Haizhou Liu , Ph.D.

Southeast University

Lecturer

Contact

Links

CV Download

[PDF-CN]     [PDF-EN]

Education

Year Degree Institution Major Supervisor GPA
2022.09 — 2024.06 Ph.D. Tsinghua University Electrical Engineering Xuan Zhang 3.9/4.0
2019.09 —2022.06 Master (Transferred to Ph.D.) Tsinghua University Environ Science and New Energy Tech Hongbin Sun/Xinwei Shen 3.9/4.0
2015.09 — 2019.06 B.Sc. Nanjing University Physics Lin Zhou/Jia Zhu 4.7/5.0

Overseas Experience

Year Identity Institution Major Supervisor GPA
2023.05 — 2024.01 Visiting Scholar UC Berkeley Computer Science Somayeh Sojoudi ——
2019.09 — 2021.08 Online Program U-M Ann Arbor Applied Data Science —— 3.9/4.0
2017.08 — 2017.12 Exchange Student Duke University Physics Sara Haravifard 3.9/4.0

Awards

  • Awarded during Ph.D. study at Tsinghua University:

    • 2022.12   Outstanding Graduating Student at Tsinghua University.
    • 2022.12   National Scholarship for Graduates.
    • 2021.12   Comprehensive Scholarship Award at Tsinghua University, First Prize.

  • Awarded during undergraduate study at Nanjing University:

    • 2019.09   Outstanding Graduation Thesis at Nanjing University.
    • 2019.05   Outstanding Graduating Student at Nanjing University.
    • 2016.11   National Scholarship for Undergraduates.

  • Awarded during internship at Huawei Technologies:

    • 2021.06   Huawei Creativitiy Pioneer 2021 (First intern in lab to be awarded this prize).

Research Directions

Smart Grid; Smart Cities; Distributed Machine Learning (Federated Learning); Integrated Energy System Optimization; Privacy Preservation.

Research Experience

  • 1. Federated Learning and Its Application in the Smart Grid News

    Supervisor: Prof. Xuan Zhang

    • Demonstrated the applicability and potentials of federated learning in Smart City load prediction problems.
    • Proposed a hybrid federated learning framework based on XGBoost, in order to incentivize homogeneous and heterogeneous data holders to simultaneously join in the collaborative training.
    • Designed a multi-task federated learning framework for district load forecasting, with dynamic and simultaneous district dropout mechanisms, respectively.

  • 2. Model/Data-Driven Integrated Energy Systems News

    Supervisor: Prof. Hongbin Sun/Prof. Xinwei Shen

    • Improved the heuristic Progressive Hedging algorithm, in order to accelerate convergence in stochastic electricity-gas coupled scheduling problems.
    • Applied artificial neural networks to achieve fast and accurate economic dispatch in an electricity-gas coupled system.
    • Proposed a data-driven warm start algorithm for optimal economic dispatch in integrated energy systems.

  • 3. Solar-Thermal Conversion based on Nanomaterials News

    Supervisors: Prof. Lin Zhou/Prof. Jia Zhu

    • Designed a highly efficient solar thermal photovoltaic absorber based on the Optical TAMM State.
    • Conducted studies and reviews on nano-scale solar water evaporation.

Internships

  • 1. Huawei Technologies Ltd.

    2012 Laboratories –Central Research Institute – Service Lab

    • Developed an XGBoost-based federated learning framework with dynamic task allocation.
    • Constructed an XGBoost learning model to predict the energy consumption patterns of Huawei’s 5G base stations.

Skillset

1. English skills: CET-6 626, TOEFL 110, GRE 329+3.5. Especially fluent in listening and speaking.

2. Programming Languages: Python, MATLAB, C++.

3. Coding Expertise: Data Analysis (Pandas, Scikit-learn), Deep Learning (TensorFlow), Git Version Control.

Publications

2024.01 H. Liu, X. Zhang, H. Sun, and M. Shahidehpour, “Boosted multi-task learning for inter-district collaborative load forecasting,”IEEE Trans. Smart Grid, vol. 15, no. 1, pp. 973-986. [Link]
2023.12 S. Tao*, H. Liu* et al., “Collaborative retired battery sorting for efficient and profitable recycling via federated machine learning,” Nat. Commun., vol. 14, Art. No. 8032 (*Equal Contribution). [Link]
2022.10 H. Liu, X. Zhang, X. Shen, H. Sun, and M. Shahidehpour, “A hybrid federated learning framework with dynamic task allocation for multi-party distributed load prediction,” IEEE Trans. Smart Grid, vol. 14, no. 3, pp. 2460-2472. [Link]
2022.08 H. Liu, X. Zhang, X. Shen, and H. Sun, “Privacy-preserving power consumption prediction based on federated learning with cross-entity data,” in Chinese Control Decis. Conf. (CCDC), pp. 181-186. [Link]
2022.05 Z. Lin*, H. Liu* et al., “Tamm plasmon enabled narrowband thermal emitter for solar thermophotovoltaics,” Sol. Energy Mater. Sol. Cells, vol. 238, Art. No. 111589 (*Equal Contribution). [Link]
2021.11 H. Liu, L. Yang, X. Shen, Q. Guo, H. Sun, and M. Shahidehpour, “A data-driven warm start approach for convex relaxation in optimal gas flow,” IEEE Trans. Power Syst., vol. 36, no. 6, pp. 5948-5951. [Link]
2021.07 H. Liu et al., “Application of modified progressive hedging for stochastic unit commitment in electricity-gas coupled systems,” CSEE J. Power Energy Syst., vol. 7, no. 4, pp. 840-849. [Link]
2020.12 H. Liu, X. Shen, Q. Guo, and H. Sun, “A data-driven approach towards fast economic dispatch in electricity-gas coupled systems based on artificial neural network,” Appl. Energy, vol. 286, Art. No. 116480. [Link]
2020.07 H. Liu, X. Shen, H. Sun, and W. Zhao, “Stochastic day-ahead scheduling of electricity-gas coupled systems via progressive hedging,” in IEEE Ind. Commer. Power Syst. Asia Tech. Conf. (ICPS), pp. 64-69. [Link]
2020.06 W. Zhao, J. Zheng, Z. Han, and H. Liu, “Large-disturbance stability analysis method based on mixed potential function for AC/DC hybrid distribution network with PET,” IET Gener. Transm. Distrib., vol. 14, no. 18, pp. 3802-3813. [Link]
2019.09 X. Liu*, H. Liu*, X. Yu, L. Zhou, and J. Zhu, “Solar thermal utilizations revived by advanced solar evaporation,” Curr. Opin. Chem. Eng., vol. 25, pp. 26-34 (*Equal Contribution). [Link]
2019.08 Y. Wang, H. Liu, and J. Zhu, “Solar thermophotovoltaics: progress, challenges and opportunities,” APL Mater., vol. 7, no. 8, Art. No. 080906. [Link]
2019.07 H. Liu, X. Yu, J. Li, N, Xu, L. Zhou, and J. Zhu, “Plasmonic nanostructures for advanced interfacial solar vapor generation,” Sci. Sin.-Phys. Mech. Astron., vol. 49, Art. No. 124203. [Link]
2019.04 J. Liang, H. Liu, J. Yu, L. Zhou, and J. Zhu, “Plasmon enhanced solar vapor generation,” Nanophotonics, vol. 8, no. 5, pp. 771-786. [Link]