Optimized Integration of Distributed Energy Resources and Internet of Things: Control Algorithms, Machine Learning, and Testbeds

Increasing use of distributed energy resources creates opportunities for customers to support power system operations by adjusting power consumption and generation to address grid needs, based on system-wide and local grid conditions. In this chapter, we present our recent works on optimized integration of renewable energy resources and customer Internet-of-Things (IoT) devices in smart grids. We first describe our innovations in control algorithms that manage customer resources to respond to power grid conditions while serving customer needs. To reduce the computational complexity of the control algorithm, we develop a neural network controller, which uses imitation learning to mimic the optimal control algorithm. The neural network controller has much lower computational complexity and can be implemented on small edge devices. We then present an integrated energy IoT testbed consisting of (1) distributed Advanced Real-time Grid Energy Monitor Systems (ARGEMS) with sensing, communication, and control capabilities, and (2) distributed smart home sites that can monitor and control physical and simulated IoT energy resources such as solar systems, home batteries, and smart appliances. The testbed enables demonstration and assessment of a variety of advanced monitoring and control strategies, including our neural network controller, for improved power grid operations and customer benefits.