16TH CPEEE 2026丨Osaka, Japan

CPEEE 2026-Invited Speakers

Assoc. Prof. Takuji Matsumoto, School of Environment and Society, Institute of Science Tokyo, Japan

Takuji Matsumoto (Member, IEEE) is an Associate Professor at the School of Environment and Society, Institute of Science Tokyo, Japan. He received his B.Eng. from the University of Tokyo, Japan, in 2005, followed by an MS in Technology and Policy from the Massachusetts Institute of Technology, USA, in 2012, and a Ph.D. in Business Administration from the University of Tsukuba, Japan, in 2020. He was a visiting PhD student at the London Business School, UK. Previously, he was a senior researcher at the Central Research Institute of Electric Power Industry, Japan. He has about 15 years of work experience in government agencies and a private think tank, mainly in the energy sector, where his work included policy evaluation, market analysis, and risk management consulting. He is the first author of several peer-reviewed journal articles, particularly in top-tier journals such as IEEE Transactions on Power Systems and Energy Economics. His research interests include electricity market analysis, energy finance, statistical modeling, and forecasting.
Speech Title: Forecasting Methods and Their Applications in Electricity Markets
Abstract: Forecasting spot electricity prices has become increasingly important for power utilities, particularly in the face of growing market volatility and uncertainty. While advanced methods, including machine learning, are being widely applied, using complex algorithms alone does not guarantee practically effective or reliable forecasting.
This talk explores the balance between interpretability and predictive performance, highlighting several representative models and their relevance to electricity market forecasting. These include regression-based approaches such as LASSO, Ridge Regression, and pcLasso, which builds on the strengths of the former methods to better capture structured information in the data.
We will also examine probabilistic forecasting approaches, including Quantile Regression, the quantile prediction model as its extension, and GAMLSS, with a focus on their ability to model uncertainty in key market variables and events such as price spikes.Finally, I will present selected findings on the integration of forecasting and optimization in electricity trading, emphasizing how predictive models can support decision-making under uncertainty. The presentation aims to provide perspectives that inform both practical implementation and further research in electricity market forecasting.

Asst. Prof. Yu-Jen Chen, Southern Taiwan University of Science and Technology (STUST), Taiwan

Dr. Yu-Jen Chen is an Assistant Professor in the Department of Mechanical Engineering at Southern Taiwan University of Science and Technology (STUST). He specializes in the design of fluid-based renewable energy systems, with research interests that include low-speed, high-torque axial flux permanent magnet (AFPM) generator design, fluid machinery energy conversion, digital twin, and intelligent predictive maintenance systems. Dr. Chen has led multiple interdisciplinary projects on green energy applications and aquaculture sustainability, integrating digital sensing and microgrid technologies into local communities. He has published extensively and presented his work in international journals and conferences related to renewable and clean energy. In addition to academic research, Dr. Chen actively promotes innovation and entrepreneurship education, guiding student teams to develop practical renewable energy solutions and organizing the Taiwan Collegiate Wind Competition (TCWC).
Speech Title: Application, Development and Analysis of Low-Speed, High-Torque Axial Flux Permanent Magnet Generator for Fluid Machinery Renewable Energies
Abstract: This presentation introduces the design, development, and performance analysis of a low-speed, high-torque axial flux permanent magnet (AFPM) generator. The proposed generator adopts a series-stator configuration equipped with air-cored windings and NdFeB permanent magnets, enabling direct-drive operation without a gearbox, compact structure, and high efficiency under variable-speed conditions. Experimental verification confirms its linear voltage–speed characteristics and stable electromagnetic behavior, achieving an efficiency range of 80% to 92% under various load conditions. The study further examines the generator’s modular structure and electromagnetic symmetry, demonstrating adaptability to multiple fluid machinery environments. By integrating digital-twin monitoring and predictive maintenance systems, this research aims to enhance the reliability and sustainability of distributed renewable energy systems. The findings contribute to advancing high-performance AFPM technology and its practical implementation in hybrid microgrid and net-zero energy applications.
Prof. Dr.-Ing. Amir Ebrahimi, Institute for Electrical Drives, Power Electronics and Devices – University of Bremen, Germany
- Amir Ebrahimi received his PhD in the field of electrical machines and drives from the University of Stuttgart. Subsequently, he served as the group leader for electromechanical drive systems and wearable robotics at the Fraunhofer Institute IPA. From 2017 to 2023, he held the position of Junior Professor for Electrical Machines at Leibniz University Hannover, where he founded the Vector theory of rotating electrical machines. Since July 1, 2023, he has been appointed as full professor and is the head of the Department of Electrical Drives and Power Electronics at the Institute of Electrical Drives, Power Electronics and Devices at the University of Bremen. His research interests encompass electric drives, renewable energy (with a specific focus on wind turbines and hydrogenerators), mechatronics (particularly wearable robotics), electromobility (including electric vehicles and electric flying), electric machines, and power electronics.
- Speech Title: AI-Driven Sensor Fusion for State and Fault Diagnostics in Electrical Machines
- Abstract: Predictive maintenance of electrical machines using Artificial Intelligence (AI) represents a transformative approach to industrial reliability and efficiency. Instead of relying on scheduled maintenance or reacting to unexpected failures, AI-driven predictive maintenance enables early detection of faults and performance degradation through continuous data monitoring and intelligent analysis. This not only reduces downtime and maintenance costs but also extends the lifespan of critical equipment.A key factor in achieving accurate predictions lies in the proper design of the sensor system. Sensors serve as the primary data source, capturing essential parameters such as vibration, temperature and current signals. Defining the right sensor types, placements, and sampling strategies ensures that the collected data truly reflects the machine’s operational condition. Furthermore, sensor fusion— the integration of data from multiple sensors— enhances diagnostic accuracy by combining complementary information. Through AI algorithms, such fused data enables more reliable fault detection and classification, even in complex or noisy environments.

Asst. Prof. I-HSIEN LIU, National Cheng Kung University, Taiwan

Dr. I-Hsien Liu is an assistant professor in the Department of Electrical Engineering and the Master Program in Cyber-Security Intelligence at National Cheng Kung University. His research focuses on industrial control systems, network security, computer networks, and cybersecurity testbeds. He is the deputy director of Taiwan Information Security Center at National Cheng Kung University (TWISC@NCKU). As a core member of the Taiwan Information Security Center at National Cheng Kung University, he plays a key role in developing critical infrastructure security testbed. Leveraging this testbed, his team has developed various protection technologies, acquired multiple invention patents, and assisted government agencies in strengthening the security of their control systems. His contributions have been widely recognized, including awards of excellence team, and the Best Popularity Award at the 2022 Annual Results Presentation from the National Science and Technology Council’s Advanced Information Security Technology Project. Moving forward, Dr. Liu continues to advance cybersecurity research, aiming to enhance the resilience and security of critical infrastructure systems.
Speech Title: Blockchain-Driven Intelligence Reservoir Control and Safety
Abstract: Reservoirs are vital for water resource management but face unprecedented challenges from extreme weather and cyberattacks targeting their critical control systems. Traditional operations, often reliant on manual processes, suffer from personnel shortages and inefficiencies, struggling to balance security, efficiency, and sustainability. To address these vulnerabilities, our team has developed some innovations technology base on cybersecurity testbed to enhance the reliability, intelligence, and resilience of reservoir control systems.