ERCOT LOAD FORECASTING. By Dr. Todd Crawford Chief Meteorologist The Weather Company, an IBM Business
|
|
- Sharon Thornton
- 7 years ago
- Views:
Transcription
1 ERCOT LOAD FORECASTING By Dr. Todd Crawford Chief Meteorologist The Weather Company, an IBM Business
2 Table of Contents Methodology 3 Weather Forecasting 3 Load Forecasting 3 Results 4 Aggregate 4 Seasonal Variation 5 The Weather Company VS. ERCOT-Issued Forecast 5 Conclusion 7 1
3 When a company s profitability is dependent on weather, accuracy and insight can be critical to success. The Weather Company, an IBM Business (Weather) has recently made significant investments in both (a) an improved weather forecasting system and (b) data science capabilities. The former allows for the most accurate, timely, and spatially resolute weather forecasts in the industry, while expertise in the latter allows us to convert these accurate weather forecasts into user-friendly products for our clients in the utility and energy trading businesses. One of these exciting new products is a load forecasting module for the ERCOT region, with new forecasts produced each hour, at hourly resolution out to 15 days. The Weather Company load forecasting algorithm exhibits errors (expressed with the MAPE metric) of generally less than 2% (for the aggregate ERCOT region) during the first three days of the forecast, rising to 3-4% by day 6 and 4-5% by day 9. A comparison with archived ERCOT-produced load forecasts out to 180 hours indicates that The Weather Company forecasts had lower errors for 98% of the forecast hours, with relative improvements ranging from 5-20%. 2
4 Methodology WEATHER FORECASTING Good load forecasts are strongly dependent upon good weather forecasts, and The Weather Company s weather forecasting engine (Forecasts on Demand, or FoD) is unsurpassed in that regard. FoD is an automated system that produces hourly forecasts for all of the most relevant weather variables (e.g., temperature, dew point, wind speed, precipitation, cloud cover, snowfall) at 4-km spatial resolution across the globe. These forecasts are updated hourly based upon the latest observations and latest model data. FoD forecasts are a skill-weighted blend of all available weather models, including the ECMWF, GFS, and NAM models (deterministic and ensemble), along with GFS MOS and our own proprietary high-resolution weather model (RPM). Weights are assigned to each model based upon the optimal combination of bias-corrected model forecasts over the most recent weeks. Furthermore, the first few hours of the forecast period are forward-corrected based upon the latest observations. Doing this insures that there are no discontinuities early in the forecast period. The weather forecasts are updated each hour as new model data and observations come in, and the 4-km spatial resolution allows for hyper-local forecasts that generate a more accurate representation of energy demand via the load forecasts. LOAD FORECASTING The Weather Company data scientists have developed a comprehensive set of neural networks for predicting load in the ERCOT region. There are eight weather zones (below, left) and four load zones (below, right) in ERCOT. More than 2500 neural networks were trained for each of the eight weather zones. The networks accounted for day of the week so that separate networks did not have to be developed for weekdays and weekends. Load forecasts from the eight weather zones were then rolled up into forecasts for the four load zones. Eight ERCOT weather zones Four ERCOT load zones 3
5 For each of the eight weather zones, unique neural networks were trained for the bal-day and next day periods, along with each of the following three days, with a final one for the entire period beyond hour 120. Variable selection was used to optimize the appropriate set of weather parameters needed for each zone and forecast period. The bal-day neural networks blend the most recent values of observed load into the raw forecast values using a similar forward correction scheme used in FoD. The next-day and medium-range forecasts are purely model driven. Results To assess the new forecasting system, we evaluated the 15-day hourly forecasts using data for the 12-month period from March 2015-February Using a full year of data insures that we capture any seasonal variability in the performance of the system. All results below are expressed with the MAPE (mean absolute percentage error) metric. The percentage error is defined here as the forecast error divided by the observed load. AGGREGATE The graph below shows aggregate statistics for the entire period, for each of the four load zones as well as overall numbers for the entire ERCOT region (dark blue). The data below is representative of the forecasts issued at 7 AM, but the data for other times (including the 10 AM forecasts) is quite similar. Errors, expressed with the MAPE metric, for The Weather Company load forecasts from March 2015 February 2016 across the ERCOT region Note that the errors begin at zero at the start of the forecast period, since Weather ingests the latest hourly demand observation into its model at forecast hour zero and uses the most recent observations to forward-correct the first few hours of the forecast string. The errors increase more sharply with time early in the forecast period as the beneficial impact of the forward-correction scheme wanes. After the first few hours, the errors increase more linearly with time. There is also a clear diurnal signal as well, with the largest errors occurring in the late evening when absolute loads are highest. 4
6 It s important to emphasize that the errors for the entire ERCOT region are lower than the errors from three of the four load zones, the exception being the more sparsely-populated West load zone. This behavior is expected. The errors in the sub-regions are generally uncorrelated, which typically results in better aggregate forecasts as a significant percentage of the errors cancel out upon combining the sub-regions. The lower errors in the West zone are primarily observed during spring and summer, when the eastern zones (North/South/Houston) are plagued by less predictable thunderstorm complexes (that produce larger forecast errors) than the West zone. SEASONAL VARIATION If we look at the errors as a function of season (below), we see that errors are generally similar through day 5. After that, errors are lowest in summer, when weather forecasting skill is higher due to a more persistent and predictable pattern. Similarly the errors in winter are considerably larger by the end of the forecast period during that more volatile season. Finally, the diurnal variation is noticeably smaller during the fall, presumably due to limited demand during this shoulder season with limited thunderstorm activity (unlike spring). Still, for all four seasons, errors remain less than 5% out to day 7. Errors, expressed with the MAPE metric, for The Weather Company load forecasts from March February 2016 across the ERCOT region THE WEATHER COMPANY FORECASTS VS. ERCOT-ISSUED FORECASTS Market participants already have access to freely-available ERCOT load forecasts, which are updated every hour. Because of this, its important to demonstrate improved skill relative to the ERCOT-issued forecasts in order to prove the value of a new load forecasting system. This section will detail the performance of the new Weather system against the ERCOT system. The first thing that stands out in the analysis is the consistently lower errors for The Weather Company forecasts throughout the forecast period, for both the 7 AM and 10 AM forecasts (below). The MAPE values from the Weather Company forecasts are consistently percentage points lower than the ERCOT-issued forecasts. 5
7 Errors, expressed with the MAPE metric, for The Weather Company and ERCOT-issued load forecasts from 2015 for the aggregate ERCOT region, for 7 AM forecasts (left) and 10 AM forecasts (right) If we express the improvement in Weather load forecasts relative to ERCOT-issued forecasts, we can see that the biggest gap is found during the crucial bal-day and next-day periods, with up to a 20% reduction in errors (below). The Weather Company advantage decreases with time, but still remains above 5% through the entire period. Improvement in MAPE for The Weather Company forecasts relative to the ERCOT-issued forecasts, using the 7 AM forecasts 6
8 Conclusions The Weather Company has recently developed a new load forecasting module that has consistently exhibited lower errors than the freely-available ERCOT forecasts over the past year. The combination of best-in-class, hourly-updating weather forecasts at 4 km spatial resolution, and expertise/experience in machine learning techniques has allowed Weather to make this exciting new leap into the load forecasting arena. The Weather Company forecast errors for the ERCOT region range from 2% during the first three days of the forecast to 4-5% by day 9. Errors are particularly low during the first 18 hours of the forecast, both in absolute terms and relative to the ERCOT-issued forecasts, when The Weather Company s forward-correction algorithm provides significant added value by intelligently incorporating recent load observations. There is little seasonal variation of forecast errors during the first six days of the forecast, but errors beyond that time are largest during the winter months, when temperature forecast errors are generally larger. Long-range errors during the summer are relatively low, on the other hand, since weather patterns are more stable and predictable during that season. 7
9 business.weather.com
Forecaster comments to the ORTECH Report
Forecaster comments to the ORTECH Report The Alberta Forecasting Pilot Project was truly a pioneering and landmark effort in the assessment of wind power production forecast performance in North America.
More informationCloud Model Verification at the Air Force Weather Agency
2d Weather Group Cloud Model Verification at the Air Force Weather Agency Matthew Sittel UCAR Visiting Scientist Air Force Weather Agency Offutt AFB, NE Template: 28 Feb 06 Overview Cloud Models Ground
More informationA system of direct radiation forecasting based on numerical weather predictions, satellite image and machine learning.
A system of direct radiation forecasting based on numerical weather predictions, satellite image and machine learning. 31st Annual International Symposium on Forecasting Lourdes Ramírez Santigosa Martín
More informationA simple scaling approach to produce climate scenarios of local precipitation extremes for the Netherlands
Supplementary Material to A simple scaling approach to produce climate scenarios of local precipitation extremes for the Netherlands G. Lenderink and J. Attema Extreme precipitation during 26/27 th August
More information4.3. David E. Rudack*, Meteorological Development Laboratory Office of Science and Technology National Weather Service, NOAA 1.
43 RESULTS OF SENSITIVITY TESTING OF MOS WIND SPEED AND DIRECTION GUIDANCE USING VARIOUS SAMPLE SIZES FROM THE GLOBAL ENSEMBLE FORECAST SYSTEM (GEFS) RE- FORECASTS David E Rudack*, Meteorological Development
More informationGuidelines on Quality Control Procedures for Data from Automatic Weather Stations
WORLD METEOROLOGICAL ORGANIZATION COMMISSION FOR BASIC SYSTEMS OPEN PROGRAMME AREA GROUP ON INTEGRATED OBSERVING SYSTEMS EXPERT TEAM ON REQUIREMENTS FOR DATA FROM AUTOMATIC WEATHER STATIONS Third Session
More informationProposals of Summer Placement Programme 2015
Proposals of Summer Placement Programme 2015 Division Project Title Job description Subject and year of study required A2 Impact of dual-polarization Doppler radar data on Mathematics or short-term related
More informationGuy Carpenter Asia-Pacific Climate Impact Centre, School of energy and Environment, City University of Hong Kong
Diurnal and Semi-diurnal Variations of Rainfall in Southeast China Judy Huang and Johnny Chan Guy Carpenter Asia-Pacific Climate Impact Centre School of Energy and Environment City University of Hong Kong
More informationTowards an NWP-testbed
Towards an NWP-testbed Ewan O Connor and Robin Hogan University of Reading, UK Overview Cloud schemes in NWP models are basically the same as in climate models, but easier to evaluate using ARM because:
More informationDaily High-resolution Blended Analyses for Sea Surface Temperature
Daily High-resolution Blended Analyses for Sea Surface Temperature by Richard W. Reynolds 1, Thomas M. Smith 2, Chunying Liu 1, Dudley B. Chelton 3, Kenneth S. Casey 4, and Michael G. Schlax 3 1 NOAA National
More informationCHAPTER 05 STRATEGIC CAPACITY PLANNING FOR PRODUCTS AND SERVICES
CHAPTER 05 STRATEGIC CAPACITY PLANNING FOR PRODUCTS AND SERVICES Solutions Actual output 7 1. a. Utilizatio n x100% 70.00% Design capacity 10 Actual output 7 Efficiency x100% 87.50% Effective capacity
More informationImproving Accuracy of Solar Forecasting February 14, 2013
Improving Accuracy of Solar Forecasting February 14, 2013 Solar Resource Forecasting Objectives: Improve accuracy of solar resource forecasts Enable widespread use of solar forecasts in power system operations
More informationWeather Normalization of Peak Load
Weather Normalization of Peak Load Load Analysis Subcommittee September 2, 2015 Issue PJM s current method of weather normalizing peak loads involves updating the peak load forecast model Revising the
More informationMARKETING ANALYTICS AS A SERVICE
MARKETING ANALYTICS AS A SERVICE WEATHER BASED CONTENT PERSONALIZATION Joseph A. Marr, Ph.D. Senior Principal Data Scientist SYNTASA Kirk D. Borne, Ph.D. Advisory Board Member SYNTASA MAY 2014 INTRODUCTION:
More informationShort-Term Forecasting in Retail Energy Markets
Itron White Paper Energy Forecasting Short-Term Forecasting in Retail Energy Markets Frank A. Monforte, Ph.D Director, Itron Forecasting 2006, Itron Inc. All rights reserved. 1 Introduction 4 Forecasting
More informationAnalysis of Climatic and Environmental Changes Using CLEARS Web-GIS Information-Computational System: Siberia Case Study
Analysis of Climatic and Environmental Changes Using CLEARS Web-GIS Information-Computational System: Siberia Case Study A G Titov 1,2, E P Gordov 1,2, I G Okladnikov 1,2, T M Shulgina 1 1 Institute of
More informationSeeing by Degrees: Programming Visualization From Sensor Networks
Seeing by Degrees: Programming Visualization From Sensor Networks Da-Wei Huang Michael Bobker Daniel Harris Engineer, Building Manager, Building Director of Control Control Technology Strategy Development
More informationCHAPTER 11 FORECASTING AND DEMAND PLANNING
OM CHAPTER 11 FORECASTING AND DEMAND PLANNING DAVID A. COLLIER AND JAMES R. EVANS 1 Chapter 11 Learning Outcomes l e a r n i n g o u t c o m e s LO1 Describe the importance of forecasting to the value
More informationHong Kong Observatory Summer Placement Programme 2015
Annex I Hong Kong Observatory Summer Placement Programme 2015 Training Programme : An Observatory mentor with relevant expertise will supervise the students. Training Period : 8 weeks, starting from 8
More informationTemperature and Humidity
Temperature and Humidity Overview Water vapor is a very important gas in the atmosphere and can influence many things like condensation and the formation of clouds and rain, as well as how hot or cold
More information2016 ERCOT System Planning Long-Term Hourly Peak Demand and Energy Forecast December 31, 2015
2016 ERCOT System Planning Long-Term Hourly Peak Demand and Energy Forecast December 31, 2015 2015 Electric Reliability Council of Texas, Inc. All rights reserved. Long-Term Hourly Peak Demand and Energy
More informationROAD WEATHER AND WINTER MAINTENANCE
Road Traffic Technology ROAD WEATHER AND WINTER MAINTENANCE METIS SSWM WMi ROAD WEATHER STATIONS ADVANCED ROAD WEATHER INFORMATION SYSTEM MAINTENANCE DECISION SUPPORT SYSTEM WINTER MAINTENANCE PERFORMANCE
More informationAnalytics That Allow You To See Beyond The Cloud. By Alex Huang, Ph.D., Head of Aviation Analytics Services, The Weather Company, an IBM Business
Analytics That Allow You To See Beyond The Cloud By Alex Huang, Ph.D., Head of Aviation Analytics Services, The Weather Company, an IBM Business Table of Contents 3 Ways Predictive Airport Analytics Could
More informationTHE STRATEGIC PLAN OF THE HYDROMETEOROLOGICAL PREDICTION CENTER
THE STRATEGIC PLAN OF THE HYDROMETEOROLOGICAL PREDICTION CENTER FISCAL YEARS 2012 2016 INTRODUCTION Over the next ten years, the National Weather Service (NWS) of the National Oceanic and Atmospheric Administration
More information6.9 A NEW APPROACH TO FIRE WEATHER FORECASTING AT THE TULSA WFO. Sarah J. Taylor* and Eric D. Howieson NOAA/National Weather Service Tulsa, Oklahoma
6.9 A NEW APPROACH TO FIRE WEATHER FORECASTING AT THE TULSA WFO Sarah J. Taylor* and Eric D. Howieson NOAA/National Weather Service Tulsa, Oklahoma 1. INTRODUCTION The modernization of the National Weather
More informationTime-of-use tariffs in the Eskom Western region
Time-of-use tariffs in the Eskom Western region by D Ramsbottom, Eskom This is a case study into the application of time of use tariffs in the Eskom Western Region undertaken to determine the effect that
More informationTemporal variation in snow cover over sea ice in Antarctica using AMSR-E data product
Temporal variation in snow cover over sea ice in Antarctica using AMSR-E data product Michael J. Lewis Ph.D. Student, Department of Earth and Environmental Science University of Texas at San Antonio ABSTRACT
More informationDesign and Deployment of Specialized Visualizations for Weather-Sensitive Electric Distribution Operations
Fourth Symposium on Policy and Socio-Economic Research 4.1 Design and Deployment of Specialized Visualizations for Weather-Sensitive Electric Distribution Operations Lloyd A. Treinish IBM, Yorktown Heights,
More information118358 SUPERENSEMBLE FORECASTS WITH A SUITE OF MESOSCALE MODELS OVER THE CONTINENTAL UNITED STATES
118358 SUPERENSEMBLE FORECASTS WITH A SUITE OF MESOSCALE MODELS OVER THE CONTINENTAL UNITED STATES Donald F. Van Dyke III * Florida State University, Tallahassee, Florida T. N. Krishnamurti Florida State
More informationActivity 1 Reading Universal Time Level 2 http://www.uni.edu/storm/activities/level2/index.shtml
Activity 1 Reading Universal Time Level 2 http://www.uni.edu/storm/activities/level2/index.shtml National Science Education Standards: As a result of activities in grades 5-8, all students should develop
More informationCloud verification: a review of methodologies and recent developments
Cloud verification: a review of methodologies and recent developments Anna Ghelli ECMWF Slide 1 Thanks to: Maike Ahlgrimm Martin Kohler, Richard Forbes Slide 1 Outline Cloud properties Data availability
More information2.8 Objective Integration of Satellite, Rain Gauge, and Radar Precipitation Estimates in the Multisensor Precipitation Estimator Algorithm
2.8 Objective Integration of Satellite, Rain Gauge, and Radar Precipitation Estimates in the Multisensor Precipitation Estimator Algorithm Chandra Kondragunta*, David Kitzmiller, Dong-Jun Seo and Kiran
More informationBIG Data Analytics Move to Competitive Advantage
BIG Data Analytics Move to Competitive Advantage where is technology heading today Standardization Open Source Automation Scalability Cloud Computing Mobility Smartphones/ tablets Internet of Things Wireless
More information2014 Forecasting Benchmark Survey. Itron, Inc. 12348 High Bluff Drive, Suite 210 San Diego, CA 92130-2650 858-724-2620
Itron, Inc. 12348 High Bluff Drive, Suite 210 San Diego, CA 92130-2650 858-724-2620 September 16, 2014 For the third year, Itron surveyed energy forecasters across North America with the goal of obtaining
More informationPartnership to Improve Solar Power Forecasting
Partnership to Improve Solar Power Forecasting Venue: EUPVSEC, Paris France Presenter: Dr. Manajit Sengupta Date: October 1 st 2013 NREL is a national laboratory of the U.S. Department of Energy, Office
More informationProbabilistic forecast information optimised to end-users applications: three diverse examples
Probabilistic forecast information optimised to end-users applications: three diverse examples ECMWF User Seminar 2015 Vanessa Stauch, Renate Hagedorn, Isabel Alberts, Reik Schaab Our group Land Transport
More informationUser Perspectives on Project Feasibility Data
User Perspectives on Project Feasibility Data Marcel Šúri Tomáš Cebecauer GeoModel Solar s.r.o., Bratislava, Slovakia marcel.suri@geomodel.eu http://geomodelsolar.eu http://solargis.info Solar Resources
More informationSavant Systems LLC Technical Application Note How to Guide: HVAC Scheduling Setup
Savant Systems LLC Technical Application Note How to Guide: HVAC Scheduling Setup Technical Description: This document describes how to schedule HVAC services. The HVAC Schedule allows the end user to
More informationHow To Handle Big Data With A Data Scientist
III Big Data Technologies Today, new technologies make it possible to realize value from Big Data. Big data technologies can replace highly customized, expensive legacy systems with a standard solution
More informationNC STATE UNIVERSITY Exploratory Analysis of Massive Data for Distribution Fault Diagnosis in Smart Grids
Exploratory Analysis of Massive Data for Distribution Fault Diagnosis in Smart Grids Yixin Cai, Mo-Yuen Chow Electrical and Computer Engineering, North Carolina State University July 2009 Outline Introduction
More informationSolarstromprognosen für Übertragungsnetzbetreiber
Solarstromprognosen für Übertragungsnetzbetreiber Elke Lorenz, Jan Kühnert, Annette Hammer, Detlev Heienmann Universität Oldenburg 1 Outline grid integration of photovoltaic power (PV) in Germany overview
More informationPredicting Solar Generation from Weather Forecasts Using Machine Learning
Predicting Solar Generation from Weather Forecasts Using Machine Learning Navin Sharma, Pranshu Sharma, David Irwin, and Prashant Shenoy Department of Computer Science University of Massachusetts Amherst
More informationSouth Dakota Severe Weather Awareness Week April 22nd through 26th
National Weather Service Aberdeen, South Dakota April 2013 Inside this issue: Severe Weather Awareness Impact Based Warnings Impact Based Warnings (cont) Record Cold March Record Cold March (cont) Seasonal
More informationClimate Extremes Research: Recent Findings and New Direc8ons
Climate Extremes Research: Recent Findings and New Direc8ons Kenneth Kunkel NOAA Cooperative Institute for Climate and Satellites North Carolina State University and National Climatic Data Center h#p://assessment.globalchange.gov
More informationIMPACT OF SAINT LOUIS UNIVERSITY-AMERENUE QUANTUM WEATHER PROJECT MESONET DATA ON WRF-ARW FORECASTS
IMPACT OF SAINT LOUIS UNIVERSITY-AMERENUE QUANTUM WEATHER PROJECT MESONET DATA ON WRF-ARW FORECASTS M. J. Mueller, R. W. Pasken, W. Dannevik, T. P. Eichler Saint Louis University Department of Earth and
More informationObserving the Changing Relationship Between Natural Gas Prices and Power Prices
Observing the Changing Relationship Between Natural Gas Prices and Power Prices The research views expressed herein are those of the author and do not necessarily represent the views of the CME Group or
More informationSolution-Driven Integrated Learning Paths. Make the Most of Your Educational Experience. Live Learning Center
Solution-Driven Integrated Learning Paths Educational Sessions Lean Global Supply Chain Basics of Operation Management Demand Management, Forecasting, and S & OP Professional Advancement Special Interest
More informationPredicting daily incoming solar energy from weather data
Predicting daily incoming solar energy from weather data ROMAIN JUBAN, PATRICK QUACH Stanford University - CS229 Machine Learning December 12, 2013 Being able to accurately predict the solar power hitting
More informationProcurement Category: Energy. Energy Market Forces: Friend or Foe?
Procurement Category: Energy Energy Market Forces: Friend or Foe? As dynamic energy pricing becomes more prevalent in the industry, multi-site organizations are presented with new challenges, as well as
More informationI D C A N A L Y S T C O N N E C T I O N. C o g n i t i ve C o m m e r c e i n B2B M a rketing a n d S a l e s
I D C A N A L Y S T C O N N E C T I O N Dave Schubmehl Research Director, Cognitive Systems and Content Analytics Greg Girard Program Director, Omni-Channel Retail Analytics Strategies C o g n i t i ve
More informationOhio Edison, Cleveland Electric Illuminating, Toledo Edison Load Profile Application
Ohio Edison, Cleveland Electric Illuminating, Toledo Edison Load Profile Application I. General The Company presents the raw equations utilized in process of determining customer hourly loads. These equations
More informationNowcasting: analysis and up to 6 hours forecast
Nowcasting: analysis and up to 6 hours forecast Very high resoultion in time and space Better than NWP Rapid update Application oriented NWP problems for 0 6 forecast: Incomplete physics Resolution space
More informationFinancing Community Wind
Financing Community Wind Wind Data and Due Diligence What is the Project's Capacity Factor? Community Wind Energy 2006 March 8, 2006 Mark Ahlstrom mark@windlogics.com Slide 1 The Need for Wind Assessment
More informationEvaluating Predictive Analytics for Capacity Planning. HIC 2015 Andrae Gaeth
Evaluating Predictive Analytics for Capacity Planning HIC 2015 Andrae Gaeth What is predictive analytics? Predictive analytics is the practice of extracting information from existing data sets, and then
More informationWhy is Internal Audit so Hard?
Why is Internal Audit so Hard? 2 2014 Why is Internal Audit so Hard? 3 2014 Why is Internal Audit so Hard? Waste Abuse Fraud 4 2014 Waves of Change 1 st Wave Personal Computers Electronic Spreadsheets
More informationDesign of a Weather- Normalization Forecasting Model
Design of a Weather- Normalization Forecasting Model Project Proposal Abram Gross Yafeng Peng Jedidiah Shirey 2/11/2014 Table of Contents 1.0 CONTEXT... 3 2.0 PROBLEM STATEMENT... 4 3.0 SCOPE... 4 4.0
More informationService Suite for Communications Mobile workforce management solutions
Service Suite for Communications Mobile workforce management solutions No other mobile workforce management provider knows the communications industry like ABB. That s why ABB has become one of the leading
More informationREGIONAL CLIMATE AND DOWNSCALING
REGIONAL CLIMATE AND DOWNSCALING Regional Climate Modelling at the Hungarian Meteorological Service ANDRÁS HORÁNYI (horanyi( horanyi.a@.a@met.hu) Special thanks: : Gabriella Csima,, Péter Szabó, Gabriella
More informationDevelopment of a. Solar Generation Forecast System
ALBANY BARCELONA BANGALORE 16 December 2011 Development of a Multiple Look ahead Time Scale Solar Generation Forecast System John Zack Glenn Van Knowe Marie Schnitzer Jeff Freedman AWS Truepower, LLC Albany,
More informationMOGREPS status and activities
MOGREPS status and activities by Warren Tennant with contributions from Rob Neal, Sarah Beare, Neill Bowler & Richard Swinbank Crown copyright Met Office 32 nd EWGLAM and 17 th SRNWP meetings 1 Contents
More informationInternational Journal of Advanced Engineering Research and Applications (IJAERA) ISSN: 2454-2377 Vol. 1, Issue 6, October 2015. Big Data and Hadoop
ISSN: 2454-2377, October 2015 Big Data and Hadoop Simmi Bagga 1 Satinder Kaur 2 1 Assistant Professor, Sant Hira Dass Kanya MahaVidyalaya, Kala Sanghian, Distt Kpt. INDIA E-mail: simmibagga12@gmail.com
More informationFinal report on RAD service chain evolution
MACC-II Deliverable D_122.5 Final report on RAD service chain evolution Date: 07/2014 Lead Beneficiary: DLR (#11) Nature: R Dissemination level: PP Grant agreement n 283576 2 / 9 Table of Contents 1. Hardware
More informationProject Title: Quantifying Uncertainties of High-Resolution WRF Modeling on Downslope Wind Forecasts in the Las Vegas Valley
University: Florida Institute of Technology Name of University Researcher Preparing Report: Sen Chiao NWS Office: Las Vegas Name of NWS Researcher Preparing Report: Stanley Czyzyk Type of Project (Partners
More informationREDUCING UNCERTAINTY IN SOLAR ENERGY ESTIMATES
REDUCING UNCERTAINTY IN SOLAR ENERGY ESTIMATES Mitigating Energy Risk through On-Site Monitoring Marie Schnitzer, Vice President of Consulting Services Christopher Thuman, Senior Meteorologist Peter Johnson,
More informationCoffee prices fall but Brazilian production estimated lower
Coffee prices fall but production estimated lower Coffee prices continued their decline as speculation over the current 2015/16 crop suggests that the market has no immediate supply concerns. Indeed, one
More informationFire Weather Index: from high resolution climatology to Climate Change impact study
Fire Weather Index: from high resolution climatology to Climate Change impact study International Conference on current knowledge of Climate Change Impacts on Agriculture and Forestry in Europe COST-WMO
More informationProviding drivers with actionable intelligence can minimize accidents, reduce driver claims and increase your bottom line. Equip motorists with the
Providing drivers with actionable intelligence can minimize accidents, reduce driver claims and increase your bottom line. Equip motorists with the ability to make informed decisions based on reliable,
More informationMode-S Enhanced Surveillance derived observations from multiple Air Traffic Control Radars and the impact in hourly HIRLAM
Mode-S Enhanced Surveillance derived observations from multiple Air Traffic Control Radars and the impact in hourly HIRLAM 1 Introduction Upper air wind is one of the most important parameters to obtain
More informationIBM Big Green Innovations Environmental R&D and Services
IBM Big Green Innovations Environmental R&D and Services Smart Weather Modelling Local Area Precision Forecasting for Weather-Sensitive Business Operations (e.g. Smart Grids) Lloyd A. Treinish Project
More informationNear Real Time Blended Surface Winds
Near Real Time Blended Surface Winds I. Summary To enhance the spatial and temporal resolutions of surface wind, the remotely sensed retrievals are blended to the operational ECMWF wind analyses over the
More informationMaximization versus environmental compliance
Maximization versus environmental compliance Increase use of alternative fuels with no risk for quality and environment Reprint from World Cement March 2005 Dr. Eduardo Gallestey, ABB, Switzerland, discusses
More informationEXPLANATION OF WEATHER ELEMENTS AND VARIABLES FOR THE DAVIS VANTAGE PRO 2 MIDSTREAM WEATHER STATION
EXPLANATION OF WEATHER ELEMENTS AND VARIABLES FOR THE DAVIS VANTAGE PRO 2 MIDSTREAM WEATHER STATION The Weather Envoy consists of two parts: the Davis Vantage Pro 2 Integrated Sensor Suite (ISS) and the
More informationAlgorithmic Trading Session 1 Introduction. Oliver Steinki, CFA, FRM
Algorithmic Trading Session 1 Introduction Oliver Steinki, CFA, FRM Outline An Introduction to Algorithmic Trading Definition, Research Areas, Relevance and Applications General Trading Overview Goals
More informationFrom Raw Data to. Actionable Insights with. MATLAB Analytics. Learn more. Develop predictive models. 1Access and explore data
100 001 010 111 From Raw Data to 10011100 Actionable Insights with 00100111 MATLAB Analytics 01011100 11100001 1 Access and Explore Data For scientists the problem is not a lack of available but a deluge.
More informationUsing the HP Vertica Analytics Platform to Manage Massive Volumes of Smart Meter Data
Technical white paper Using the HP Vertica Analytics Platform to Manage Massive Volumes of Smart Meter Data The Internet of Things is expected to connect billions of sensors that continuously gather data
More informationSolar Input Data for PV Energy Modeling
June 2012 Solar Input Data for PV Energy Modeling Marie Schnitzer, Christopher Thuman, Peter Johnson Albany New York, USA Barcelona Spain Bangalore India Company Snapshot Established in 1983; nearly 30
More informationMonsoon Variability and Extreme Weather Events
Monsoon Variability and Extreme Weather Events M Rajeevan National Climate Centre India Meteorological Department Pune 411 005 rajeevan@imdpune.gov.in Outline of the presentation Monsoon rainfall Variability
More informationClimate Data and Information: Issues and Uncertainty
Climate Data and Information: Issues and Uncertainty David Easterling NOAA/NESDIS/National Climatic Data Center Asheville, North Carolina, U.S.A. 1 Discussion Topics Climate Data sets What do we have besides
More informationPlease see the Seasonal Changes module description.
Overview Children will measure and graph the precipitation on the playground throughout the year using a rain gauge. Children will also observe satellite images of clouds and begin to investigate how clouds
More informationWater Demand Forecast Approach
CHAPTER 6 2009 REGIONAL WATER SUPPLY OUTLOOK Water Demand Forecast Approach 6.1 Introduction Long-range water demand forecasting is a fundamental tool that water utilities use to assure that they can meet
More informationA Forecasting Decision Support System
A Forecasting Decision Support System Hanaa E.Sayed a, *, Hossam A.Gabbar b, Soheir A. Fouad c, Khalil M. Ahmed c, Shigeji Miyazaki a a Department of Systems Engineering, Division of Industrial Innovation
More informationShort-term solar energy forecasting for network stability
Short-term solar energy forecasting for network stability Dependable Systems and Software Saarland University Germany What is this talk about? Photovoltaic energy production is an important part of the
More informationCustomer Relationship Management
IBM Global Business Services CRM Customer Relationship Management Solutions from IBM Global Business Services Do you really know your customers? How do they like to interact with you? How do they use your
More informationA verification score for high resolution NWP: Idealized and preoperational tests
Technical Report No. 69, December 2012 A verification score for high resolution NWP: Idealized and preoperational tests Bent H. Sass and Xiaohua Yang HIRLAM - B Programme, c/o J. Onvlee, KNMI, P.O. Box
More informationBasics of weather interpretation
Basics of weather interpretation Safety at Sea Seminar, April 2 nd 2016 Dr. Gina Henderson Oceanography Dept., USNA ghenders@usna.edu Image source: http://earthobservatory.nasa.gov/naturalhazards/view.php?id=80399,
More informationBig Data in Transportation Engineering
Big Data in Transportation Engineering Nii Attoh-Okine Professor Department of Civil and Environmental Engineering University of Delaware, Newark, DE, USA Email: okine@udel.edu IEEE Workshop on Large Data
More informationTHE HUMIDITY/MOISTURE HANDBOOK
THE HUMIDITY/MOISTURE HANDBOOK Table of Contents Introduction... 3 Relative Humidity... 3 Partial Pressure... 4 Saturation Pressure (Ps)... 5 Other Absolute Moisture Scales... 8 % Moisture by Volume (%M
More informationNOAA to Provide Enhanced Frost Forecast Information to Improve Russian River Water Management
NOAA to Provide Enhanced Frost Forecast Information to Improve Russian River Water Management David W. Reynolds Meteorologist in Charge (Retired) National Weather Service Forecast Office San Francisco
More informationAn Overview of the Convergence of BI & BPM
An Overview of the Convergence of BI & BPM Rich Zaziski, CEO FYI Business Solutions Richz@fyisolutions.com OBJECTIVE To provide an overview of the convergence of Business Intelligence (BI) and Business
More informationIRG-Rail (13) 2. Independent Regulators Group Rail IRG Rail Annual Market Monitoring Report
IRG-Rail (13) 2 Independent Regulators Group Rail IRG Rail Annual Market Monitoring Report February 2013 Index 1 Introduction...3 2 Aim of the report...3 3 Methodology...4 4 Findings...5 a) Market structure...5
More informationSAVE POD AND FAR Normalization for Event Frequency in Performance Metrics (IFR Example)
SAVE POD AND FAR Normalization for Event Frequency in Performance Metrics (IFR Example) Matthew Lorentson August 2015 1 High Points POD and FAR must not be used individually to summarize performance Performance
More informationPlanning Demand For Profit-Driven Supply Chains
Demand Planning for Profit-Driven Supply Chains epaper / Adexa Common epaper Series Pitfalls in Supply Chain System Implementations Author: William H. Green Planning Demand For Profit-Driven Supply Chains
More informationUSING BIG DATA FOR OPERATIONS & ENERGY MANAGEMENT IN HOSPITALITY
www.wiproecoenergy.com USING BIG DATA FOR OPERATIONS & ENERGY MANAGEMENT IN HOSPITALITY ANALYZE. ACHIEVE. ACCELERATE Table of Content 03... Abstract 04... Need for Operational & Energy Efficiency 04...
More informationBetter planning and forecasting with IBM Predictive Analytics
IBM Software Business Analytics SPSS Predictive Analytics Better planning and forecasting with IBM Predictive Analytics Using IBM Cognos TM1 with IBM SPSS Predictive Analytics to build better plans and
More informationExpressing a complex world in terms you can understand
Big Data Simplified Expressing a complex world in terms you can understand Information Management has never been easy. Making sure information is modeled, trusted, integrated, and governed to meet the
More informationDemand Management Where Practice Meets Theory
Demand Management Where Practice Meets Theory Elliott S. Mandelman 1 Agenda What is Demand Management? Components of Demand Management (Not just statistics) Best Practices Demand Management Performance
More informationERCOT Monthly Operational Overview (March 2014) ERCOT Public April 15, 2014
ERCOT Monthly Operational Overview (March 2014) ERCOT Public April 15, 2014 Grid Operations & Planning Summary March 2014 Operations The peak demand of 54,549 MW on March 3 rd was greater than the mid-term
More informationBig Data Analytics and its Impact on Supply Chain Management
Big Data Analytics and its Impact on Supply Chain Management Dr. Mahesh Ramamani Management Consultant, Business Analytics & Strategy IBM India July 2015, CII Conference on Redefining Supply Chain in the
More informationHuai-Min Zhang & NOAAGlobalTemp Team
Improving Global Observations for Climate Change Monitoring using Global Surface Temperature (& beyond) Huai-Min Zhang & NOAAGlobalTemp Team NOAA National Centers for Environmental Information (NCEI) [formerly:
More information