Browsing by Author "Dhake, H."

Now showing 1 - 4 of 4

Algorithms for Hyperparameter Tuning of LSTMs for Time Series Forecasting
(MDPI, 2023) Dhake, H.; Kashyap, Y.; Kosmopoulos, P.
The rapid growth in the use of Solar Energy for sustaining energy demand around the world requires accurate forecasts of Solar Irradiance to estimate the contribution of solar power to the power grid. Accurate forecasts for higher time horizons help to balance the power grid effectively and efficiently. Traditional forecasting techniques rely on physical weather parameters and complex mathematical models. However, these techniques are time-consuming and produce accurate results only for short forecast horizons. Deep Learning Techniques like Long Short Term Memory (LSTM) networks are employed to learn and predict complex varying time series data. However, LSTM networks are susceptible to poor performance due to improper configuration of hyperparameters. This work introduces two new algorithms for hyperparameter tuning of LSTM networks and a Fast Fourier Transform (FFT) based data decomposition technique. This work also proposes an optimised workflow for training LSTM networks based on the above techniques. The results show a significant fitness increase from 81.20% to 95.23% and a 53.42% reduction in RMSE for 90 min ahead forecast after using the optimised training workflow. The results were compared to several other techniques for forecasting solar energy for multiple forecast horizons. © 2023 by the authors.
Climatological Trends and Effects of Aerosols and Clouds on Large Solar Parks: Application Examples in Benban (Egypt) and Al Dhafrah (UAE)
(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Dhake, H.; Kosmopoulos, P.; Mantakas, A.; Kashyap, Y.; El-Askary, H.; Elbadawy, O.
Solar energy production is vastly affected by climatological factors. This study examines the impact of two primary climatological factors, aerosols and clouds, on solar energy production at two of the world’s largest solar parks, Benban and Al Dhafrah Solar Parks, by using Earth observation data. Cloud microphysics were obtained from EUMETSAT, and aerosol data were obtained from the CAMS and assimilated with MODIS data for higher accuracy. The impact of both factors was analysed by computing their trends over the past 20 years. These climatological trends indicated the variations in the change in each of the factors and their resulting impact over the years. The trends were quantified into the actualised drop in energy production (Wh/m2/year) in order to obtain the impact of each factor. Aerosols displayed a falling trend of ?17.78 Wh/m2/year for Benban and ?44.88 Wh/m2/year for Al Dhafrah. Similarly, clouds also portrayed a largely falling trend for both stations, ?36.29 Wh/m2/year (Benban) and ?70.27 Wh/m2/year (Al Dhafrah). The aerosol and cloud trends were also observed on a monthly basis to study their seasonal variation. The trends were further translated into net increases/decreases in the energy produced and the resulting emissions released. The analysis was extended to quantify the economic impact of the trends. Owing to the falling aerosol and cloud trends, the annual production was foreseen to increase by nearly 1 GWh/year (Benban) and 1.65 GWh/year (Al Dhafrah). These increases in annual production estimated reductions in emission released of 705.2 tonne/year (Benban) and 1153.7 tonne/year (Al Dhafrah). Following these estimations, the projected revenue was foreseen to increase by 62,000 USD/year (Benban) and 100,000 USD/year (Al Dhafrah). Considering the geographical location of both stations, aerosols evidently imparted a larger impact compared with clouds. Severe dust storm events were also analysed at both stations to examine the worst-case scenario of aerosol impact. The results show that the realized losses during these events amounted to 2.86 GWh for Benban and 5.91 GWh for Al Dhafrah. Thus, this study showcases the benefits of Earth observation technology and offers key insights into climatological trends for solar energy planning purposes. © 2024 by the authors.
Multi-Layer Cloud Motion Vector Forecasting for Solar Energy Applications
(Elsevier Ltd, 2024) Kosmopoulos, P.; Dhake, H.; Melita, N.; Tagarakis, K.; Georgakis, A.; Stefas, A.; Vaggelis, O.; Korre, V.; Kashyap, Y.
Real-time forecasting of solar radiation posses several benefits and has huge potential for industrial applications. However, the intermittent nature of solar radiation makes it difficult to forecast accurately. Cloud cover is one of the major influencing factors of solar radiation. Thus, forecasting cloud motion effectively can help to improve the accuracy of short-term solar radiation forecasts. In this study, a novel Multi-Layer Cloud Motion Vector (referred as 3D-CMV) forecasting technique was introduced, which combined with the fast radiative transfer model (FRTM) produces forecasts up to 3 h ahead at 15 min intervals over 5km × 5km grids across Europe and North Africa. The cloud microphysics obtained from the Support to Nowcasting and Very Short Range Forecasting (SAFNWC) of the European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT) was used as input to the forecasting system. The results obtained improvements in forecasts as compared to the conventional cloud motion vector techniques, across all seasons and sky conditions. Comparisons against ground-based measurements from the Baseline Surface Radiation Network (BSRN) revealed an overall maximum percentage difference of less than 12%, bias under -20 Wm−2 and a root mean square error (RMSE) under 80 Wm−2. Performance evaluations of Multi-Layer Cloud Motion Vector has been performed against several state-of-the-art techniques and presented in this study. Short-term solar energy forecasting has an established market and rising demand. Accurate forecasts from Multi-Layer CMV hence pose a high potential for real world applications. © 2023 The Authors
Ray-Tracing modeling for urban photovoltaic energy planning and management
(Elsevier Ltd, 2024) Kosmopoulos, P.; Dhake, H.; Kartoudi, D.; Tsavalos, A.; Koutsantoni, P.; Katranitsas, A.; Lavdakis, N.; Mengou, E.; Kashyap, Y.
The traditional Radiative Transfer Modelling solutions for Solar Energy monitoring and forecasting often provide outputs for a single point location or an area location. However, for high resolution representation of areas these solutions suffer due to low simulation speeds. This approach makes it difficult for decision-makers to accurately estimate the solar potential of the administrative area and plan installations accordingly. In this direction, the study introduces three-dimensional Ray-Tracing based radiative modeling which is a high-speed area-based solution for solar energy monitoring. The three-dimensional ray-tracing was simulated by using advanced graphic creation platforms and cloud computing in conjunction with satellite data of the clouds, aerosols, building shadows effects and three-dimensional representations of the city using Cesium 3D tiles and Unreal Engine ®. The entire system was developed in a hybrid model to be exploited by urban planners for solar PV installations and by electricity distribution system operators for energy management and efficient incorporation of the produced energy into the regular and smart grids. This study implements and analyses this Ray-Tracing model for solar photovoltaic energy potential estimation at a rooftop level for the city of Athens, Greece. The total rooftop exploitable area in Athens was found to be close to 34 km2, which is able to massively host distributed PVs followed by almost 4.3 TWh of annually produced energy, whilst Penteli (a Municipality in Athens) possessed a potential of 96.8 GWh with an exploitable area of just 0.8 km2. This amount of energy, in a hypothetical full coverage scenario, is able to provide for 48.7% of Athens's total energy requirement. Similar year-long simulations were conducted using the EU's largest rooftop solar installation at Stavros Niarchos Foundation Cultural Center and randomly selected rooftops having solar installations in different municipalities in Athens. With these estimated solar potential values, the gross savings in natural gas consumption and hence the CO2 equivalent emissions can be computed. With the current estimated solar potential of Athens, the analyzed savings accounted of nearly 2.43 billion euros and 18 MT CO2 equivalent emissions. These computed annual savings are capable of covering installation costs for nearly 100,000 new solar installations. The end-product of this study is the development of a solar cadastre web tool which will support the decision-makers in the energy transition policies and the solar PV penetration into the urban environment and eventually drive the effort into renewable energy transition across the globe. © 2024 The Author(s)