A battery/supercapacitor hybrid energy storage system is developed to mitigate the battery degradation for electric vehicles. By coordinating the battery and supercapacitor, the proposed system avoids using the large bidirectional DC/DC. Through the improved topology and two added controlled switches, the battery current can be managed flexibly. Based on the battery and supercapacitor voltage, seven operation modes of battery and capacitor cooperation are designed. The control strategy is redesigned to match the modes, in which the key control parameters are calibrated based on three standard driving cycles. During driving, the proposed system calls the predefined parameter set by the cycle recognition technique. The objective of the cycle-related control is to maximize the harvest of the braking energy and minimize battery degradation in various driving styles. Taking the battery case solely as a benchmark and the infinite supercapacitors case as the largest battery degradation mitigation scenario, the battery degradation quantification of the proposed energy storage system shows more than 80% mitigation of the maximum theoretical battery degradation mitigation on urban dynamometer driving schedule (UDDS), highway fuel economy cycle (HWFET), and high-speed (US06) driving cycle, respectively. During the tested driving cycles, the simulation result indicates the battery degradation reduced by 30% more than the battery solely scenario, which proves the benefit of the proposed system.

Voltage control plays an important role in the operation of electricity distribution networks, especially with high penetration of distributed energy resources. These resources introduce significant and fast varying uncertainties. In this paper, we focus on reactive power compensation to control voltage in the presence of uncertainties. We adopt a chance constraint approach that accounts for arbitrary correlations between renewable resources at each of the buses. We show how the problem can be solved efficiently using historical samples analogously to the stochastic quasi-gradient methods. We also show that this optimization problem is convex for a wide variety of probabilistic distributions. Compared to conventional per-bus chance constraints, our formulation is more robust to uncertainty and more computationally tractable. We illustrate the results using standard IEEE distribution test feeders.

Formant estimation from vowel segments, is very useful for linguistic purposes. Traditionally, formants are estimated using classical signal processing methods and statistical models. The averaged continuous extraction of formant frequency along the vowel segments is taken as the formant of vowels. New approaches using neural networks to predict vowel formants on an annotated database, where the input is the acoustic features and output is the mean formant frequency value. Recently, the Bilinear Network (BL) and Temporal Attention-Augmented Bilinear Network (TABL) have proven to be very effective on financial time-series analysis task, compared to recurrent networks and convolution networks. Similar to our work, we explored how to extend the structure of BL and learn from TABL to produce better short-term modeling capability for vowel formant estimation. More specifically, we proposed to replace the attention mechanism with sigmoid gate and use a learnable parameter to dynamically integrate the first linear transformation output, thus learning better representation of BL. Experiments on the vowels test set of public VTR corpus showed that our approach significantly surpassed DNN, CNN, BL and achieved slightly better performance than the poweful TABL model in terms of mean absolute error and mean absolute percent error rate on F1, F2, F3 and overall.