Hi all,

 I’m happy to inform you that EMSEL Prof. Tariq (Assistant professor, DKU), Usama Ph.D student's paper (w/Seshagiri: IIPE) has been accepteded at International Journal of Energy Research (SCI, JCR TOP 3%:NUCLEAR SCIENCE & TECHNOLOGY​). Congratulation for this outstanding journal publication. 

Shahzeb Tariq+, Usama Ali+, Seshagiri Rao Ambati and ChangKyoo Yoo*, Attention Driven–Chained Transfer Learning for Generalized Sequential State of Charge Forecasting in Vanadium Redox Flow Batteries, ​International Journal of Energy Research (ISSN:0363-907X​, JCR TOP 3%:NUCLEAR SCIENCE & TECHNOLOGY), Wiley publishing, Vol. 2025 (1), pp. 9925384(2025.3) (Ack: NRF2021R1A2C2007838)​

산화환원 배터리 Sequential SOC forecast DL 예측 모델 : Forecasting of SOC of Flow battery using multi-head attention with Chained Transfer Learning vanadium redox flow batteries ​

** EMSEL/DKU Shahzeb교수와 Usama 통합 과정 논문이 International Journal of Energy Research​​ ​저널 (SCI, Top 3% journal​)​에 게재되었습니다 

-  공동연구기관: 동국대 바이오환경과학과, 인도 석유화학에너지공과대학

- 저널 : International Journal of Energy Research​ 저널 (SCI, Top TOP 2.9%), NUCLEAR SCIENCE & TECHNOLOGY​ 분야에서 Rank 1/34 로 매우 좋은 저널​

- 연구 주제: 대용량 에너지 저장시스템 Vanadium redox flow batteries 산화환원 배터리 Sequential SOC forecast DL 예측 모델

|** 1st research output on Vanadium redox flow battery **

 Title : Attention-driven chained transfer learning for generalized sequential state of charge forecasting in vanadium redox flow batteries

Journal: International Journal of Energy Research

Keywords: Energy storage, Vanadium redox flow battery, State of charge, Sequential forecast, Multi-head self-attention, Chained transfer learning

Key : Forecasting of Future state of charge (SOC) levels of Flow Battery using integrated multi-head attention (MHA) with chained transfer learning (CTL)

*  대용량 에너지 저장시스템​ 플로우 배터리 분야 첫 연구실 논문으로 ​Vanadium redox flow battery​ 모델링 그리고 SOC예측 모델, 추후 연구로 RL control 및 Iterative Learning Control진행..

축하합니다.<o:p></o:p>

--------------------------------------------------------------------------------

Abstract

The increasing integration of renewable energy sources into power grids necessitates efficient energy storage systems to balance supply and demand. Vanadium redox flow batteries (VRFBs) are becoming increasingly popular because of their long lifespan and flexible energy storage capabilities. Central to the effectiveness of VRFBs is the accurate estimation of future state of charge (SOC) levels. However, conventional SOC forecast frameworks suffer from poor generalization capabilities, which restrict their applicability in real-life energy systems. This research introduces a sequential forecast framework that combines multi-head attention (MHA) with chained transfer learning (CTL) to estimate SOC sequences across multiple temporal horizons. The model performance is evaluated by forecasting SOC levels of the VRFB system operated under various charging and discharging current profiles. The results demonstrate that the change in the VRFB system’s operational dynamics significantly reduces the forecast accuracy of conventional frameworks, with maximum MAE reaching 66%. Compared to the best performing baseline trained on a linear current profile, the CTL-MHA-GRU decreased the maximum MAE from 28.7% to below 1.5%. The generalization capability of the proposed framework addresses a critical barrier to the integration of SOC forecast frameworks with smart energy storage systems.

Keywords: Energy storage, Vanadium redox flow battery, State of charge, Sequential forecast, Multi-head self-attention, Chained transfer learning

  <o:p></o:p>

Fig. 8 Schematic representation of the proposed CTL based sequential forecast framework.<o:p></o:p>