Microgrid TestBed for Temporal Forecasting Patterns of Failure for Smart Cities

Abstract

The malfunction variables of power stations are related to the areas of weather, physical structure, control and load behaviour. To predict temporal power failure is difficult due to their unpredictable characteristics. As high accuracy is normally required, the estimation of failures of short-term temporal prediction is highly difficult. This study presents a method for converting stochastic behaviour into a stable pattern, which can subsequently be used in a short-term estimator. For this conversion, K-means clustering is employed, followed by Long-Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms are used to perform the Short-term estimation. The environment, the operation and the generated signal factors are all simulated using mathematical models. Weather parameters and load samples have been collected as part of a data set. Monte-Carlo simulation using MATLAB programming has been used to conduct experimental estimation of failures. The estimated failures of the experiment are then compared with the actual system temporal failures and found to be in good match. Therefore, for any future power grid, there is a testbed ready to estimate the future failures.

Citation

Qashou, A., Yousef, S., Okoro, A. and Hazzaa, F. (2023), "Microgrid TestBed for Temporal Forecasting Patterns of Failure for Smart Cities", Dadwal, S.S., Jahankhani, H., Bowen, G. and Nawaz, I.Y. (Ed.) Technology and Talent Strategies for Sustainable Smart Cities, Emerald Publishing Limited, Leeds, pp. 189-227. https://doi.org/10.1108/978-1-83753-022-920231010