Sanzana Tabassum
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sanzana Tabassum has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Eklas Hossain
Boise State University, Boise, ID, USA
2 shared publications - Ashraf Ul Islam
Department of Electrical and Electronic Engineering, Khulna University of Engineering and Technology, Khulna 9203, Bangladesh
1 shared publication - Debopriya Roy Dipta
Department of Electrical and Electronic Engineering, Khulna University of Engineering and Technology, Khulna 9203, Bangladesh
1 shared publication - Ehtashamul Haque
BRAC University, Dhaka, Bangladesh
1 shared publication - Naeem Mohammad
Department of Electrical and Electronic Engineering, Khulna University of Engineering and Technology, Khulna 9203, Bangladesh
1 shared publication - Nafiu Nawar
Department of Electrical and Electronic Engineering, Khulna University of Engineering and Technology, Khulna 9203, Bangladesh
1 shared publication
Latest Publications
- Open Access
Solar Energy in the United States: Development, Challenges and Future Prospects
The ambitious target of net-zero emission by 2050 has been aggressively driving the renewable energy sector in many countries. Leading the race of renewable energy sources is solar energy, the fastest growing energy source at present. The solar industry has witnessed more growth in the last decade than it has in the past 40 years, owing to its technological advancements, plummeting costs, and lucrative incentives. The United States is one of the largest producers of solar power in the world and has been a pioneer in solar adoption, with major projects across different technologies, mainly photovoltaic, concentrated solar power, and solar heating and cooling, but is expanding towards floating PV, solar combined with storage, and hybrid power plants. Although the United States has tremendous potential for exploiting solar resources, there is a scarcity of research that details the U.S. solar energy scenario. This paper provides a comprehensive review of solar energy in the U.S., highlighting the drivers of the solar industry in terms of technology, financial incentives, and strategies to overcome challenges. It also discusses the prospects of the future solar market based on extensive background research and the latest statistics. In addition, the paper categorizes the U.S. states into five tiers based on their solar prospects calculated using analytical hierarchy process and regression analysis. The price of solar technologies in the U.S. is also predicted up to 2031 using Wright’s law, which projected a 77% reduction in the next decade.
Open AccessSolar Energy in the United States: Development, Challenges and Future Prospects
The ambitious target of net-zero emission by 2050 has been aggressively driving the renewable energy sector in many countries. Leading the race of renewable energy sources is solar energy, the fastest growing energy source at present. The solar industry has witnessed more growth in the last decade than it has in the past 40 years, owing to its technological advancements, plummeting costs, and lucrative incentives. The United States is one of the largest producers of solar power in the world and has been a pioneer in solar adoption, with major projects across different technologies, mainly photovoltaic, concentrated solar power, and solar heating and cooling, but is expanding towards floating PV, solar combined with storage, and hybrid power plants. Although the United States has tremendous potential for exploiting solar resources, there is a scarcity of research that details the U.S. solar energy scenario. This paper provides a comprehensive review of solar energy in the U.S., highlighting the drivers of the solar industry in terms of technology, financial incentives, and strategies to overcome challenges. It also discusses the prospects of the future solar market based on extensive background research and the latest statistics. In addition, the paper categorizes the U.S. states into five tiers based on their solar prospects calculated using analytical hierarchy process and regression analysis. The price of solar technologies in the U.S. is also predicted up to 2031 using Wright’s law, which projected a 77% reduction in the next decade.
- Open Access
- 30 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 160646-160660
A Comparative Analysis of Deep Neural Networks for Hourly Temperature Forecasting
High-resolution temperature forecasting can often prove to be challenging for conventional machine learning models as temperature is highly seasonal and varies with the time of the year as well as with passing hours of the day. In most cases, only the daily extremes or mean temperatures are provided by temperature forecasting methods. However, with the growing availability of data and the development of deep neural networks (DNNs) capable of detecting complex relationships, high-resolution temperature forecasting is becoming easier. Typically, historical temperature data along with multiple meteorological sensor data is used for temperature forecasting which increases the complexity of the system making it harder and costlier to implement physically. In this paper, high-resolution hourly temperature forecasting is performed using only historical temperature data. The paper presents a comparative analysis among four popular DNNs-simple recurrent neural network (SRN), gated recurrent unit (GRU), long-short term memory (LSTM), convolutional neural network (CNN), and two hybrid models- CNN-LSTM parallel network and GRU-LSTM parallel network trained on Beijing temperature dataset. Experimental results showed GRU-LSTM parallel network obtained the lowest RMSE (1.691°C) whereas CNN has the best computational efficiency obtaining a slightly worse RMSE (1.759°C). Additionally, a robustness analysis is performed on temperature data from four additional geographically diverse locations (Toronto, Las Vegas, Seattle, and Dallas) which reveals GRU to be the most consistent algorithm. Finally, the paper establishes a correlation between the model performance and the dataset based on their variance and mean absolute deviation with reference to the training dataset.
- 30 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 160646-160660
Open AccessA Comparative Analysis of Deep Neural Networks for Hourly Temperature Forecasting
High-resolution temperature forecasting can often prove to be challenging for conventional machine learning models as temperature is highly seasonal and varies with the time of the year as well as with passing hours of the day. In most cases, only the daily extremes or mean temperatures are provided by temperature forecasting methods. However, with the growing availability of data and the development of deep neural networks (DNNs) capable of detecting complex relationships, high-resolution temperature forecasting is becoming easier. Typically, historical temperature data along with multiple meteorological sensor data is used for temperature forecasting which increases the complexity of the system making it harder and costlier to implement physically. In this paper, high-resolution hourly temperature forecasting is performed using only historical temperature data. The paper presents a comparative analysis among four popular DNNs-simple recurrent neural network (SRN), gated recurrent unit (GRU), long-short term memory (LSTM), convolutional neural network (CNN), and two hybrid models- CNN-LSTM parallel network and GRU-LSTM parallel network trained on Beijing temperature dataset. Experimental results showed GRU-LSTM parallel network obtained the lowest RMSE (1.691°C) whereas CNN has the best computational efficiency obtaining a slightly worse RMSE (1.759°C). Additionally, a robustness analysis is performed on temperature data from four additional geographically diverse locations (Toronto, Las Vegas, Seattle, and Dallas) which reveals GRU to be the most consistent algorithm. Finally, the paper establishes a correlation between the model performance and the dataset based on their variance and mean absolute deviation with reference to the training dataset.