The permanent magnet synchronous motor (PMSM) is a highly efficient energy saving machine. Due to its simple structural characteristics, good heat radiation capability, and high efficiency, PMSMs are gradually replacing AC induction motors in many industrial applications. The PMSM has a nonlinear system and lies on parameters that differ over time with complex high-class dynamics. To achieve the excessive performance operation of a PMSM, it essentially needs a speed controller for providing accurate speed tracking, slight overshoot, and robust disturbance repulsion. Therefore, this article provides an overview of different robust control techniques for PMSMs and reviews the implementation of a speed controller. In view of the uncertainty factors, such as parameter perturbation and load disturbance, the H∞ robust control strategy is mainly reviewed based on the traditional control techniques, i.e., robust H∞ sliding mode controller (SMC), and H∞ robust current controller based on Hamilton–Jacobi Inequality (HJI) theory. Based on comparative analysis, this review simplifies the development trend of different control technologies used for a PMSM speed regulation system.

/pdf/critical-review-on-robust-speed-control-techniques-for-wa7dism0.pdf

Critical Review on Robust Speed Control Techniques for Permanent Magnet Synchronous Motor (PMSM) Speed Regulation

Using deep learning and meteorological parameters to forecast the photovoltaic generators intra-hour output power interval for smart grid control

Forecasting intra-hour solar photovoltaic energy by assembling wavelet based time-frequency analysis with deep learning neural networks

Ensemble of machine learning and spatiotemporal parameters to forecast very short-term solar irradiation to compute photovoltaic generators’ output power

Electrical load forecasting plays a crucial role in the proper scheduling and operation of power systems. To ensure the stability of the electrical network, it is necessary to balance energy generation and demand. Hence, different very short-term load forecast technologies are being designed to improve the efficiency of current control strategies. This paper proposes a new forecaster based on artificial intelligence, specifically on a recurrent neural network topology, trained with a Levenberg–Marquardt learning algorithm. Moreover, a sensitivity analysis was performed for determining the optimal input vector, structure and the optimal database length. In this case, the developed tool provides information about the energy demand for the next 15 min. The accuracy of the forecaster was validated by analysing the typical error metrics of sample days from the training and validation databases. The deviation between actual and predicted demand was lower than 0.5% in 97% of the days analysed during the validation phase. Moreover, while the root mean square error was 0.07 MW, the mean absolute error was 0.05 MW. The results suggest that the forecaster’s accuracy is considered sufficient for installation in smart grids or other power systems and for predicting future energy demand at the chosen sites.

https://www.mdpi.com/1996-1073/13/19/5210/pdf

Very Short-Term Load Forecaster Based on a Neural Network Technique for Smart Grid Control

Energy distribution companies have experienced an increase in catastrophic failures in power systems due to the theft of grounding cable. The objective of this study is to develop an innovative technology which is able to detect the absence of grounding cable in medium and high voltage systems. The wireless technology developed communicates periodically with the system’s central control unit to ensure reliable and safe operation of the installation. Because it is not economically profitable to modify power systems’ infrastructure, this novel sensor is non-intrusive as well as self-supplying. Based on the validation step’s results, we conclude that the sensor is ready to be tested in smart grid equipment to monitor the state of grounding cables.

Fernando Martín

Papers

Ensemble of machine learning and spatiotemporal parameters to forecast very short-term solar irradiation to compute photovoltaic generators’ output power

Very Short-Term Load Forecaster Based on a Neural Network Technique for Smart Grid Control

Non-intrusive, self-supplying and wireless sensor for monitoring grounding cable in smart grids

FOC-Droop control strategy for PMSM fed paralleled multi-inverter power systems oriented to aeronautical applications