Sohag Kumar Saha | PhD in ECE @ TnTech

✅ PhD Researcher

class ContactInformationCard: 
  def __init__(self):
    self.dept  = "Electrical and Computer Engineering @ Tennessee Tech University" 
    self.lab   = "Smart Grid Lab @ CLEM 103" 
    self.email = "ssaha42@tntech.edu" 
    self.phone = "+1 (931) 252-9504" 
  def flipCard(self):
    print("tap on the card to flip.")
  def closeCard(self):
    print("tap outside to close it.")

Sohag Kumar Saha

ssaha42.tntech.com

Sohag Kumar Saha / 🎧

I am a graduate research assistant at the Smart Grid Lab under Center for Energy Systems Research (CESR) affiliated with the Tennsee Tech University at Cookeville, TN, USA under the supervision of Prof. Dr. Satish Mahajan.

I grew up in Manikganj, Bangladesh, and was fortunate to spend my most memorable time at the Pabna University of Science and Technology (electrical and electronic engineering program from 2009-2013) with very good friends, where we learned a lot of technical aspects and also played Cricket, football (soccer) on University fields together.

I do research in microgrid intelligent energy management using machine learning and metaheuristic-based algorithms for determining the optimal operation of DERs and dispatch of load efficiently. I have also, utilized the real-time HIL simulation of Typhoon HIL, SEL 3530-4 RTAC, and EPC inverters power controllers.

Intelligent Energy Management in Grids: smart grid, microgrid, hardware-in-the-loop simulation
Machine Learning and Deep Learning in Power Systems: forecasting of solar irradiance, and load profiles

📜 Recent News

The solar irradiance forecasting using hybrid deep learning paper accepted in NAPS 2024, Texas, US.

August 8th, 2024

The Peak Shaving using Battery Energy Storage Systems via Hardware-in-the-Loop (HIL) poster accepted in Appalachian Energy Summit 2023 (June 7-9), Appalachian State University, North Carolina, USA.

May 26th, 2023

The MiTM attack for investing network vulnerabilities in smart grid paper accepted in IEEE World AI IoT Congress (AIIoT) 2023, Seattle, WA, US.

May 8th, 2023

The anomaly detection techniques in smart grid paper accepted in IEEE World AI IoT Congress (AIIoT) 2023, Seattle, WA, US.

May 8th, 2023

The digital twin application on autonomous vehicular systems paper accepted in IEEE World AI IoT Congress (AIIoT) 2023, Seattle, WA, US.

May 8th, 2023

The automatic dust detection in solar PV panels using deep learning poster accepted in 18th Annual Research and Creative Inquiry Day-2023, Tennessee Technological University, TN, USA.

April 18th, 2023

I am invited to review papers at IEEE PES General Meeting conference.

February 2023

I joined as a Graduate Teaching Assistant/ Instructor at the dept. of Electrical and Computer Engineering, Tennessee Tech University, USA.

August 2022

I received Bangladesh Sweden Trust Fund scholarship for covering the Travel expense of my PhD study at Tennessee Tech University, USA.

May 2022

I joined as a Graduate Research Assistant at the Smart Grid Lab under the Center for the Energy Systems Research (CESR), Tennessee Tech University, USA.

August 2021

📚 Publications

CCLGS: Multivariate Optimal Hybrid Deep Learning Model for Forecasting of Day-Ahead Solar Irradiance with Meteorological Constraints
North American Power Symposium (NAPS) 2024 (10/13/2024-10/15/2024)
Sohag Kumar Saha, Satish M. Mahajan.
[PDF]
Abstract: With the growing integration of solar power generation into smart grids, accurate solar irradiance forecasting is of paramount importance for efficient grid operation and renewable energy management. In this paper, a data decomposition approach with two different methods of deep learning and grid search optimization was combined to develop a better hybrid model to forecast solar irradiance. The proposed model combines spatial and temporal information to improve forecasting accuracy by considering the impact of meteorological constraints such as global horizontal irradiance, temperature, relative humidity, wind speed, cloud type, direct normal irradiance, diffuse horizontal irradiance, and solar zenith angle. In addition to the model architecture, this work incorporates hyper-parameter optimization to fine-tune the parameters of the model for optimal performance. The design of the model ensures that the system adapts to the specific characteristics of the solar irradiance data and meteorological conditions under consideration. The proposed hybrid model was evaluated using real-world data to outperform traditional forecasting methods in terms of accuracy. The results of the proposed hybrid model indicate better prediction ability as measured by four parameters (lower RMSE and MAE, fewer epochs, and a higher \({R^2}\) co-efficient). ... See More

🧩 Outreach activities

APSCL-ISVRelay: Design of An Intelligent Supervision Relay for Protection of Tertiary Winding of the Power Auto-Transformer
Innovation Idea Project, APSCL, BD
Sohag Kumar Saha, Mesbah Salahuddin, Oli Ahad Khan, and M.H. Khan
[POST]
Description: We have presented a smart intelligent relay for supervision of the protection of the tertiary winding of the power auto-transformer of the inter-bus coupling transformer of Ashuganj 132/230 kV Grid Substation, Ashuganj, B.Baria, Bangladesh.