Search

Electromobility contributes to decreasing environmental pollution and fossil fuel dependence, as well as increasing the integration of renewable energy resources. The increasing interest in using electric vehicles (EVs), enhanced by machine learning (ML) algorithms for intelligent automation, has reduced the reliance on. This shift has created an interdependence between power, automatically, and transportation networks, adding complexity to their management and scheduling. Moreover, due to complex charging infrastructures, such as variations in power supply, efficiency, driver behaviors, charging demand, and electricity price, advanced techniques should be applied to predict a wide range of variables in EV performance. As the adoption of EVs continues to accelerate, the integration of ML and especially deep learning (DL) algorithms will play a pivotal role in shaping the future of sustainable transportation. This paper provides a mini review of the ML impacts on mobility electrification. The applications of ML are evaluated in various aspects of e-mobility, including battery management, range prediction, charging infrastructure optimization, autonomous driving, energy management, predictive maintenance, traffic management, vehicle-to-grid (V2G), and fleet management. The main advantages and challenges of models in the years 2013–2024 have been represented for all mentioned applications. Also, all new trends for future work and the strengths and weaknesses of ML models in various aspects of mobility transportation are covered. By discussing and reviewing research papers in this field, it is revealed that leveraging ML models can accelerate the transition to electric mobility, leading to cleaner, safer, and more sustainable transportation systems. This paper states that the dependence on big data for training, the high uncertainty of parameters affecting the performance of electric vehicles, and cybersecurity are the main challenges of ML in the e-mobility sector. [ABSTRACT FROM AUTHOR]

Distributed generation (DG) sources play a special role in the operation of active energy networks. The microgrid (MG) is known as a suitable substrate for the development and installation of DGs. However, the future of energy distribution networks will consist of more interconnected and complex MGs, called multi-microgrid (MMG) networks. Therefore, energy management in such an energy system is a major challenge for distribution network operators. This paper presents a new energy management method for the MMG network in the presence of battery storage, renewable sources, and demand response (DR) programs. To show the performance of each connected MG's inefficient utilization of its available generation capacity, an index called unused power capacity (UPC) is defined, which indicates the availability and individual performance of each MG. The uncertainties associated with load and the power output of wind and solar sources are handled by employing the chance-constrained programming (CCP) optimization framework in the MMG energy management model. The proposed CCP ensures the safe operation of the system at the desired confidence level by involving various uncertainties in the problem while optimizing operating costs under Mixed-Integer Linear Programming (MILP). The proposed energy management model is assessed on a sample network concerning DC power flow limitations. The procured power of each MG and power exchanges at the distribution network level are investigated and discussed. [ABSTRACT FROM AUTHOR]

One of the main challenges of Lombok Island, Indonesia, is the significant disparity between peak load and base load, reaching 100 MW during peak hours, which is substantial considering the island's specific energy dynamics. Battery energy storage systems provide power during peak times, alleviating grid stress and reducing the necessity for grid upgrades. By 2030, one of the proposed capacity development scenarios on the island involves deploying large-scale lithium-ion batteries to better manage the integration of solar generation. This paper focuses on the life cycle assessment and life cycle costing of a lithium iron phosphate large-scale battery energy storage system in Lombok to evaluate the environmental and economic impacts of this battery development scenario. This analysis considers a cradle-to-grave model and defines 10 environmental and 4 economic midpoint indicators to assess the impact of battery energy storage system integration with Lombok's grid across manufacturing, operation, and recycling processes. From a life cycle assessment perspective, the operation subsystem contributes most significantly to global warming, while battery manufacturing is responsible for acidification, photochemical ozone formation, human toxicity, and impacts on marine and terrestrial ecosystems. Recycling processes notably affect freshwater due to their release of 4.69 × 10−4 kg of lithium. The life cycle costing results indicate that over 85% of total costs are associated with annualized capital costs at a 5% discount rate. The levelized cost of lithium iron phosphate batteries for Lombok is approximately 0.0066, demonstrating that lithium-ion batteries are an economically viable option for Lombok's 2030 capacity development scenario. A sensitivity analysis of input data and electricity price fluctuations confirms the reliability of our results within a 20% margin of error. Moreover, increasing electricity prices for battery energy storage systems in Lombok can reduce the payback period to 3.5 years. [ABSTRACT FROM AUTHOR]

The main objective of this paper is to design a robust multi-objective H 2 / H ∞ delayed feedback controller for load frequency control of a multi-area interconnected power system by taking into account all theoretical and practical constraints. To achieve more precise modelling and analysis, the limitation of valve position, governor, and transmission delay are considered to guarantee of LFC system's stability in practical applications. The nonlinear delayed system is approximated by the Takagi–Sugeno fuzzy model. Then, a parallel distributed compensation scheme is utilized for designing the control system of the overall system. The proposed multi-objective and robust H 2 / H ∞ controller simultaneously minimizes the H 2 and H ∞ control performance indexes. Finally, simulation results verify the robustness and effectiveness of the proposed scheme in dealing with the impact of load disturbances, model uncertainties, transmission time delays, and nonlinearities in the model. [ABSTRACT FROM AUTHOR]