Zhishang Wang
Biography
Zhishang Wang received his Master?s degree in Computer Science from the University of Freiburg, Germany, in 2019. His academic excellence and passion for research led him to the University of Aizu, where he completed his Ph.D. in Computer Science and Engineering in 2023. Currently, Dr. Wang is an assistant professor in the Division of Computer Engineering at the University of Aizu. His research interests are diverse and cutting-edge, including sustainable computing, and AI-enabled blockchain systems for smart grid platforms. He is also interested in the field of machine learning systems, blockchain, trustworthy AI and neuromorphic systems. He has published numerous papers in prestigious journals and conferences, showcasing his innovative work and dedication to advancing technology. In addition to his research, Dr. Wang has been involved in several collaborative projects, such as the development of a blockchain-based electric vehicle integration system for power management in smart grids. His work not only pushes the boundaries of current technology but also aims to create practical solutions for real-world problems.
Research Interest
Advanced Computing Systems Lab, The University of Aizu, Japan
Abstract
Driving Sustainable Computing: Architectures and Systems for Efficient Energy
Management with EVs and Renewable Resources
The rapidly advancing field of computing technology necessitates continuous
innovation to cater to society's evolving needs while ensuring sustainability and energy
efficiency. Electric vehicles (EVs) and the integration of renewable resources are key
components of this transition, offering promising solutions to reduce carbon emissions.
However, sustainable computing systems that support these technologies face critical
challenges in balancing security, efficiency, and environmental impact. From a security
perspective, robust measures are essential to protect data and ensure model integrity.
From an efficiency standpoint, system designs must minimize energy consumption,
optimize computational performance, and reduce communication overhead. To address
these challenges, a novel framework is proposed, integrating collaborative learning for
qualified local model selection, a blockchain-based approach to ensure model integrity,
and a hybrid cluster-blockchain mechanism to minimize overhead in distributed
networks. This framework aligns with the principles of sustainable computing systems
and green computing, aiming to reduce the ecological footprint while maintaining high
performance.
This method has been deployed to two major projects. The first is an AI-enabled
blockchain approach for electric vehicle integration that combines collaborative
learning for electric vehicle energy consumption prediction with AI-driven solar energy
forecasting to improve resource planning. The second project focuses on vehicle-to
grid networks, enabling secure and efficient energy trading between vehicles and the
power grid. Additional works extend these concepts to other areas, demonstrating the
versatility of sustainable computing solutions.
Future work will refine these sustainable computing architectures for more complex
vehicular networks and investigate strategies for low-power, resource-efficient
computing. By prioritizing sustainability and energy efficiency, this research aims to
provide robust, scalable solutions that adapt to evolving requirements in the energy and
automotive sectors, with the potential for broader application across diverse industries
and domains. Furthermore, the development of prototypes and collaboration with
related companies through a collaborative and multidisciplinary approach will ensure
practical and impactful outcomes.
