NOAA and DOE partnered up with industry to demonstrate how enhancements in observation networks can improve wind forecasting, thus providing economic savings to utilities by reducing their operational costs. This paper and presentation will provide an overview of the NOAA/DOE partnership with WindLogics and Midwest ISO (MISO), and some preliminary results. Team members include: WindLogics, National Renewable Energy Laboratory (NREL), South Dakota State University, Nextera, and MISO. The main objectives of the project are: 1) to provide additional meteorological data near the turbine hub height for assimilation into the NOAA High Resolution Rapid Refresh (HRRR) model, 2) determine the improvements of wind power forecasts as result of better measurements, and 3) quantify the economic benefits for MISO. The study area covers a large portion of the MISO operating region and includes North and South Dakota, Iowa, Minnesota, and Nebraska, as shown in Figure 1. The sensor network includes existing NOAA upper air observations (white icons), Nextera nacelle anemometers (green dots), Nextera tall towers (orange squares, some not shown for proprietary reasons), WindLogics sodars (light yellow squares), NOAA-provided profilers and flux stations (blue icons), and South Dakota State University (SDSU) tall towers (red squares). Six different wind power forecasts will be generated for the study. The forecasts will include a raw forecast, forecast with Support Vector Machine (SVM) learning system, and an ensemble forecast with SVM. Each of the approaches will be run with and without the new HRRR inputs. An uncertainty analysis will be performed on each of the forecasts using Mean Absolute Error (MAE), Root Mean Square Error (RSME), bias metrics, and adapted metrics for wind power. Alternative metrics will also be investigated, such as the Kolmogorov-Smirnov test Integral (KSI) or information entropy. The utility and benefit of these metrics will be explored within the unit commitment and economic dispatch process. MISO operates on a “Day 2” market, which means that they commit generation units on a day-ahead basis and dispatch units in real-time. They also administer fast energy markets, and have robust ancillary services markets. This structure, coupled with their large balancing area provides a lot of flexibility for managing variable generation sources. To evaluate the cost benefits of wind forecasting improvements for MISO, their system will be modeled in a production cost model. The base case will utilize the raw forecast without HRRR inputs, and will be compared to all other cases. The analysis will evaluate the impact of forecasted energy delivery and actual delivery on cost, the impact on ancillary service requirements, the benefits of selling in hour-ahead or day-ahead markets, and the benefit of ramp forecasts. Preliminary results of this analysis will be presented.