Journal: The Journal of Engineering

Abbreviation

Publisher

Institution of Engineering and Technology

Journal Volumes

ISSN

2051-3305

Description

Filters

2018 - 20203
Reset filters

Search Results

Publications 1 - 3 of 3
  • Travelling wave protection with disturbance classification for distribution grids with distributed generation
    Item type: Conference Paper
    Davydova, Nadezhda; Hug, Gabriela (2018)
    The Journal of Engineering
    The high penetration of distributed generation in distribution grids and the development of microgrids may cause the malfunctioning of the conventional distribution level protection systems. Despite multiple works dedicated to addressing this problem, the development of reliable, high-speed, and cost-efficient protection systems for active grids remains a topical issue. This study proposes a protection system for medium voltage lines that relies entirely on the analytical description of travelling wave transients. This protection uses only local high-frequency current measurements and power-frequency voltage measurements, which potentially makes it a low-cost yet reliable solution. The protection system operates securely by not tripping healthy lines in case of disturbances that do not lead to any faults. The proposed protection is tested on the IEEE 34-bus distribution system with distributed generation.
  • Triple Buck Converter – an Efficient Low-Distortion Switch-Mode Power Amplifier Topology
    Item type: Journal Article
    Mauerer, Mario; Kolar, Johann W. (2020)
    The Journal of Engineering
  • Convolutional sequence to sequence non-intrusive load monitoring
    Item type: Journal Article
    Chen, Kunjin; Wang, Qin; He, Ziyu; et al. (2018)
    The Journal of Engineering
    A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this study. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partially overlapped output sequences of the network are averaged to produce the final output of the model. The authors apply the proposed model to the reference energy disaggregation data set dataset and compare it with the convolutional sequence to point model in the literature. Results show that the proposed model is able to give satisfactory disaggregation performance for appliances with varied characteristics.
Publications 1 - 3 of 3