AI-enabled data analytics and control for power system IoT framework
* 21PESGM0123, IoT-enabled DER gateways for sustainable, scalable and secure DER integration: A. RENJIT, EPRI * 21PESGM0124, IoT data-driven power system stability assessment and control: Y. XU, Nanyang Technological University * 21PESGM0125, IoT-based virtual power plant solutions considering smart home energy management: Z. DONG, UNSW Sydney * 21PESGM0126, Big data based evaluation of low-voltage metering devices and monitoring of load demand behaviors: F. WEN, Zhejiang University * 21PESGM0127, Optimal control of blockchain-enabled distributed resources for grid services using deep reinforcement learning: Z. YI, GEIRI North America * 21PESGM0128, IoT and AI combined testbed for distributed demand response devices: M. MOTALLEB, Softbank Energy
-
PES
IEEE Members: $10.00
Non-members: $20.00
While IoT systems are being deployed to benefit the power systems and the customers, they are generating a tremendous volume of data from the grid's edge. This can be utilized to further improve the situation awareness and operation of the grid. This panel session will discuss the emerging AI analytics methods for managing such exponentially increasing data for power systems' IoT frameworks, from both grid and demand-side points of view. Specifically, this will include novel machine learning techniques employed to analyze data and control IoT systems at different network layers (e.g., edge devices and cloud servers) and architectures (e.g., blockchain and distributed systems), as well as how these emerging techniques can benefit the operation of the bulk power grid in terms of stability and reliability.
Chairs:
Di Shi, AINERGY LLC, Yan Xu, Nanyang Technological University
Sponsor Committees:
(PSOPE) Technologies &, Innovation Subcommittee