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) 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.

The accurate forecasting of solar radiation plays an important role for predictive control applications for energy systems with a high share of photovoltaic (PV) energy. Especially off-grid microgrid applications using predictive control applications can benefit from forecasts with a high temporal resolution to address sudden fluctuations of PV-power. However, cloud formation processes and movements are subject to ongoing research. For now-casting applications, all-sky-imagers (ASI) are used to offer an appropriate forecasting for aforementioned application. Recent research aims to achieve these forecasts via deep learning approaches, either as an image segmentation task to generate a DNI forecast through a cloud vectoring approach to translate the DNI to a GHI with ground-based measurement (Fabel et al., 2022; Nouri et al., 2021), or as an end-to-end regression task to generate a GHI forecast directly from the images (Paletta et al., 2021; Yang et al., 2021). While end-to-end regression might be the more attractive approach for off-grid scenarios, literature reports increased performance compared to smart-persistence but do not show satisfactory forecasting patterns (Paletta et al., 2021). This work takes a step back and investigates the possibility to translate ASI-images to current GHI to deploy the neural network as a feature extractor. An ImageNet pre-trained deep learning model is used to achieve such translation on an openly available dataset by the University of California San Diego (Pedro et al., 2019). The images and measurements were collected in Folsom, California. Results show that the neural network can successfully translate ASI-images to GHI for a variety of cloud situations without the need of any external variables. Extending the neural network to a forecasting task also shows promising forecasting patterns, which shows that the neural network extracts both temporal and momentarily features within the images to generate GHI forecasts.ReferencesFabel, Y., Nouri, B., Wilbert, S., Blum, N., Triebel, R., Hasenbalg, M., Kuhn, P., Zarzalejo, L. F., and Pitz-Paal, R.: Applying self-supervised learning for semantic cloud segmentation of all-sky images, Atmospheric Measurement Techniques, 15, 797–809, https://doi.org/10.5194/amt-2021-1, 2022.Nouri, B., Blum, N., Wilbert, S., and Zarzalejo, L. F.: A Hybrid Solar Irradiance Nowcasting Approach: Combining All Sky Imager Systems and Persistence Irradiance Models for Increased Accuracy, Solar RRL, 2100442, https://doi.org/10.1002/solr.202100442, 2021.Paletta, Q., Arbod, G., and Lasenby, J.: Benchmarking of deep learning irradiance forecasting models from sky images – An in-depth analysis, Solar Energy, 224, 855–867, https://doi.org/10.1016/j.solener.2021.05.056, 2021.Pedro, H. T. C., Larson, D. P., and Coimbra, C. F. M.: A comprehensive dataset for the accelerated development and benchmarking of solar forecasting methods, Journal of Renewable and Sustainable Energy, 11, 36102, https://doi.org/10.1063/1.5094494, 2019.Yang, H., Wang, L., Huang, C., and Luo, X.: 3D-CNN-Based Sky Image Feature Extraction for Short-Term Global Horizontal Irradiance Forecasting, Water, 13, 1773, https://doi.org/10.3390/w13131773, 2021.

This work proposes a novel approach for probabilistic end-to-end all-sky imager-based nowcasting with horizons of up to 30 min using an ImageNet pre-trained deep neural network. The method involves a two-stage approach. First, a backbone model is trained to estimate the irradiance from all-sky imager (ASI) images. The model is then extended and retrained on image and parameter sequences for forecasting. An open access data set is used for training and evaluation. We investigated the impact of simultaneously considering global horizontal (GHI), direct normal (DNI), and diffuse horizontal irradiance (DHI) on training time and forecast performance as well as the effect of adding parameters describing the irradiance variability proposed in the literature. The backbone model estimates current GHI with an RMSE and MAE of 58.06 and 29.33 W m⁻², respectively. When extended for forecasting, the model achieves an overall positive skill score reaching 18.6 % compared to a smart persistence forecast. Minor modifications to the deterministic backbone and forecasting models enables the architecture to output an asymmetrical probability distribution and reduces training time while leading to similar errors for the backbone models. Investigating the impact of variability parameters shows that they reduce training time but have no significant impact on the GHI forecasting performance for both deterministic and probabilistic forecasting while simultaneously forecasting GHI, DNI, and DHI reduces the forecast performance.

In Ghana, unreliable public grid infrastructure greatly impacts rural healthcare, where diesel generators are commonly used despite their high financial and environmental costs. Photovoltaic (PV)-hybrid systems offer a sustainable alternative, but require robust, predictive control strategies to ensure reliability. This study proposes a sector-specific Model Predictive Control (MPC) approach, integrating advanced load and meteorological forecasting for optimal energy dispatch. The methodology includes a long-short-term memory (LSTM)-based load forecasting model with probabilistic Monte Carlo dropout, a customized Numerical Weather Prediction (NWP) model based on the Weather Research and Forecasting (WRF) framework, and deep learning-based All-Sky Imager (ASI) nowcasting to improve short-term solar predictions. By combining these forecasting methods into a seamless prediction framework, the proposed MPC optimizes system performance while reducing reliance on fossil fuels. This study benchmarks the MPC against a traditional rule-based dispatch system, using data collected from a rural health facility in Kologo, Ghana. Results demonstrate that predictive control greatly reduces both economic and ecological costs. Compared to rule-based dispatch, diesel generator operation and fuel consumption are reduced by up to 61.62% and 47.17%, leading to economical and ecological cost savings of up to 20.7% and 31.78%. Additionally, system reliability improves, with battery depletion events during blackouts decreasing by up to 99.42%, while wear and tear on the diesel generator and battery are reduced by up to 54.93% and 37.34%, respectively. Furthermore, hyperparameter tuning enhances MPC performance, introducing further optimization potential. These findings highlight the effectiveness of predictive control in improving energy resilience for critical healthcare applications in rural settings.

Proposal of a poster for the EMS2022Intention:Within the research project EnerSHelF (Energy-Self-Sufficiency for Health Facilities in Ghana), i. a. energy-meteorological and load-related measurement data are collected, for which an overview of the availability is to be presented on a poster.Context:In Ghana, the total electricity consumed has almost doubled between 2008 and 2018 according to the Energy Commission of Ghana. This goes along with an unstable power grid, resulting in power outages whenever electricity consumption peaks. The blackouts called "dumsor" in Ghana, pose a severe burden to the healthcare sector. Innovative solutions are needed to reduce greenhouse gas emissions and improve energy and health access.The aim of the project is therefore to develop PV-based energy solutions for healthcare facilities and to improve the reliability and integrability of such systems in the local electricity grid.The work is based on a measurement campaign that has been running since 2020 at three hospitals spread across the country. The variables measured include:Global tilted irradiance (GTI)Soiling ratio and temperature of the PV panelsAll-sky camera recordingsLoad measurement aggregate (grid node)Load measurement sub-distribution (departments and devices)In addition, weather stations are operated at the sites to improve weather forecasts.These datasets can be used to follow different approaches to managing the harsh conditions caused by dry and rainy seasons, and to design and control PV hybrid systems appropriately.According to the World Bank (2017) only 3% of the population in West Africa and the Sahel can currently access PV power through off-grid systems. As an important catalyst for sustainable development, access to a reliable source of clean energy is vital for inclusive economic development, improved human health, wellbeing and security. As such, EnerSHelF can contribute to Sustainable Development Goals (SDG) of health (SDG 3), energy (SDG 7) and partnerships (SDG 17).