Hello, A yearly allocation for the LCRC cluster has been requested with the following updated information: Submitter/PI: Edwin Campos Project Name: Solar_Forecasting Division: EVS Project title: Multi-Model Machine-Learning Solar Forecasting Technology Associated funding: DOE EERE SunShot Other Systems: None. Science: The objectives of this 3-year project (started on Aug. 2013) are as follows: -Step 1: Perform seminal research to improve modeling and forecasting of solar irradiance. -Step 2: Apply research results obtained from Step 1 (previous) to develop solar power forecasts. -Step 3: Validate developed solar forecasts to meet target values of pre-existing standard metrics. Project description: Failures to predict solar energy generation accurately will undoubtedly constrain the national expansion of renewable energy. There are several technology barriers -- such as forecast inputs integration, forecasts output integration, scalability of forecasting tools, and numerical representation of relevant cloud processes -- that must be overcome for improving solar forecast accuracies to a useful level, if solar energy were to be become a dependable source of energy. This project proposes to overcome these barriers by using novel machine-learning algorithms, big-data analytics, and hi-performance computers. The project will demonstrate that transformational improvements are possible on solar forecasting -- for periods between 0 to 6 hours (including power ramps) and the day ahead -- by determining optimal combinations for observations of thermodynamic profiles measured over a solar power plant, measured cloud motions in the area (e.g., from remote sensing observations at high resolution) and routine forecast outputs from numerical weather models. During the 1st year of the project, we developed computational modules in IDL, Matlab and Fortran. Some of these now run in single core mode on Fusion. Since there was no IDL available on Fusion, we supported the purchase of an IDL software license for the LCRC system, which is expected to be available before the beginning of FY2015. During the following years of the project, we will implement parallel processing of various solar forecasting codes to generate 0-47 hour forecasts over multiple sites across the USA. Industry partnership: IBM, Northrop Grumman, ISO-NewEngland, 3Tier, Green Mountain Power, Tucson Electric Power, Petra Solar, California ISO, JUWI energy, Prime Solutions Inc. Energy Engineering. Project URL: http://solarhighpen.energy.gov/project/ibm_thomas_j_watson_research_center_w... Current FY Hours Used: undetermined amount New FY Requested allocation: 360000 Q1: 60000 Q2: 80000 Q3: 100000 Q4: 120000 Justification: Storage requirements: Thank You, The LCRC Accounts System