500 Naturwissenschaften und Mathematik
Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Keywords
- Elektrizitätsversorgung (1)
- Ghana (1)
- Ghanaian health sector (1)
- LSTM (1)
- Load forecasting (1)
- Medizinische Einrichtung (1)
- Neural network (1)
- SARIMA (1)
- West Africa (1)
- Westafrika (1)
Faculty
- Fakultät 07 / Institut für Elektrische Energietechnik (2) (remove)
To realize a reliable and cost-effective application of high-temperature superconductive (HTS) equipment at high-voltage (HV) levels, the influence of thermally induced gas bubbles on the dielectric strength of different solid insulating materials in liquid nitrogen (LN2) was investigated. A heatable copper tape electrode arrangement was developed simulating HTS tapes with insulation in between. AC breakdown measurements were performed without and with forced boiling on insulating papers, polypropylene laminated paper (PPLP) and polyimide (PI) films. Under nucleate boiling the influence of bubbles on the dielectric strength of all materials was not significant. However under film boiling the dielectric strength of the insulating papers decreased to a level comparable to their dielectric strength in air, demonstrating the insufficient impregnation of porous materials under film boiling. For PI there was no degradation at all. PPLP retained about 70% of its basic dielectric strength in LN2.
Ghana suffers from frequent power outages, which can be compensated by off-grid energysolutions. Photovoltaic-hybrid systems become more and more important for rural electrificationdue to their potential to offer a clean and cost-effective energy supply. However, uncertainties relatedto the prediction of electrical loads and solar irradiance result in inefficient system control and canlead to an unstable electricity supply, which is vital for the high reliability required for applicationswithin the health sector. Model predictive control (MPC) algorithms present a viable option to tacklethose uncertainties compared to rule-based methods, but strongly rely on the quality of the forecasts.This study tests and evaluates (a) a seasonal autoregressive integrated moving average (SARIMA)algorithm, (b) an incremental linear regression (ILR) algorithm, (c) a long short-term memory (LSTM)model, and (d) a customized statistical approach for electrical load forecasting on real load data of aGhanaian health facility, considering initially limited knowledge of load and pattern changes throughthe implementation of incremental learning. The correlation of the electrical load with exogenousvariables was determined to map out possible enhancements within the algorithms. Results showthat all algorithms show high accuracies with a median normalized root mean square error (nRMSE)<0.1 and differing robustness towards load-shifting events, gradients, and noise. While the SARIMAalgorithm and the linear regression model show extreme error outliers of nRMSE >1, methods viathe LSTM model and the customized statistical approaches perform better with a median nRMSE of0.061 and stable error distribution with a maximum nRMSE of <0.255. The conclusion of this study isa favoring towards the LSTM model and the statistical approach, with regard to MPC applicationswithin photovoltaic-hybrid system solutions in the Ghanaian health sector.