Using Historical Data To Fine-Tune AURORAxmp Predictive Capabilities
0 likes178 views
The document discusses enhancing the predictive capabilities of the Aurora forecasting tool through historical data analysis and various metrics. It emphasizes the importance of reliable data and infrastructure, suggesting multiple key inputs and metrics for comparison. Additionally, it highlights challenges in backcasting and data management related to energy market behavior.
Using Historical Data To Fine-Tune AURORAxmp Predictive Capabilities
- 1. Using Historical Data to Fine- tune Aurora Predictive Capability and Gain Insights into Market Behavior Chris Handwerk and Derek Salvino October 16, 2009
- 2. Motivation Models are great at giving insights, but are only as good as: Their capabilities The data that you feed into them AURORAxmp® is an excellent power price forecasting tool, with lots of advanced and detailed functionality. Like a fine racing car, it needs to be tuned up before it can be used to race competitively How do we gain confidence in the model? 1
- 3. Data 2 http://blogs.smh.com.au/radar/flabbycover.jpg Having reliable and accurate data is essential Data infrastructure and organization is key http://celebrity-babies.com/2007/09/09/tina-fey-and-da/
- 4. Key Input Data (SFELT) 3 Stack (generation characteristics) Fuels EmissionsLoad Transmission
- 5. Data sources EPIS database Excellent for resource constrained organizations Publicly available CEMS (Continuous Emissions Monitoring System - EPA) FERC Forms EIA ISO Proprietary sources Energy Velocity Platt’s SNL IIR (Industrial Information Resources) 4
- 6. Suggested Metrics for Comparison – Stack Matching 5
- 7. Suggested Metrics for Comparison – Unit Operation 6
- 8. Suggested Metrics for Comparison – Transmission Flows 7
- 9. Suggested Metrics for Comparison – Zonal LMP (basis) 8
- 10. Zonal LMP challenges in Aurora zonal Marginal cost of marginal unit Bid adder of marginal unit LMP Energy Congestion Loss Energy Between zone loss and congestion Within zone loss and congestion Between zone loss and congestion Within Aurora 9
- 11. Things worth investigating Generator characteristics Start-up costs Ramp rates # of bidding segments (upper bidding block) Emissions (seasonality) Outage behavior Minimum uptimes/downtimes Reliability Must Run (RMR) Transmission link limits/wheeling charges Fuel costs – burner tip v. market price 10
- 12. Backcasting challenges How close is good enough? Transmission Financial v. physical behavior Behavior of border regions Incorporating regulatory considerations Data management and availability Resources 11
- 13. 12 Finely tuning your racing car will put you in the winner’s circle! http://www.autobahnmag.com/wp-content/uploads/2009/05/59b48c3fd7circle.jpg