Search

This paper shows the potential of artificial intelligence (AI) in Li-ion battery charging methods by introducing a new charging algorithm based on artificial neural networks (ANNs). The proposed charging algorithm is able to find an optimized charging current profile, through ANNs, considering the real-time conditions of the Li-ion batteries. To test and validate the proposed approach, a low-cost battery management system (BMS) was developed, supporting up to 168 cells in series and n cells in parallel. When compared with the multistage charging algorithm, the proposed charging algorithm revealed a shorter charging time (7.85%) and a smaller temperature increase (32.95%). Thus, the results show that the proposed algorithm based on AI is able to effectively charge and balance batteries and can be regarded as a subject of interest for future research. [ABSTRACT FROM AUTHOR]

This paper provides virtual inertia and mechanical power-based double synchronous controller (DSC) for power converters based on the d- and q-components of the converter current to assure the stable operation of the grid with the penetration of large-scale renewable energy resources (RERs). The DSC is projected based on emulating both the inertia and mechanical power variables of the synchronous generators (SGs), and its performance is compared with a non-synchronous controller (NSC) that is without these emulations. The main contributions of the DSC are providing a large margin of stability for the power grid with a wide area of low and high values of virtual inertia, also improving significantly power grid stability (PGS) with changing properly the embedded virtual variables of inertia, mechanical power, and also mechanical power error. Also, decoupling features of the proposed DSC in which both d and q components are completely involved with the characteristics of SGs as well as the relationship between the interfaced converter and dynamic models of SGs are other important contributions of the DSC over the existing control methods. Embedding some coefficients for the proposed DSC to show its robustness against the unknown intrinsic property of parameters is another contribution in this paper. Moreover, several transfer functions are achieved and analyzed that confirm a more stable performance of the emulated controller in comparison with the NSC for power-sharing characteristics. Simulation results confirm the superiority of the proposed DSC in comparison with other existing control techniques, e.g., the NSC techniques. [ABSTRACT FROM AUTHOR]

This paper presents a virtual inertia and mechanical power-based control strategy to provide a stable operation of the power grid under high penetration of renewable energy sources (RESs). The proposed control technique is based on a new active and reactive power-based dynamic model with the permanent magnet synchronous generator (PMSG) swing equation, in which all PMSG features i.e., inertia and mechanical power are embedded within the controller as the main contribution of this paper. To present an accurate analysis of the virtual PMSG-based parameters, the desired zero dynamics of the grid angular frequency are considered to evaluate the effects of virtual mechanical power (VMP) on the active and reactive power sharing, as well as the investigation of virtual inertia variations for the grid angular frequency responses. Moreover, by considering various active power errors and virtual inertia, the impacts of active power error on reactive power in the proposed control technique, are precisely assessed. Simulation results are employed in Matlab/Simulink software to verify the stabilizing abilities of the proposed control technique. [ABSTRACT FROM AUTHOR]

Short-Term Load Forecasting is critical for reliable power system operation, and the search for enhanced methodologies has been a constant field of investigation, particularly in an increasingly competitive environment where the market operator and its participants need to better inform their decisions. Hence, it is important to continue advancing in terms of forecasting accuracy and consistency. This paper presents a new deep learning-based ensemble methodology for 24 h ahead load forecasting, where an automatic framework is proposed to select the best Box-Jenkins models (ARIMA Forecasters), from a wide-range of combinations. The method is distinct in its parameters but more importantly in considering different batches of historical (training) data, thus benefiting from prediction models focused on recent and longer load trends. Afterwards, these accurate predictions, mainly the linear components of the load time-series, are fed to the ensemble Deep Forward Neural Network. This flexible type of network architecture not only functions as a combiner but also receives additional historical and auxiliary data to further its generalization capabilities. Numerical testing using New England market data validated the proposed ensemble approach with diverse base forecasters, achieving promising results in comparison with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]