Research Article
Performance Prediction of Solar-Powered Domestic Fridge in Hot-Humid Climates Using Machine Learning
Joseph Kwarteng Acheampong*
,
Theophilus Frimpong Adu,
Daniel Marfo
Issue:
Volume 11, Issue 2, December 2026
Pages:
29-40
Received:
27 May 2026
Accepted:
29 June 2026
Published:
9 September 2026
Abstract: The intermittent nature of solar energy and dynamic environmental conditions pose significant challenges to the performance and reliability of solar-powered refrigeration systems in hot-humid climates. While traditional thermodynamic models offer limited predictive capability under real-world variability, machine learning (ML) presents a promising alternative for addressing these complexities. This study develops and evaluates ML-based models to predict the performance of a 92-liter DC solar-powered domestic refrigerator, focusing on power input (Pin), coefficient of performance (COP), and refrigerating capacity (CR). Experimental data, including solar irradiance, ambient temperature, and system operational parameters, were collected at 10-minute intervals under hot-humid conditions. Three ML algorithms: Artificial Neural Network (ANN), Random Forest Regression (RFR), and Support Vector Regression (SVR) were trained and validated using a dataset of 500 samples. Key findings reveal that ambient temperature strongly influences system performance, exhibiting a negative correlation with COP (-0.65) and CR (-0.56), while solar irradiance shows a non-linear relationship with these metrics. Among the models, SVR demonstrated exceptional accuracy for power input prediction (R2 = 0.99, RMSE = 0.41), whereas ANN achieved the highest performance for COP prediction (R2 = 0.85, RMSE = 1.45). RFR emerged as the most robust for refrigerating capacity estimation (R2 = 0.71), though all models faced challenges due to the parameter's transient dependence. The results highlight the potential of hybrid ML approaches to optimize solar refrigeration systems in climate-specific scenarios. This study contributes a scalable, data-driven framework for performance prediction, offering practical insights for system design, adaptive control strategies, and policy recommendations to enhance the adoption of solar refrigeration in off-grid and energy-insecure regions. The limitations of dataset size and weather variability are acknowledged, suggesting avenues for future research, including long-term real-world validation and ensemble modeling.
Abstract: The intermittent nature of solar energy and dynamic environmental conditions pose significant challenges to the performance and reliability of solar-powered refrigeration systems in hot-humid climates. While traditional thermodynamic models offer limited predictive capability under real-world variability, machine learning (ML) presents a promising ...
Show More
Research Article
Modelling and Economic Evaluation of a Solar-Assisted Crude Oil Heating System for Flow Assurance in Pipeline Transportation
Issue:
Volume 11, Issue 2, December 2026
Pages:
41-61
Received:
4 October 2026
Accepted:
16 October 2026
Published:
29 October 2026
Abstract: Crude oil transportation in the Niger Delta requires effective thermal management to maintain flow assurance. Heat loss, wax precipitation, and increasing viscosity can restrict crude-oil flow and increase operational risks. This study developed an analytical techno-economic framework for solar-assisted heating of a representative 20 km crude-oil pipeline using Nigerian crude-oil properties and Niger Delta solar-resource data. Evacuated-tube collectors and a sensible-heat storage tank were sized, and a 25-year lifecycle cost analysis compared the hybrid solar-plus-gas system with gas-fired and electric-heating references. The model estimated a heating demand of 1.78 MW (15,622 MWh annually); polyurethane-foam insulation contributed 82.7% of total pipeline thermal resistance. An 8,549 m2 collector field with 3,490 modules and a 546 m³ storage tank achieved an annual solar fraction of 38.7%. The solar system required USD 3.22 million in capital investment. After including supplementary gas for the 61.3% of annual demand not met by solar, and costing the conventional references against the full annual demand, the estimated annual OPEX was USD 139,840 for solar-assisted heating, USD 351,589 for gas-fired heating, and USD 1.698 million for electric heat tracing. Over 25 years at a 10% discount rate, the corrected lifecycle costs were USD 4.860 million, USD 5.594 million, and USD 17.316 million, respectively. The solar-assisted system had an estimated positive NPV of USD 0.734 million relative to gas-fired heating, an incremental-capital simple payback of 4.8 years, and a discounted payback of approximately 6.9 years. Its LCOH was USD 0.0343/kWh, about 13.1% below the gas-fired reference and 72.0% below electric heat tracing. Monte Carlo analysis using a simplified cash-flow formulation yielded a 100% probability of positive NPV for the investigated parameter distributions. The findings indicate potential for solar-assisted pipeline heating, but supplementary heating remains essential during low-solar periods. Pilot-scale validation and further assessment of hybrid backup strategies are recommended.
Abstract: Crude oil transportation in the Niger Delta requires effective thermal management to maintain flow assurance. Heat loss, wax precipitation, and increasing viscosity can restrict crude-oil flow and increase operational risks. This study developed an analytical techno-economic framework for solar-assisted heating of a representative 20 km crude-oil p...
Show More
