Technologies
Intelligent Dynamic Energy Management System (I-DEMS) for Integration of Renewable Energy Sources with Smart Grid
As sustainable, green, and environmentally friendly renewable energy sources, e.g. wind and solar, begin to supply increasing percentages of power to the grid, integrating them into grid operations is becoming increasingly difficult, because the output of renewable resources fluctuates depending on the weather condition and time of day and the majority of renewable energies cannot guarantee a continuous and steady amount of power generation. Grids that allow for the integration of renewable energy sources have to consider these destabilizing effects due to such variable energy inflow. As renewable power sources are gaining increasing levels of grid penetration, intelligent energy management technologies that can handle variability and uncertainty become essential, and advanced control algorithms to manage energy dispatch and maximize its performance become crucial.
We have been dedicated to the development of a highly reliable, self-regulating, and efficient smart grid system which will allow the integration of renewable distributed power generation with grid. We have pioneered the development of an intelligent dynamic energy management system (I-DEMS) for smart grid by introducing an evolutionary adaptive dynamic programming and reinforcement learning framework. The I-DEMS is an optimal or near-optimal DEMS capable of performing grid-connected and islanded grid operations. Using the I-DEMS to schedule dispatches allows the renewable energy sources and energy storage devices to be utilized to their maximum in order to supply the critical load at all times. Based on the grid’s system states, the I-DEMS generates energy dispatch control signals, while a forward-looking network evaluates the dispatched control signals over time.
Multi-Agent Control System For Real-time Volt/VAR Optimization in Smart Substation Due to the effects of load profiles on the quality of delivered energy to the customers, a key function of smart grid is to monitor and control the amount of reactive power and energy losses in distribution systems. One of the main techniques employed to reduce losses in distribution feeders is Volt/VAR Optimization (VVO). VVO is an advanced method that optimizes voltage and/or reactive power (VAR) of a distribution network based on predetermined aggregated feeder load profile. This is normally done based on offline techniques using load tap-changers, voltage regulators, capacitor banks, and other existing Volt/VAR control devices in distribution substations and/or distribution feeders. The challenge is integrating all of these elements into a totally digital substation and making it work in a demanding environment.
To overcome this challenge, we have developed a new multi-agent control system for VVO optimization based on load profiles calculated using real-time measurements of service quality at the point of delivery to customers. While most traditional power control systems act passively to events, the control system we have developed adds active control options to the control strategies. The multi-agent system developed by us is designed to take into account dynamic environmental requirements to deliver its objectives, which works within a real-time and fully distributed system where each node can connect to other nodes at the same or different level. These communications can be scheduled on-demand based on their tasks such as self-healing and data mining. The system could define valid ranges of data, detect out-of-range data, and transfer the data and fault messages to the destination.