Day-Ahead Electric Load Forecast for a Ghanaian Health Facility Using Different Algorithms

Abstract

Ghana suffers from frequent power outages, which can be compensated by off-grid energy solutions. Photovoltaic-hybrid systems become more and more important for rural electrification due to their potential to offer a clean and cost-effective energy supply. However, uncertainties related to the prediction of electrical loads and solar irradiance result in inefficient system control and can lead to an unstable electricity supply, which is vital for the high reliability required for applications within the health sector. Model predictive control (MPC) algorithms present a viable option to tackle those 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 a Ghanaian health facility, considering initially limited knowledge of load and pattern changes through the implementation of incremental learning. The correlation of the electrical load with exogenous variables was determined to map out possible enhancements within the algorithms. Results show that 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 SARIMA algorithm and the linear regression model show extreme error outliers of nRMSE >1, methods via the LSTM model and the customized statistical approaches perform better with a median nRMSE of 0.061 and stable error distribution with a maximum nRMSE of <0.255. The conclusion of this study is a favoring towards the LSTM model and the statistical approach, with regard to MPC applications within photovoltaic-hybrid system solutions in the Ghanaian health sector.

Life Cycle Assessment of Sodium-Nickel-Chloride Batteries

“…In Ghana, 14.1% of the population had no access to electricity in 2020 [34] and access to electricity did not guarantee a constant supply [35]. The electricity generation is mostly based on fossil fuels, as 62% of the electricity from the national grid is generated by oil and natural gas [36].…”

“…The electricity generation is mostly based on fossil fuels, as 62% of the electricity from the national grid is generated by oil and natural gas [36]. Diesel generators are as well widely used [35]. Off-grid solutions, such as mini grids which are supplied by renewable energy, can satisfy the increasing demand for electricity and ensure a low-emission and reliable power supply [37] [38].…”

Seemingly unrelated time series model for forecasting the peak and short-term electricity demand: Evidence from the Kalman filtered Monte Carlo method

“…Sub-Saharan Africa's electrical demand is growing due to fast population growth, resulting in increasing demand. Despite a 2.45% drop in the number of people without access to electricity between 2013 and 2018, the electrification rate has remained low at 45% ([ 13 , 15 ] According to Chaaraoui et al [ 15 ], unreliable energy supply affects about 80% of Sub-Saharan African enterprises, owing to outdated power grid technology and inadequate network management. The Ghanaian energy industry suffers from substantial transmission and distribution losses of about 20%, while electricity prices are growing due to inflation and bad contracting with foreign power plant providers, resulting in a transition from low electricity availability to low affordability [ 16 ].…”

The Role of Local Citizen Energy Communities in the Road to Carbon-Neutral Power Systems: Outcomes from a Case Study in Portugal

“…For producers the nominal quantity of energy considers the produced energy at nominal power while for consumers it considers the peak energy consumption. Table 1 presents the typical values for the NRMSE of each player considering average values from the literature [5,14,[37][38][39][40][41][42][43][44][45][46][47][48].…”