (MOO) and Reinforcement Learning (RL) framework for secure data transmission within the Smart Grid AMI. Primarily, we formulate the routing problem as a MOO challenge with four primary objectives namely, energy efficiency, latency minimization, reliability, and security to capture the essence of efficient and secure data transmission. Further, we introduce an RL agent based on the Proximal Policy Optimization (PPO) algorithm for robust policy learning. The RL agent by exploring diverse routing actions and receiving rewards optimizes the routing decisions within the network environment based on the objectives specified in the multi-objective function (MOF). A novel MOF quantifies trade-offs between security and performance metrics, integrating QKD-based security metrics with traditional optimization objectives. This function guides the RL agent in making informed routing decisions. Through extensive simulations using the NS-2 simulator in a realistic Smart Grid AMI environment, the proposed approach obtained energy consumption of 750 J, latency of 55 ms, and security level of 96% and also revealed significant improvements compared to conventional techniques widely employed for secured communication in AMI networks. Overall, the simulation results exhibited that the proposed method showed outstanding performance by achieving energy efficiency of 0.95, latency reduction of 0.92, reliability improvement of 0.94, and security enhancement of 0.96. Overall, this integration offers a pioneering solution to address the evolving security challenges in the Smart Grid landscape and contributes to the advancement of secure data transmission in Smart Grid AMI networks, fostering a resilient and secure energy ecosystem. [ABSTRACT FROM AUTHOR]

This study aims to peak power shaving and reduce the cost of energy by using improved energy management system (EMS) in a microgrid. This study has three scenarios. In the first scenario, the EV charging station and the wind turbine operate standalone. In the second scenario, a microgrid structure including an energy storage system (ESS) and an EMS is established. The threshold algorithm has been used for the energy management. In the last scenario, fuzzy logic-based EMS is used for energy management. The impact of EV charge station and wind turbine on the grid and the cost of energy are analyzed for three scenarios. The results show that the use of microgrid-connected ESS significantly reduces the cost of energy and creates a more balanced load for the grid side. It is also proved that the EMS affects the energy losses. It is revealed that when the proposed fuzzy logic-based EMS is used, the energy cost is reduced by 78% and the peak power is reduced by 70%. Thus, it is seen that the proposed EMS successfully reduces both the cost of energy and the negative impact of EVs on the grid by balancing grid side load. [ABSTRACT FROM AUTHOR]

This research article considers a microgrid (MG) with various distributed generation sources (DGs) such as microturbine (MT), fuel cell (FC), wind turbine (WT), and solar cell (PV) along with the battery storage system. This article aims to simultaneously minimize operational costs and emissions for a daily schedule, while considering uncertainties such as load demand, market prices, and electricity generated by different renewable energy sources (RESs). This article proposes the slime mould algorithm (SMA) to solve this complex optimization problem. Initially, SMA is tested for three scenarios considering the minimization of operational cost and emission, respectively, as two single objectives. In Scenario A, a reduction of 1.95% in operational cost and 4.57% in emissions is observed compared to the Grasshopper Optimization Algorithm (GOA). In scenarios B and C, SMA reduces operational cost by 0.78% and 2.65%, respectively, while also reducing emissions by 6.27% and 0.28%, respectively, when compared to GOA. The results obtained by other algorithms are worse than those obtained by GOA. This study also showed that SMA effectively considers multi-objective functions by using the weighted sum method and the fuzzy decision-maker to approach the Pareto-optimal solution, achieving a good tradeoff between operational cost and emissions in each scenario. [ABSTRACT FROM AUTHOR]

In the context of global carbon emission reduction, solar photovoltaic (PV) technology is experiencing rapid development. Using high-resolution remote sensing images to accurately obtain PV information over a large region, including location and size, has the advantages of high statistical efficiency and timely data update for the PV energy management. Due to the intra-class diversity of PV panels and the intricate variability in their deployment environments, existing semantic segmentation methods often have problems such as under-segmentation and mis-segmentation. To alleviate these problems, this paper proposes an improved DeepLabv3+ semantic segmentation network to more accurately extract PV panels from high-resolution remote sensing images. With the aim of alleviating under-segmentation, a multi-level context aggregation module is developed. This module can enhance the model's ability to learn the characteristics of PV panels and their surrounding environment by aggregating rich contextual information from multi-scale and semantic levels. To alleviate the problem of mis-segmentation, a hybrid attention module is introduced. This module sequentially and adaptively adjusts the weight distribution in both the channel and spatial dimensions, thus enabling the model to focus more on the feature information and spatial positions of PV objects. Experiments conducted on a self-constructed Beijing PV segmentation dataset show that the method in this paper has advantages of completeness and accuracy in extracting PV panels compared to the baseline model and current mainstream semantic segmentation network. In addition, the results of experiments on extracting PV panels in real region show that our model also has good stability and generalization capability. [ABSTRACT FROM AUTHOR]

Globally, and especially in developing nations, the increasing demand for energy, coupled with transmission and consumption inefficiencies, poses significant challenges. As the proliferation of household appliances and electric vehicles (EVs) rises, dependency on electricity surges, further straining the existing power infrastructure. While renewable energy resources (RERs) such as solar and wind gain traction, the reliance on conventional utilities persists, especially in homes. This reliance, especially on fossil fuels, intensifies environmental concerns due to greenhouse gas emissions. This paper presents the smart household energy management system (SHEMS), designed to optimize domestic energy consumption. Capitalizing on the Internet of Things (IoT), SHEMS offers real-time energy monitoring and management, providing homeowners an adaptable architectural framework to regulate their energy use. Fundamental component of SHEMS is a controller interfacing with all household loads and the main meter, ensuring timely data on power consumption. Notably, during peak times, the system can autonomously adjust appliance settings, balancing energy savings without compromising user convenience. Paired with a user-friendly application, SHEMS provides individuals comprehensive oversight of their consumption patterns, fostering more sustainable energy use in an increasingly electrified world. [ABSTRACT FROM AUTHOR]

In recent years, extreme focus on renewable energy has intensified due to environmental concerns and the depletion of fossil fuel supplies. In a DC microgrid that includes AC grid, photovoltaic (PV), wind, and battery storage systems, there are some problems such as intermittency and variability, mismatched generation and demand, inefficient energy utilization by storage batteries, and unstable DC link voltage. To overcome these problems, an integrated strategy for better energy management and a new MPPT technique is proposed in this research. The robust model predictive control (RMPC) method is proposed to deal with uncertainties and disturbances while offering the best possible control options. A comparison of the two algorithms reveals that the RMPC performs better than the conventional model predictive control (MPC) method. To harvest the maximum solar electricity from the PV system, a sophisticated MPPT optimization technique called muddled tuna swarm optimization (MTSO) is applied. Drone squadron optimization (DSO) and slime mould optimization (SMO) are outperformed by MTSO in terms of dynamic performance, effectively tracking the maximum power point (MPP) of the PV system even under various irradiance conditions. The suggested RMPC approach and MTSO technique are effective in achieving optimal energy and battery management as well as maximum solar power extraction, according to the simulation findings. On the OPAL-RT platform, real-time simulation is used to test the control strategy. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid NBO–SDRN approach for a solar PV (SPV) array fed water pumping system utilizing a single-ended primary inductor converter (SEPIC) based BLDC motor drive. The proposed hybrid method combines Namib beetle optimization algorithm (NBO) and spiking deep residual networks (SDRN). Commonly, it is named the NBO–SDRN technique. The main goal of the NBO–SDRN method is enhanced energy efficiency, improved control algorithms, and optimal utilization of available solar energy resources. This paper focuses on integrating a SEPIC converter-based brushless DC motor drive in such systems to optimize energy conversion, enhance control, and promote environmentally friendly water supply. The BLDC (brushless direct current) motor drive and advanced control algorithms enable precise speed and torque control, improving overall energy efficiency and adaptability to varying water demand. By then, the NBO–SDRN method is done in the MATLAB working stage, and the execution is calculated with the present procedures. The proposed approach performs better outcomes in all existing singular spectrum analysis (SSA), heap-based optimization (HBO), and bee circle search algorithm (CSA) methods. From the result, the NBO–SDRN method-based efficiency is 95% higher than the existing methods. [ABSTRACT FROM AUTHOR]

This article proposed the architecture of a stand-alone photovoltaic connected system (SPVS) with energy storage. An SPVS with energy storage requires power management for various operating modes. A coordinate controller is often necessary to manage the change in control architecture depending on the operating mode. This proposed system contains a boost converter (BC) and a bidirectional switched quasi-Z-source DC-DC converter (BSQZSDC). The BC is used for two purposes. The first is extracting the maximum power from the PV. The second is to control the DC link voltage when the SPVS is not in MPPT mode; dual-loop PI controllers are used for this. The BSQZSDC is used for energy management and regulates DC link voltage when SPVS operates in MPPT mode. This paper addresses about the effective control approach that BSQZSDC used, i.e., the double-integral sliding mode control, to regulate the DC link voltage and battery current in various operating modes. Experimental results were carried out to depict that the controller reasonably achieves the control objectives and proper energy management. [ABSTRACT FROM AUTHOR]

Due to increasing load demand and the energy crisis, microgrids (MGs) have attracted more attention. The idea and technology of microgrids (MGs) have undergone significant advancements largely aimed at enabling the automation of distribution systems and enhance the integration of renewable energy sources (RESs). In this paper, the MG is a combined form of various distributed generations (DGs), battery energy storage system (BESS), and plug-in hybrid electric vehicles (PHEVs). A novel approach is introduced to minimize the operational expenses of the grid-connected low-voltage microgrid by leveraging a probabilistic expert optimization technique. This methodology takes into account various factors such as power supply costs, power dissipation, PHEV charging requirements, and the optimal capacity of BESS. Three charging techniques are proposed in this paper to control the PHEVs' charging demand at homes and public charging stations. This study employs a comprehensive model to simulate a whole day, accounting for the stochastic charging requirements of PHEVs, load profiles, RESs outputs, and variations in energy price. To address the inherent nonlinearity of the optimization problem, the energy management within the MG is tackled using the slime mould algorithm, a population-based stochastic optimizer. The primary goal is to minimize operational costs in the microgrid by optimizing the efficient utilization of available resources. [ABSTRACT FROM AUTHOR]

In this paper, a dynamic parameters lightning search algorithm (DP-LSA) is proposed for optimal operation management of electric vehicle (EV) parking lots (PLs) and distributed generations (DGs) in a microgrid (MG). The MG comprises distributed generation sources such as diesel generators and fuel cells. The batteries of electric vehicles parked in the PL are also used for energy storage. A proposed objective function combines operating, maintenance, and replacement costs, considering inflation, motivation, and annual growth. Simulations are done in two scenarios, and the proposed algorithm results are compared with particle swarm optimization (PSO) algorithm results. Simulation results prove the better performance of the proposed LSA algorithm than the PSO algorithm in reducing the microgrid operation cost. [ABSTRACT FROM AUTHOR]

State-of-the-art smart cities have been calling for economic but efficient energy management over a large-scale network, especially for the electric power system. It is a critical issue to monitor, analyze, and control electric loads of all users in the system. In this study, a non-intrusive load monitoring method was designed for smart power management using computer vision techniques popular in artificial intelligence. First of all, one-dimensional current signals are mapped onto two-dimensional color feature images using signal transforms (including the wavelet transform and discrete Fourier transform) and Gramian Angular Field (GAF) methods. Second, a deep neural network with multi-scale feature extraction and attention mechanism is proposed to recognize all electrical loads from the color feature images. Third, a cloud-based approach was designed for the non-intrusive monitoring of all users, thereby saving energy costs during power system control. Experimental results on both public and private datasets demonstrate that the method achieves superior performances compared to its peers, and thus supports efficient energy management over a large-scale Internet of Things network. [ABSTRACT FROM AUTHOR]

In the context of rapidly increasing energy demands and environmental concerns, optimizing energy management in commercial buildings is a critical challenge. Smart grids, empowered by advanced Energy Management Systems (EMS), play a pivotal role in addressing this challenge through Demand Side Management (DSM). However, the efficiency of DSM-based building EMS is often limited by the accuracy of load forecasting. This paper addresses this gap by exploring load forecasting models within DSM-based building EMS, focusing on a case study in a commercial building in Ankara, Turkey. Employing Deep Learning (DL) models for load forecasting, we provide inputs for rule-based controllers to enhance energy efficiency. Our major contribution is the development of the ANFIS-IC algorithm, aimed at maximizing demand response participation in commercial buildings. ANFIS-IC, integrating ANFIS controllers with LSTM-based load consumption forecasts, leads to a 33.14% reduction in energy consumption and a 39.22% decrease in energy costs, surpassing the performance of rule-based controllers alone which achieve reductions of 25.34% in energy consumption and 34.03% in energy costs. These findings not only highlight the potential of integrating rule-based controllers with deep learning algorithms but also underscore the importance of accurate load forecasting in improving the effectiveness of DSM-based building EMS. [ABSTRACT FROM AUTHOR]

Electricity consumption in homes is on the rise due to the increasing prevalence of home appliances and longer hours spent indoors. Home energy management systems (HEMSs) are emerging as a solution to reduce electricity consumption and efficiently manage power usage at home. In the past, numerous studies have been conducted on the management of electricity production and consumption through solar power. However, there are limited human-centered studies focusing on the user's lifestyle. In this study, we propose an Intelligent Home Energy Management System (i-HEMS) and evaluate its energy-saving effectiveness through a demonstration in a standard house in Korea. The system utilizes an IoT environment, PID sensing, and behavioral pattern algorithms. We developed algorithms based on power usage monitoring data of home appliances and human body detection. These algorithms are used as the primary scheduling algorithm and a secondary algorithm for backup purposes. We explored the deep connection between power usage, environmental sensor data, and input schedule data based on Long Short-Term Memory network (LSTM) and developed an occupancy prediction algorithm. We analyzed the use of common home appliances (TV, computer, water purifier, microwave, washing machine, etc.) in a standard house and the power consumption reduction by the i-HEMS system. Through a total of six days of empirical experiments, before implementing i-HEMS, home appliances consumed 13,062 Wh. With i-HEMS, the total consumption was reduced to 10,434 Wh (a 20% reduction), with 9060 Wh attributed to home appliances and 1374 Wh to i-HEMS operation. [ABSTRACT FROM AUTHOR]

The results shown in this paper extend our research group's previous work, which presents the theoretically achievable hydrogen engine-out NO ​ x eo (H ​ 2 -NO ​ x eo ) Pareto front of a hydrogen hybrid electric vehicle (H ​ 2 -HEV). While the Pareto front is calculated offline, which requires significant computing power and time, this work presents an online-capable algorithm to tackle the energy management of a H ​ 2 -HEV with explicit consideration of the H ​ 2 -NO ​ x eo trade-off. Through the inclusion of realistic predictive data on the upcoming driving mission, a model predictive control algorithm (MPC) is utilized to effectively tackle the conflicting goal of achieving low hydrogen consumption while simultaneously minimizing NO ​ x eo . In a case study, it is shown that MPC is able to satisfy user-defined NO ​ x eo limits over the course of various driving missions. Moreover, a comparison with the optimal Pareto front highlights MPC's ability to achieve close-to-optimal fuel performance for any desired cumulated NO ​ x eo target on four realistic routes for passenger cars. [ABSTRACT FROM AUTHOR]

With the rapid development of renewable energy and the increasing maturity of energy storage technology, microgrids are quickly becoming popular worldwide. The stochastic scheduling problem of microgrids can increase operational costs and resource wastage. In order to reduce operational costs and optimize resource utilization efficiency, the real-time scheduling of microgrids becomes particularly important. After collecting extensive data, reinforcement learning (RL) can provide good strategies. However, it cannot make quick and rational decisions in different environments. As a method with generalization ability, meta-learning can compensate for this deficiency. Therefore, this paper introduces a microgrid scheduling strategy based on RL and meta-learning. This method can quickly adapt to different environments with a small amount of training data, enabling rapid energy scheduling policy generation in the early stages of microgrid operation. This paper first establishes a microgrid model, including components such as energy storage, load, and distributed generation (DG). Then, we use a meta-reinforcement learning framework to train the initial scheduling strategy, considering the various operational constraints of the microgrid. The experimental results show that the MAML-based RL strategy has advantages in improving energy utilization and reducing operational costs in the early stages of microgrid operation. This research provides a new intelligent solution for microgrids' efficient, stable, and economical operation in their initial stages. [ABSTRACT FROM AUTHOR]

Energy management strategies play a crucial role in enhancing the fuel efficiency of hybrid electric vehicles (HEVs) and mitigating greenhouse gas emissions. For the current commonly used time horizon optimization methods that only target the trend curve of the optimal battery state of charge (SOC) trajectory obtained offline, which are only suitable for buses with known future driving conditions, this paper proposed an energy management strategy based on an adaptive network-based fuzzy inference system (ANFIS) that optimizes the time horizon length and enhances adaptability to driving conditions by integrating historical vehicle velocity, accelerations, and battery SOC trajectory. First, the vehicle velocity prediction model based on the radial basis function (RBF) neural network is used to predict the future velocity sequence. After that, ANFIS was used to optimize and update the length of the forecast time horizon based on the historical vehicle velocity sequence. Finally, compared with the fixed time horizon energy management strategy, which is based on model predictive control (MPC), the average calculation time of the energy management strategy is reduced by about 23.5%, and the fuel consumption per 100 km is reduced by about 6.12%. [ABSTRACT FROM AUTHOR]

Energy management systems allow the Smart Grids industry to track, improve, and regulate energy use. Particularly, demand-side management is regarded as a crucial component of the entire Smart Grids system. Therefore, by aligning utility offers with customer demand, anticipating future energy demands is essential for regulating consumption. An updated examination of several forecasting techniques for projecting energy short-term load forecasts is provided in this article. Each class of algorithms, including statistical techniques, Machine Learning, Deep Learning, and hybrid combinations, are comparatively evaluated and critically analyzed, based on three real consumption datasets from Spain, Germany, and the United States of America. To increase the size of tiny training datasets, this paper also proposes a data augmentation technique based on Generative Adversarial Networks. The results show that the Deep Learning-hybrid model is more accurate than traditional statistical methods and basic Machine Learning procedures. In the same direction, it is demonstrated that more comprehensive datasets assisted by complementary data, such as energy generation and weather, may significantly boost the accuracy of the models. Additionally, it is also demonstrated that Generative Adversarial Networks-based data augmentation may greatly improve algorithm accuracy. [ABSTRACT FROM AUTHOR]

Metal-organic frameworks (MOFs) hold great promise for diverse applications when combined with polymers. However, a persistent challenge lies in the susceptibility of exposed MOF pores to molecule and polymer penetration, compromising the porosity and overall performance. Here, we design a molecular-caged MOF (MC-MOF) to achieve contracted window without sacrificing the MOF porosity by torsional conjugated ligands. These molecular cages effectively shield against the undesired molecule penetration during polymerization, thereby preserving the pristine porosity of MC-MOF and providing outstanding light and thermal management to the composites. The polymer containing 0.5 wt % MC-MOF achieves an 83% transmittance and an exceptional haze of 93% at 550 nanometers, coupled with remarkable thermal insulation. These MC-MOF/polymer composites offer the potential for more uniform daylighting and reduced energy consumption in sustainable buildings when compared to traditional glass materials. This work delivers a general method to uphold MOF porosity in polymers through molecular cage design, advancing MOF-polymer applications in energy and sustainability. [ABSTRACT FROM AUTHOR]

Background: Increased working from home has imposed new challenges on public service employees, while also granting opportunities for job crafting. Grounding on the Job Demands-Resources model and Hobfoll's Conservation of Resources theory this exploratory research aims to investigate the work-nonwork balance of employees one and a half years after the outbreak of the COVID-19 pandemic. Therefore, the research focus lies on employees' job crafting strategies to optimize their working from home experience concerning boundary management and energy resource management. Methods: Twelve semi-structured telephone interviews were conducted with public service employees from different sectors in Germany. The experiences were content analyzed using the software MaxQDA and inductive and deductive categories were derived. Results: Boundary management comprised different strategies such as communicative (e.g., negotiating work time), physical (e.g., going to the garden), temporal (e.g., logging off in between the work day) and behavioral (e.g., prioritizing tasks) strategies. The job crafting strategies regarding energy management included preventing exhaustion (e.g. taking breaks), healthy cooking and energy management in case of sickness (e.g. deciding on sick leave). Conclusions: This qualitative case study enriches research on job crafting by offering insights on boundary tactics and energy resources management strategies for remote working during the COVID-19 pandemic. The results point out different starting points for employees and decision makers, how a work-nonwork balance, energy management and thus employees' wellbeing may be increased when working from home in the future. Trial registration: The study design and methodology were approved by the Ethics Committee of the University of Cologne and the study was prospectively registered (Ref No. 21-1417_1). [ABSTRACT FROM AUTHOR]

This paper addresses the limited adaptability and the computational burden of energy management systems (EMSs) for hybrid electric vehicles (HEVs) implemented via dynamic programming (DP)-based approaches. First, a deterministic dynamic programming (DDP) framework is presented to solve HEV EMS problems subject to a specific driving cycle. To address this limitation, an improved DDP approach, integrating the actual travelled position of the vehicle into the control law, is proposed. This way, a given DDP-based EMS can be applied to all the driving cycles, yet still measured on the same road. Stochastic dynamic programming (SDP)-based EMSs are also developed and prove to be more adaptive to driving scenarios completely different from the ones used for their computation. Real-world driving cycles are employed in all the presented cases, while a reduced HEV powertrain model is used to alleviate the typical DP computational burden. [ABSTRACT FROM AUTHOR]

In this study, an online monitoring system was implemented for the operational control of an industrial-scale steam generation system. The proposed system allows the migration from measuring boiler efficiency under stationary conditions to measuring it under seasonal conditions, providing greater opportunities for improvement in energy performance. For this purpose, a baseline and goal line model of energy consumption as a function of steam production for an operational base period was constructed. The study shows that the steam generation process has a consumption rate of 0.0885 m³/kg, which is associated with boiler technology, fuel quality, insulation condition, heat recovery equipment, among others. In addition, there is evidence of non-production consumption of 41.225 m³/h, which is mainly due to average consumption in non-productive maneuvers such as starting, stopping, and searching for an operating regime in response to changes in steam demand. The correlation between gas consumption and steam generation was 86.4 %, which represents a 13.6 % variability of consumption associated with controllable operational variables with opportunity for adjustment. The monitoring and control of the main operating parameters of the boiler allows an economic savings of 3.13 % in the boiler, which implies a reduction in operating costs of 92,843 USD per year. The analysis of the operational parameters indicates that it is necessary to maintain a feed water temperature higher than 65 °C and a flue gas temperature lower than 214 °C to ensure boiler efficiency higher than 80 %. With the implementation of activities focused on reducing the combustion gas temperature, increasing the feed water temperature, and controlling operational variables, a 9.01 % reduction in the boiler's natural gas consumption was achieved because of the implementation of operational control. [ABSTRACT FROM AUTHOR]

Alternative energy sources are needed for a sustainable world due to rapidly increasing energy consumption, fossil fuels, and greenhouse gases worldwide. A hybrid renewable energy system (HRES) must be optimally dimensioned to be responsive to sudden load changes and cost-effective. In this study, the aim is to reduce the carbon emissions of a university campus by generating electricity from a hybrid energy production system with solar panels, wind turbine, a diesel generator, and battery components. On the university campus where the hybrid energy system will be installed, the ambient temperature, solar radiation, wind speed, and load demands have been recorded in our database. Optimization algorithms were used to select the power values of the system components to be installed using these data in an efficient and inexpensive manner according to the ambient conditions. For optimal sizing of HRES components, gray wolf optimizer combined with cuckoo search (GWOCS) technique was investigated using MATLAB/Simulink. In this way, it has been tried to increase their efficiency by combining current optimization techniques. The cornerstone of our optimization efforts for both on-grid and off-grid models pivots on a constellation of critical decision variables: the power harvested from wind turbines, the productivity of solar panels, the capacity of battery storage, and the power contribution of diesel generators. In our pursuit of minimizing the annual cost metric, we employ a tailor-made function, meticulously upholding an array of constraints, such as the quotient of renewable energy and the potential risk of power disruption. A robust energy management system is integral to our design, orchestrating the delicate power flow balance among micro-grid components—vital for satisfying energy demand. Upon analyzing the outcomes of the study, it is apparent that the proposed Scenario 1 HRES effectively utilizes solar and battery components within the off-grid model, surpassing the efficiency of four other hybrid scenarios under consideration. Regarding optimization processes, the off-grid model exhibits superior results with the implementation of the GWOCS algorithm, delivering faster and more reliable solutions relative to other methodologies. Conversely, the optimization of the on-grid model reaches its optimal performance with the application of the cuckoo search algorithm. A comprehensive comparison from both technical and economic view points suggests the on-grid model as the most feasible and suitable choice. Upon completion of the optimization process, the load demand is catered to by a combination of a 2963.827-kW solar panel, a 201.8896-kW battery, and an additional purchase of 821.9 MWh from the grid. Additionally, an energy surplus sale of 1379.8 MWh to the grid culminates in an annual cost of system (ACS) of 475782.8240 USD, a total net present cost of 4815520.2794 USD, and a levelized cost of energy of 0.12754 USD/kWh. Solar panels cover the entire system, and the renewable energy fraction is 100%. [ABSTRACT FROM AUTHOR]

Energy generation and pollutant emissions are two faces of the same coin, as the current energy sources i.e., fossil energy, are still considered to be major sources of greenhouse gases (GHG). Therefore, shifting to cleaner energy sources imposes itself as an inevitable solution to reduce this environmental cost. In this paper, a hybrid system based on the multi-agent approach and Long Short-Term Memory (LSTM) neural networks to forecast the energy production and its carbon dioxide (CO2) emissions and simulate the potential emission reduction in case of switching to renewable energy sources is presented. The proposed system's architecture consists of combining LSTM models with the agent-based technology, where multiple LSTM forecasting models were trained to forecast the production of each type of the studied energies and then estimate the equivalent emitted CO2 and calculate the influence of the renewable energy inputs on the carbon emissions and the fossil fuels consumption. The simulation process consists of two phases: firstly, each forecasting agent uses a specific LSTM model to forecast short-term energy production. Secondly, these agents send the forecasted values to the coordination agent who is responsible for calculating the total CO2 emissions and the benefits of the renewable energy inputs. [ABSTRACT FROM AUTHOR]

A lithium-ion battery–ultracapacitor hybrid energy storage system (HESS) has been recognized as a viable solution to address the limitations of single battery energy sources in electric vehicles (EVs), especially in urban driving conditions, owing to its complementary energy features. However, an energy management strategy (EMS) is required for the optimal performance of the HESS. In this paper, an EMS based on the particle swarm optimization (PSO) of the fuzzy logic controller (FLC) is proposed. It aims to minimize battery current and power peak fluctuations, thereby enhancing its capacity and lifespan, by optimizing the weights of formulated FLC rules using the PSO algorithm. This paper utilizes the battery temperature as the cost function in the optimization problem of the PSO due to the sensitivity of lithium-ion batteries (LIBs) to operating temperature variations compared to ultracapacitors (UCs). An evaluation of optimized FLC using PSO and a developed EV model is conducted under the Urban Dynamometer Driving Schedule (UDDS) and compared with the unoptimized FLC. The result shows that 5.4% of the battery's capacity was conserved at 25.5 °C, which is the highest operating temperature attained under the proposed strategy. [ABSTRACT FROM AUTHOR]

This article aims to demonstrate the technical capabilities and effectiveness of an energy production and management system for school facilities using a modular solution. The system is assumed to generate electricity from renewable sources, such as wind or sun. The potential of renewable energy sources in Cracow, Poland, was assessed, with a focus on solar energy (photovoltaic panels, PV). Taking into account the installation of heating and other equipment, an analysis of the facility's electricity demand was carried out. The study recommended the use of a heat pump system to heat and cool the facility. Renewable energy sources will meet 81% of the facility's projected annual demand, according to the study. An analysis of the energy consumption and production profiles shows that almost 69% of the energy produced by the PV panels is consumed on site. Of the remaining energy, 31% is fed back into the grid and sold to the grid operator or used by other facilities within the shared settlement. The overall balance results in a small electricity deficit that must be covered by the grid. If suitable sites are available, the facilities under study could consider installing a wind turbine as a potential supplement to the energy deficit. [ABSTRACT FROM AUTHOR]

Non-Intrusive Load Monitoring (NILM), which provides sufficient load for the energy consumption of an entire building, has become crucial in improving the operation of energy systems. Although NILM can decompose overall energy consumption into individual electrical sub-loads, it struggles to estimate thermal-driven sub-loads such as occupants. Previous studies proposed Non-Intrusive Thermal Load Monitoring (NITLM), which disaggregates the overall thermal load into sub-loads; however, these studies evaluated only a single building. The results change for other buildings due to individual building factors, such as floor area, location, and occupancy patterns; thus, it is necessary to analyze how these factors affect the accuracy of disaggregation for accurate monitoring. In this paper, we conduct a fundamental evaluation of NITLM in various realistic office buildings to accurately disaggregate the overall thermal load into sub-loads, focusing on occupant thermal load. Through experiments, we introduce NITLM with deep learning models and evaluate these models using thermal load datasets. These thermal load datasets are generated by a building energy simulation, and its inputs for the simulation were derived from realistic data like HVAC on/off data. Such fundamental evaluation has not been done before, but insights obtained from the comparison of learning models are necessary and useful for improving learning models. Our experimental results shed light on the deep learning-based NITLM models for building-level efficient energy management systems. [ABSTRACT FROM AUTHOR]

A novel framework for adaptive energy management, rooted in deep learning principles, is proposed to minimize fuel consumption in extended‐range electric vehicles amidst intricate driving scenarios. This innovative approach integrates a long short‐term memory (LSTM) network for pattern recognition across three driving patterns and an adaptive fuzzy controller. To mitigate the impact of poor hyperparameter selection on recognition accuracy, Gray Wolf Optimization is employed to optimize the hidden layer nodes, training times, and learning rate of the LSTM. Simultaneously, a genetic algorithm is utilized to optimize the vertex coordinates of the fuzzy control membership function, enabling the adaptive adjustment of parameters in the fuzzy energy management strategy. The condition recognition model accurately identifies the vehicle's driving status and seamlessly transitions to an energy management strategy tailored to the present conditions. This ensures optimal operation, enhancing overall fuel efficiency and performance. The simulation results robustly validate the efficacy of this approach: the GWO‐LSTM network achieves an impressive 97.7% accuracy in recognizing working conditions, surpassing the 88.9% accuracy of the traditional LSTM network. Furthermore, the fuel consumption reduction achieved by the adaptive fuzzy energy management strategy amounts to 11.9% compared with the conventional fuzzy energy management approach. This outcome underscores the tangible enhancement in vehicle fuel economy resulting from the seamless integration of deep learning techniques. [ABSTRACT FROM AUTHOR]

The broad demonstration of grid-forming converters (GFMs) in microgrid applications has been well documented. Following this, the idea of GFM was assessed for its potential use in large-scale linked networks that include transmission and distribution systems combined with renewable energy sources. As a result, a thorough examination of GFM performance became imperative. This study provides a comprehensive examination of GFMs, encompassing fundamental principles, control mechanisms, implementation strategies, operational aspects, and potential avenues for further research. The capacity of GFMs to withstand system disturbances is of utmost importance for ensuring the overall stability of the system, particularly in situations where inertial response is diminished. Classical control methods are inadequate in addressing transient stability circumstances, necessitating the development of current control approaches to overcome these limitations. The utilization of GFM control is becoming increasingly important in the global initiative to establish a sustainable energy system through the integration of renewable energy. GFM control is particularly significant as it determines the level of controllability over non-dispatchable and variable generation, especially on a larger scale, thus contributing to the practical realization of this initiative. Therefore, an extensive and evaluative examination of many control systems, control theories, and algorithms has been conducted in the last twenty years. This study provides a comprehensive classification of control objectives and applications, emphasizing their importance and effectiveness. The findings of this study are equally applicable to various interdisciplinary fields such as power system operation, power electronics, renewable energy integration, advanced control, and smart grids. [ABSTRACT FROM AUTHOR]

Effective control of inner climatic conditions in a Heating ventilation and air conditioning (HVAC) system based on efficiency of the system is imperative to ensure occupant comfort, energy efficiency, and preservation of indoor air quality. The existing problems with HVAC system includes inefficient adjustment to internal room parameters and limited optimization based on varying loads. The current study investigates the influence of Industry 4.0 by assessing internal room parameters in an indoor ventilated room conditions for system output. Smart systems like AI and IoT, integrated with sensors, dynamically adjust indoor conditions based on external climate, enhancing HVAC system efficiency. Using Artificial Neural Networks (ANN) and Response Surface Methodology (RSM), integrated with AI and IoT sensors, optimally adjust indoor conditions in correlation with external climate, maximizing HVAC system efficiency. The study utilizes input parameters including Dry Bulb Temperature (DBT), Relative Humidity (RH), and Solar Radiation across diverse days to analyze system efficiency. ANN and RSM iteratively optimize system efficiency by training on RH, DBT, and air quality data. They converge on recommending 42% RH, 28 °C DBT, and 25 PM air quality, achieving 0.851 desirability. This approach enhances heat load (75.89%) and ventilation load (69.12%) efficiency significantly. Integration of Industry 4.0 sensors in the HVAC system resulted in a 16% efficiency increase and 15% cost effectiveness in the controlled room compared to prior measurements. [ABSTRACT FROM AUTHOR]

This paper considers a resource allocation problem involving servers and mobile users (MUs) operating in a serverless edge computing (SEC)-enabled Internet of Things (IoT) network. Each MU has a fixed budget, and each server is powered by the grid and has energy harvesting (EH) capability. Our objective is to maximize the revenue of the operator that operates the said servers and the number of resources purchased by the MUs. We propose a Stackelberg game approach, where servers and MUs act as leaders and followers, respectively. We prove the existence of a Stackelberg game equilibrium and develop an iterative algorithm to determine the final game equilibrium price. Simulation results show that the proposed scheme is efficient in terms of the SEC's profit and MU's demand. Moreover, both MUs and SECs gain benefits from renewable energy. [ABSTRACT FROM AUTHOR]

This research introduces a pioneering Energy Management System (EMS) for microgrids, integrating fuzzy neural networks and a modified particle swarm optimization (MPSO) algorithm. The key contribution lies in minimizing production costs while optimizing the use of renewable sources like photovoltaic (PV), wind turbines (WT), and energy storage. The novel approach considers time-dependent constraints, ensuring adaptability and superior system performance. Additionally, the study introduces an innovative demand response (DR) analysis using a neural-fuzzy network, enhancing customer response and energy cost dynamics. The MPSO algorithm addresses economic load distribution challenges, demonstrating superior performance in comparative analysis. This integrated approach offers a groundbreaking solution for sustainable and efficient energy planning in microgrids. The analysis demonstrates that the proposed method achieves higher energy savings (83%) compared to baseline levels of 72%, showcasing its superior efficiency. Comparative analysis with genetic and particle swarm optimization algorithms reveals consistently lower average expenses and increased cost-effectiveness with the proposed approach. • FNN with modified PSO algorithm is proposed for analyzing the EMS in MG. • PV, WT, MT, FC and Battery are considered as the MG. • Demand response (DR) is evaluated using FNN method. • The objective function is to minimize the cost functions and maximum profits. • Consider various operating conditions and evaluate them with statital indecs. [ABSTRACT FROM AUTHOR]

—Using hydrogen production as energy storage can realize large-scale storage and transportation of energy, which is conducive to flexible scheduling of offshore wind power resources. However, compared with the battery energy storage system, the energy management strategy (EMS) of the dual-storage offshore wind power system with hydrogen production is more complex and nonlinear due to the large number of state variables and control variables. In order to realize the EMS of the system to maximize the benefits and minimize the aging cost, a nonlinear convex model is first established, and then an iterative solution method combining convex programming (CP) and dynamic programming (DP) is proposed. Among them, CP solves the global optimization problem of power distribution, and DP determines the start and stop of the electrolyzer. Finally, the feasibility of the proposed method is verified by simulation analysis. [Display omitted] • Conversion among different working states of the electrolyzer is considered, including cold start and warm start. • Degradation models of the electrolyzer and battery storage are considered for their state of health preservation. • An iterative algorithm combing dynamic programming and convex programming is proposed to search the optimal power splits and the electrolyzer state. [ABSTRACT FROM AUTHOR]

Considering different applications that require varied power and voltage conversion levels between AC grids and AC loads, AC–AC power conversion between AC grids has become an inevitable technology of energy management systems. An isolated converter for performing AC-to-AC transmission is proposed with minimal components for reduced losses and enhanced system efficiency. Single-phase direct buck-boost AC to AC converter with minimum components constituted with two dual IGBT control units (IGBT 1–IGBT 4), inductor (Lf), and capacitor (Cf) is proposed in this work. The MATLAB/Simulink platform is used to provide in-depth analysis of the circuit and components along with the design guidelines, and simulation outcomes of this proposed model. The voltage gains of G = 2.13, power factor of 0.97, and overall efficiency of 98% are achieved in the proposed system with minimum components of 4 switches, 2 conductors, and 1 capacitor and inductor respectively. The obtained results are compared with existing technology to evaluate the proposed system. [ABSTRACT FROM AUTHOR]

Realizing efficient energy utilization from the heat source of the sun and the cold source of outer space is of great significance for addressing the global energy and environmental crisis. Materials with ideal full‐spectrum solar absorption and infrared emission are highly desirable for adapting to the continuous weather dynamic throughout the day, nonetheless, their development remains challenging. Here, a polymer nanocomposite with full‐spectrum strong solar (280–2500 nm) absorption ranging from 88.8% to 94.8% with an average value of 93.2% and full‐spectrum high infrared (8–13 µm) emission ranging from 81.3% to 90.0% with an average value of 84.2%, is reported by melt‐processing polypropylene and uniformly dispersed low‐loading MXene nanosheets (1.9 vol%). The nanocomposite can achieve daytime photothermal enhancement of ≈50 °C and nighttime radiative cooling of 8 °C. The temperature difference throughout the day ensures all‐day uninterrupted thermoelectric generation, yielding a power density output of 1.5 W m−2 (daytime) and 7.9 mW m−2 (nighttime) in real outdoor environment without any additional energy consumption. This work provides an impressive polymer nanocomposite with ideal full‐spectrum solar absorption and infrared emission for all‐day uninterrupted thermal energy management and conversion. [ABSTRACT FROM AUTHOR]

Hydrogen energy storage systems (HESS) play an essential role in Microgrid (MG) systems to address the inherent generation characteristics of renewable energy sources. Also, the integration of Demand Response (DR) into the Energy Management System (EMS) of a renewable-based Multi-Microgrid (MMG) can lead to substantial technical and economic benefits. This paper proposes a modified optimization algorithm for optimizing MMG Energy Management (EM). The proposed algorithm is a modified version of the Student Psychology-Based Optimization (SPBO) technique called Modified Student Psychology-Based Optimization (MSPBO). This modification aims to improve issues such as slow convergence, low solution accuracy, lack of diversity, and getting stuck in local optima. The proposed MSPBO method incorporates a local escape operator and a collaborative student class to achieve a better balance between exploiting known solutions and exploring new possibilities. The MSPBO algorithm is applied to address the EM challenge within a MMG context. Considering the integration of renewable sources as Wind turbines and solar photovoltaic and the HESS, the EM problem is formulated as a two-stage multi-objective optimization: minimizing the operating cost of conventional generators and power transactions cost in addition to the cost of HESS, while maximizing operator benefits and peak load reduction. This multi-objective problem is tackled using a hybrid ε-lexicography–weighted-sum approach that avoids the need for normalization. The performance of the proposed MSPBO is evaluated using CEC 2017 benchmark test functions, utilizing various statistical measures such as best, average, worst, rank, and standard deviation (SD) of fitness values, along with Wilcoxon's rank-sum test. The MSPBO technique is compared with other optimization algorithms for these test functions, highlighting its efficiency and adeptness in achieving a harmonious trade-off between exploiting known solutions and exploring new ones. Furthermore, the MSPBO method is applied to solve two case studies. In Case 1, which involves a single stage with conventional demand response optimization, the results achieved using MSPBO are benchmarked against other optimization techniques, revealing its superior efficacy in addressing the EM challenge. In Case 2, a more complex two-stage multi-objective problem is tackled using MSPBO, and the assessment of the integration of HESS in the MMG is evaluated. In the second stage, there is a notable enhancement in peak load reduction percentage (PRP), from 13.9% to 16.13% without the HESS and from 12.68% to 16.46% with the integration of HESS. [ABSTRACT FROM AUTHOR]

Among the global carbon emissions in different fields, the carbon emissions in the transportation sector account for more than 1/4. Only the development of passenger car technology makes it difficult to achieve the climate goals. E-bike is considered to be one of the effective solutions. Hydrogen energy, as one of the representatives of new energy, has the advantages of cleanliness, high efficiency, and high energy density. Therefore, in this paper, a long-range hydrogen-electric hybrid bike and its energy management strategy are designed to achieve optimal performance. Herein, two energy management strategies, including the threshold-based and fuzzy logic optimized threshold-based strategy, are designed and compared by evaluating the parameters of equivalent hydrogen consumption, state of charge fluctuation, and the final state of the control system. The results show that with an initial SOC of 50% for Li-ion battery, the fuzzy logic optimized threshold-based strategy reduces equivalent hydrogen consumption by up to 16% compared to the threshold-based strategy. Besides, the fluctuation of the Li-ion battery's state of charge could be reduced by up to 54.7%, indicating that the fuzzy logic optimized threshold-based strategy is a promising energy management strategy for fuel cell hybrid E-bike. [Display omitted] • A long-range hydrogen-electric hybrid E-bike with metal hydride hydrogen storage is designed. • A fuzzy logic optimized threshold-based energy management strategy (EMS) is proposed. • Li-ion battery SOC fluctuations could be reduced by up to 54.7% via fuzzy logic optimized EMS. • Fuzzy logic optimized EMS shows self-adaptability and economic H 2 consumption for hybrid E-bike. [ABSTRACT FROM AUTHOR]

For hydrogen fuel cell vehicles, energy management strategies (EMS) are vital for balancing fuel cell and battery power, limiting fuel cell power, maintaining state of charge (SOC) fluctuation range and mitigating degradation. Reinforcement learning-based EMS, especially using deep Q-network (DQN) and deep deterministic policy gradient (DDPG), have demonstrated potential for enhancing the fuel economy of hybrid electric vehicles (HEV) and fuel cell electric vehicles (FCEV). This research proposes mutation protection DQN (MPD)-based EMS to improve hydrogen fuel economy and reduce fuel cell degradation under driving cycles with plenty of mutations. By quantifying mutation, exploring its relationship with driving conditions and integrating a mutation protection module with DQN, MPD-based EMS achieves approximately 11% and 6% better fuel economy compared to the other two learning-based EMS. Additionally, it also reduces fuel cell degradation by approximately 21% and 13%. • Quantifying the mutation of driving conditions through variance. • Utilizing information entropy to process mutations. • Introducing a dynamic mutation threshold value. • Designing mutation protection module and integrating it into the DQN. [ABSTRACT FROM AUTHOR]

Energy management control (EMC) becomes imperative in hybrid energy systems that involve multiple sources. The main objective of this study is to concentrate on the effective control and utilization of energy in a hybrid system combining photovoltaic solar and wind sources, together with a battery bank. A sophisticated intelligent supervisor, employing a fuzzy logic controller (FLC), adeptly balances the power generated by the proposed system in response to the load demand. Simulation results demonstrate that, despite the initial maximum battery state of charge value being set at 90%, the battery's state of charge does not exceed 60% during charging. Additionally, during discharge, the battery state of charge remains above 27%, surpassing the initially set minimum value of 25%. This achievement is attributed to the exchange of energy flow facilitated by the implemented intelligent management. The notable advantage of this intelligent management lies in its ability to precisely control the state of charge (SOC) of the battery across five distinct states, a feat not achievable with traditional management practices that rely on only two SOC levels (SOCmin–SOCmax). [ABSTRACT FROM AUTHOR]

Energy management systems are the most significant field in the potential electric vehicles (EVs). Also, EVs are widely used because of their pollution-free nature worldwide and their specific feature of flexibility. However, the EV charging system's significant challenges are power loss and high power consumption. Therefore, a robust load-balancing strategy is required to address the EV charging system's issues. Therefore, a novel intelligent hybrid Buffalo-based Recurrent Energy Management System (BREMS) has been proposed to reduce the power consumption of EVs and mitigate power losses. Here, two primary functions have been done. Initially, hydro and solar sources are modeled with the help of energy storage components and a power grid to enhance the system's efficiency. Then, the optimization fitness module is initiated to the hidden layer of the neural framework to monitor the loaded grids and distributes the loads to imbalanced grids. Implementation and designing processes have been done on the MATLAB platform. The simulation outcomes of the proposed design have been compared with conventional models in terms of power loss, cost of energy, utilization of power, and execution time. The comparative assessment shows that the presented system obtained better outcomes than other models. [ABSTRACT FROM AUTHOR]

This study aims to develop an adaptable home energy management system capable of integrating the bidirectional smart charging of electric vehicles. The final goal is to achieve a user-defined objectives such as cost minimization or maximizing renewable self-consumption. Industrialwise, the present work yields valuable outcomes in identifying operational frameworks and boundary conditions. Optimal scheduling benefits both users and the electric network, thus enhancing grid utilization and increasing renewable energy integration. By coordinating power interactions with dynamic time-of-use tariffs, the energy management system minimizes user costs and aids the grid by cutting peak hour energy consumption. Charging and discharging operations in electric vehicles comply with energy level constraints outlined by bidirectional charging protocols. The proposed approach ensures the scheduling of cycles that minimize detrimental effects on battery health when evaluating an economically ageing mechanism. Compared to uncontrolled charging, optimal scheduling resulted in a significant reduction in the total operational cost of the dwelling. Trade-off conditions between renewable integration and potential savings are identified and numerically evaluated by means of multiobjective optimization. In contrast to scheduling-based models, the proposed architecture possesses the ability to iteratively adapt decision variables in response to system changes, thus responding effectively to external stochastic uncertainty. [ABSTRACT FROM AUTHOR]

The smart transformer (ST) is a multiport and multi-stage converter that allows for the formation of meshed hybrid microgrids (MHMs) by enabling AC-DC ports in medium and low voltage. This type of microgrid has advantages over the performance of conventional hybrid AC-DC microgrids (HMGs); however, the number of degrees of freedom of the ST increases the complexity of the energy management systems (EMSs), which require adequate and accurate modeling of the power flow of the converters and the MG to find the feasible solution of optimal power flow (OPF) problems in the MHM. An ST's equivalent power flow model is proposed for formulating the MHM OPF problem and developing low-frequency equivalent models integrated with a decoupled hierarchical control architecture under a real-time simulation approach to the ST-based MHM. A simulation model of the MHM in the Simulink® environment of Matlab® 9.12 is developed and implemented under a digital real-time simulation (DRTS) approach on the OPAL-RT® platform. This model allows for determining the accuracy of the developed equivalent models, both low-frequency and power flow, and determining the MHM performance based on optimal day-ahead scheduling. Simulation test results demonstrated the ST equivalent model's accuracy and the MHM's accuracy for OPF problems with an optimal day-ahead scheduling horizon based on the model-in-the-loop (MIL) and DRTS approach. [ABSTRACT FROM AUTHOR]

This study presents a Two-Layer Deep Deterministic Policy Gradient (TL-DDPG) energy management strategy for Hydrogen fuel cell hybrid train, that aims to solve the problem that traditional reinforcement learning strategies require high initial values and are difficult to optimize global variables. Augmenting the optimization capabilities of the inner layer, a frequency decoupling algorithm integrates into the outer layer, furnishing a fitting initial value for strategy optimization. This addition aims to bolster the stability of fuel cell output, thereby enhancing the overall efficiency of the hybrid power system. In comparison with the traditional reinforcement learning algorithm, the proposed approach demonstrates notable improvements: a reduction in hydrogen consumption per 100 km by 16.3 kg, a 9.7% increase in the output power stability of the fuel cell, and a 1.8% enhancement in its efficiency. [ABSTRACT FROM AUTHOR]

The integration of distributed energy resources and smart grid technologies has increased the vulnerability and complexity of modern power systems, especially in the face of extreme events. Enhancing the resilience of power systems is crucial to ensure continuous and reliable electricity supply during and after such events. This paper proposes a preventive framework to enhance the resilience of networked microgrids (NMGs) during extreme events. The framework integrates optimal energy management strategies and preventive resilience enhancement measures, focusing on the coordination and utilization of hydrogen (H2) energy systems and controllable distributed generators (CDGs). The framework leverages capacity‐based signals to prompt H2 system owners and CDG operators to prepare for disruptions by fully charging H2 storage tanks and pre‐scheduling CDG commitments. By utilizing this proactive energy scheduling, critical loads can be supplied through stationary fuel cells and CDGs, improving overall network resilience. The proposed resilient energy management approach combines optimization techniques to improve the resilience of NMGs and reduce their dependence on the main grid. Numerical simulations demonstrate the effectiveness of the proposed linear model in enhancing the resilience of NMGs and improving their operational performance during extreme events. The contributions of this paper include advancements in understanding NMGs, the development of a preventive framework, integration of H2 energy systems and CDGs, and proposal of effective signalling models. [ABSTRACT FROM AUTHOR]

Green hydrogen (H 2) has garnered significant attention in recent years as a key component of a zero-emission future owing to its diverse range of applications. The energy management (EM) strategy of the green H 2 production system (HPS) plays a crucial role in facilitating efficient and cost-effective green H 2 production. This can be achieved by regulating the operating point of the electrolyzer (EL) to obtain economic and operational benefits. This study proposes an optimal EM scheme for a photovoltaic-based battery (BT) grid-connected green HPS. The HPS is intended to meet H 2 and electricity demands of an industrial HPS. The objective of the EM scheme is to minimize the cost of green H 2 production by minimizing the total system costs of the HPS, while ensuring that the system operates reliably. The objective is realized by incorporating the EM strategy model with Z-score statistical values of past grid electricity costs, which reflect seasonal electricity price trends. This enables green H 2 production when the utility grid electricity prices are relatively low. The EM variables considered for the optimization include: EL status (on/off operation of the EL), electricity purchased from the grid, input power to the EL and output power from EL (H 2 production rate), energy stored in the H 2 storage tank and BT, discharging and charging power of the BT and H 2 tank. Four test case systems (Case #1 - #4) were used to demonstrate the techno-economic benefits of the proposed EM scheme model for green HPS. Finally, a sensitivity analysis is performed on the green HPS to investigate the impact PV power and EL capacity on the cost of H 2 and EL efficiency. • A new energy management scheme for an industrial green hydrogen production system is proposed. • The energy management scheme model uses the Z-score statistical value of past electricity prices. • Using onsite PV power and battery storage to minimize cost of hydrogen production. • Utilizing green hydrogen in industrial processes can significantly reduce CO 2 emissions. [ABSTRACT FROM AUTHOR]

Efficient energy management in residential environments is a constant challenge, in which Home Energy Management Systems (HEMS) play an essential role in optimizing consumption. Load recognition allows the identification of active appliances, providing robustness to the HEMS. The precise identification of household appliances is an area not completely explored. Gaps like improving classification performance through techniques dedicated to separability between classes and models that achieve enhanced reliability remain open. This work improves several aspects of load recognition in HEMS applications. In this research, we adopt Neighborhood Component Analysis (NCA) to extract relevant characteristics from the data, seeking the separability between classes. We also employ the Regularized Extreme Learning Machine (RELM) to identify household appliances. This pioneering approach achieves performance improvements, presenting higher accuracy and weighted F1-Score values—97.24% and 97.14%, respectively—surpassing state-of-the-art methods and enhanced reliability according to the Kappa index, i.e., 0.9388, outperforming competing classifiers. Such evidence highlights the promising potential of Machine Learning (ML) techniques, specifically NCA and RELM, to contribute to load recognition and energy management in residential environments. [ABSTRACT FROM AUTHOR]

Fuel Cell Electric Vehicle (FCEV) powertrain layouts and control strategies have historically overlooked the asymmetric energy storage effect, despite its significant impact on system efficiency. In this study, we propose a novel FCEV powertrain layout using dual fuel cells to uncover hidden fuel efficiency improvement factors in comparison with the conventional Single Fuel Cell System (SFS). To address the issues of low efficiency operation in SFS and the limitations of existing energy management strategies that hinder high output performance, we present a minimum efficiency-based power control strategy. Additionally, we implement a partial system operation strategy to optimize efficiency according to the state of the power sources. This combined approach results in substantial improvements in both hardware and software efficiency, a possibility that was not previously achievable. Through this research, we demonstrate the potential for enhancing the fuel efficiency of the multi-stack system, a concept that has not been implemented yet. Moreover, we propose a new direction for the architectural design of FCEVs that overcomes the limitations of the SFS, thereby addressing potential malfunctions. [ABSTRACT FROM AUTHOR]

Renewable energies have become pivotal in the global energy landscape. Their adoption is crucial for phasing out fossil fuels and promoting environmentally friendly energy solutions. In recent years, the energy management system (EMS) concept has emerged to manage the power grid. EMS optimizes electric grid operations through advanced metering, automation, and communication technologies. A critical component of EMS is power forecasting, which facilitates precise energy grid scheduling. This research paper introduces a deep learning hybrid model employing convolutional neural network–long short-term memory (CNN-LSTM) for short-term photovoltaic (PV) solar energy forecasting. The proposed method integrates the variational mode decomposition (VMD) algorithm with the CNN-LSTM model to predict PV power output from a solar farm in Boussada, Algeria, spanning 1 January 2019, to 31 December 2020. The performance of the developed model is benchmarked against other deep learning models across various time horizons (15, 30, and 60 min): variational mode decomposition–convolutional neural network (VMD-CNN), variational mode decomposition–long short-term memory (VMD-LSTM), and convolutional neural network–long short-term memory (CNN-LSTM), which provide a comprehensive evaluation. Our findings demonstrate that the developed model outperforms other methods, offering promising results in solar power forecasting. This research contributes to the primary goal of enhancing EMS by providing accurate solar energy forecasts. [ABSTRACT FROM AUTHOR]

Amidst an energy crisis stemming from increased energy costs and the looming threat of war, there has been a burgeoning interest in energy conservation and management worldwide. Industrial complexes constitute a significant portion of total energy consumption. Hence, reducing energy consumption in these complexes is imperative for energy preservation. Typically, factories within similar industries aggregate in industrial complexes and share similar energy utilities. However, they often fail to capitalize on this shared infrastructure efficiently. To address this issue, a network system employing a virtual utility plant has been proposed. This system enables proactive measures to counteract energy surplus or deficit through AI-based predictions, thereby maximizing energy efficiency. Nevertheless, deploying conventional server systems within factories poses considerable challenges. Therefore, leveraging edge devices, characterized by low power consumption, high efficiency, and minimal space requirements, proves highly advantageous. Consequently, this study focuses on constructing and employing data collection and AI systems to utilize edge devices as standalone systems in each factory. To optimize the AI system for low-performance edge devices, we employed the integration-learning AI modeling technique. Evaluation results demonstrate that the proposed system exhibits high stability and reliability. [ABSTRACT FROM AUTHOR]