The Vermont Weather Analytics Center (VWAC) is a collaboration between Vermont Electric Power Company (VELCO), statewide partners and IBM to develop and build a system and platform which will optimize the utilization of renewable generation resources, increase grid reliability and lower weather event-related operational costs.
Vermont’s complex terrain and vast local variability coupled with large gaps in observational data pose many challenges from a weather forecasting perspective, which impacts renewable energy generation, energy demand and transmission/distribution grid operations. The VWAC platform integrates weather, energy and data models into a framework that enables real-time prediction, analytics and data processing.
The VWAC platform is comprised of several major components. The weather prediction component is powered by IBM’s Deep Thunder, an advanced NWP model that is based, in part, on a configuration of the Advanced Research core of the Weather Research and Forecasting (WRF-ARW) model. The weather prediction model drives several other models which are part of the platform. These include renewable energy (wind, solar) generation and electricity demand prediction components as well as real-time data analytics components for smart meter and grid data.
The platform hardware includes a high performance computing cluster (HPCC) on which Deep Thunder and other models are run as well as other associated servers, storage and networking for data processing, analytics, products generation and visualization. The platform will be operated by VELCO in partnership with stakeholders and IBM. This is a unique and challenging undertaking for a utility and certainly for a utility of VELCO’s size. It underscores the commitment of Vermont utilities and stakeholders in developing and applying leading edge solutions for renewable energy and grid operations.
We will describe the platform and systems architecture as well as the hardware on which it runs. Examples of applications products will be discussed as well as the interrelationship of major platform components.