Browsing by Author "Nyarko, Frank Kwabena Afriyie"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Machine learning forecasting of solar PV production using single and hybrid models over different time horizons
    (Heliyon, 2024-04-15) Asiedu, Shadrack T.; Nyarko, Frank Kwabena Afriyie; Boahen, Samuel; Effah, Francis Boafo; Asaaga, Benjamin Atribawuni
    This study uses operational data from a 180 kWp grid-connected solar PV system to train and compare the performance of single and hybrid machine learning models in predicting solar PV production a day-ahead, a week-ahead, two weeks ahead and one month-ahead. The study also analyses the trend in solar PV production and the effect of temperature on solar PV production. The performance of the models is evaluated using R 2 score, mean absolute error and root mean square error. The findings revealed the best-performing model for the day ahead forecast to be Artificial Neural Network. Random Forest gave the best performance for the two-week and a month-ahead forecast, while a hybrid model composed of XGBoost and Random Forest gave the best performance for the week-ahead prediction. The study also observed a downward trend in solar PV production, with an average monthly decline of 244.37 kWh. Further, it was observed that an increase in the module temperature and ambient temperature beyond 47 ◦ C and 25 ◦ C resulted in a decline in solar PV production. The study shows that machine learning models perform differently under different time horizons. Therefore, selecting suitable machine learning models for solar PV forecasts for varying time horizons is extremely necessary.
  • No Thumbnail Available
    Item
    Modelling interconnections in c-SI Solar Photovoltaic modules for improved reliability in Kumasi in Sub - Saharan Africa
    (2021-07-12) Nyarko, Frank Kwabena Afriyie;
    The use of climate-specific temperature-cycling profile is critical in precisely quantifying the degradation rate and accurately determining the service fatigue life of the crystalline silicon photovoltaic (c-Si PV) module operating in various climates. A reliable in-situ outdoor weathering database is pivotal in generating the required climate-specific temperature cycle profile. This study concerns the prediction of the reliability of both SnPb and Pb-free solder interconnects in a c-Si PV module from a sub-Saharan Africa outdoor weathering conditions. The test site for this study is located at the College of Engineering, KNUST Ghana (latitude 6º 40" N and longitude 1º 37" W at an elevation of 250 m above sea level). The research utilizes a three-year (2012 to 2014) high-resolution data to generate temperature cycles profiles that are representative of the test site climate. Subsequently, the generated temperature cycles were used in numerical investigations to examine the impact of these temperature cycle loads on the creep damage in the solder used as cell interconnecting material. The study involved an initial determination of the accurate constitutive model of EVA (encapsulant) for thermo-mechanical analysis of the c-Si solar cell. Furthermore, the life (number of cycles to failure) of the interconnecting solders were predicted using Finite Element Analysis (FEA) software (Ansys 18.2). The Garafalo-Arrhenius creep model was used to study the creep behaviour of the interconnecting solders since creep is the main damaging mechanism in the solder. Finally, the effects of temperature dwells and ramps were investigated from the change in Accumulated Creep Energy Density (ACED) profiles at the respective load steps for temperature ramps and dwells. Analysis of the data on temperature variation and thermally induced stresses showed that the test site has a temperature profile with a ramp rate of 8.996, a hot dwell time of 228 minutes, and a cold dwell time of 369 minutes. Maximum and minimum module temperatures of 58.9 and 23.7, respectively; in a cycle time of 86400 s (24 hrs) were recorded. Results from the numerical study showed that the linear viscoelastic material model (LVMM) of EVA generated the most consistent response to the thermo-mechanical analysis. Additionally, life cycle prediction results of soldered interconnections from ACED revealed that SnPb solder interconnections are likely to last longer (23.4 years) under the sub-Saharan African test region compared with Pb-free solder interconnects (13.69 years). Finally, a study on the effects of temperature dwells and ramps on creep damage of interconnections showed that the temperature ramps (heating and cooling load steps) accounted for approximately 80% of the creep damage in the soldered interconnections.