Briefing on day-ahead load forecasting Amber Motley, Manager Short - PowerPoint PPT Presentation

Apr 01, 2024 •47 likes •137 views

Briefing on day-ahead load forecasting Amber Motley, Manager Short Term Forecasting Board of Governors Meeting General Session November 14, 2018 Load forecast accuracy improved 10% in 2018 CAISO Day Ahead Mean Absolute Percent Error

Briefing on day-ahead load forecasting Amber Motley, Manager – Short Term Forecasting Board of Governors Meeting General Session November 14, 2018
Load forecast accuracy improved 10% in 2018 CAISO Day Ahead Mean Absolute Percent Error (MAPE) CAISO Day Ahead MAPE 2.5% 2.5% Forecast improvement observed in Q1 and Q2 2018 2.0% 2.0% 1.5% 1.5% MAPE MAPE MAPE MAPE 1.0% 1.0% 0.5% 0.5% 0.0% 0.0% Q1 Q1 Q2 Q2 Q3 Q3 Q4 Q4 2013 2014 2015 2016 2017 2018 2013 2014 2015 2016 2017 Page 2
Analysis of load forecast error looked at the following: • Effect of behind the meter resource production • Underlying temperature / weather forecast • Regional forecast granularity / micro climate effects • Machine learning model tuning parameter • Manual adjustments Page 3
Hourly error increases in middle of day due to effects of increasing behind the meter production on mid-day load. Page 4
Average MW behind the meter error varies significantly by Quarter in 2017. Page 5
During Q1, Q2, and Q4 ISO forecasts are driven by cloud cover Quarter Page 6
There is a difference between ground measured irradiance and satellite interpolated actuals in 2017. Quarter Page 7
Conclusion of analysis • Load forecast accuracy is most impacted by cloud cover variability effects on 7,000MW of behind-the-meter capacity during Q1, Q2, and Q4. • New forecast techniques are needed to support the magnitude and changes to behind-the-meter resource capacity. • Improved visibility into the actual aggregate behind-the-meter production is needed to improve calibration of forecast models Page 8
Work plan of next steps Task Estimated Schedule Regional Breakout End of 2018 Incorporate Behind the Meter Actuals June 30, 2019 Re-assess BTM Forecast Provider June 30, 2019 Modeling Environment TBD; working with IT Multiple Models TBD; working with IT Appropriate Blending Options TBD; working with Vendor Probabilistic Forecasting TBD working with DOE Sponsored Research Project Continuously researching best Develop new forecasting approaches practices & new techniques Page 9

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

CPUC Track III Resource Adequacy Workshop March 12-13, 2019 Day 1 Load Forecasting Proposals

CPUC Track III Resource Adequacy Workshop March 12-13, 2019 Day 1 Load Forecasting Proposals and Discussion Timeline MID MAR LSEs report hourly usage from previous year to CEC LATE APR LSEs submit initial year-ahead load forecasts to CEC

380 views • 7 slides

Long-term electric load Why Forecast Electric Load forecasting is necessary so that Decisions on

Presentation To City Council March, 2 2020 by J.R. Windsor Slide 1 Electric Load Forecasting Jim Windsor Retired Assistant Director of Utilities Slide 2 Long-term electric load Why Forecast Electric Load forecasting is necessary so that

238 views • 5 slides

CDM Forecasting Initiative Stan But March 22, 2011 Manager, Economics & Load Forecasting 1

CDM Forecasting Initiative Stan But March 22, 2011 Manager, Economics & Load Forecasting 1 Key messages from February10, 2011 stakeholder session As recommended by stakeholders, a 3 rd party study on CDM impacts is not required

523 views • 13 slides

Electric lectrical al load forecasting load forecasting E using artificial neural using

Electric lectrical al load forecasting load forecasting E using artificial neural using artificial neural network kohonen kohonen network methode methode Galang Jiwo Syeto / EEPIS- Galang Jiwo Syeto / EEPIS -ITS ITS 7406.040.058

682 views • 31 slides

LOAD FORECASTING AND DEMAND SIDE MANAGEMENT Dr. G Garland La Laliberte Bipol ole III Co

LOAD FORECASTING AND DEMAND SIDE MANAGEMENT Dr. G Garland La Laliberte Bipol ole III Co Coalition Weather-Adjusted Historic and Forecast Gross Firm Energy before DSM, projected from 20-year historic data, GWh 35000 33000 31000 29000

426 views • 20 slides

Briefing on supply conditions Mark Rothleder VP, Market Quality & Renewable Integration EIM

Briefing on supply conditions Mark Rothleder VP, Market Quality & Renewable Integration EIM Governing Body Meeting General Session April 19, 2017 Actual net-load and 3-hour ramps are approximately 4 years ahead of the original estimate

461 views • 10 slides

ROBUST ONLINE AGGREGATION OF FORECASTS APPLICATION TO ELECTRICITY LOAD FORECASTING Pierre

ROBUST ONLINE AGGREGATION OF FORECASTS APPLICATION TO ELECTRICITY LOAD FORECASTING Pierre Gaillard October 21, 2015 University of Copenhagen T he framework of this talk Sequential prediction of arbitrary time-series based on expert forecasts:

555 views • 19 slides

High Needs Block Planning Ahead Prudent forecasting and early action High Needs has not

High Needs Block Planning Ahead Prudent forecasting and early action High Needs has not yet to overspent (nor has done for past 8 years) and might not this year Early forecasting carried out and action has been taken at an early

559 views • 10 slides

A Review of Manitoba Hydr os Electric Load Forecasting a 5 January 2018 presentation to the

A Review of Manitoba Hydr os Electric Load Forecasting a 5 January 2018 presentation to the Manitoba Public Utilities Board delivered by Dr. Garland Laliberte on behalf of the Bipole III Coalition in the matter of Manitoba Hydro s 2017-18

841 views • 24 slides

Distribution Forecasting Working Group Energy Storage Assumptions & Forecasts May 16, 2018 1

Distribution Forecasting Working Group Energy Storage Assumptions & Forecasts May 16, 2018 1 Background Energy storage operational assumptions and load impacts are important to overall load forecasting and distribution planning:

240 views • 13 slides

Forecasting the use, costs and benefits of HSR in the years ahead Samer Madanat UC Berkeley

Forecasting the use, costs and benefits of HSR in the years ahead Samer Madanat UC Berkeley Outline Demand models and ridership forecasts Errors in demand models and consequences Case study: the CA HSR Conclusion The

322 views • 20 slides

Probabilistic Models for One-Day Ahead Solar Irradiance Forecasting in Renewable Energy

Probabilistic Models for One-Day Ahead Solar Irradiance Forecasting in Renewable Energy Applications Carlos V. A. Silva, ICS Dept, University of Hawai`i at M noa Lipyeow Lim , ICS Dept, University of Hawai`i at M noa Duane Stevens, Atmo. Sc.

721 views • 23 slides

Welcome to Forecasting Using R Rob Hyndman Author, forecast Forecasting Using R What you will

FORECASTING USING R Welcome to Forecasting Using R Rob Hyndman Author, forecast Forecasting Using R What you will learn Exploring and visualizing time series Simple benchmark methods for forecasting Exponential smoothing and

715 views • 22 slides

Forecasting intraday-load curve using sparse learning methods Dominique Picard LPMA- Universit

Forecasting intraday-load curve using sparse learning methods Dominique Picard LPMA- Universit Paris-Diderot-Paris 7 Collaborators : Mathilde Mougeot UPD, Vincent Lefieux RTE, Laurence Maillard RTE Numerical methods for high dimensional

1.62k views • 94 slides

Machine Learning for Multi-step Ahead Forecasting of Volatility Proxies Jacopo De Stefani, Ir. -

Machine Learning for Multi-step Ahead Forecasting of Volatility Proxies Jacopo De Stefani, Ir. - jdestefa@ulb.ac.be Prof. Gianluca Bontempi - gbonte@ulb.ac.be Olivier Caelen, PhD - olivier.caelen@worldline.com Dalila Hattab, PhD -

537 views • 39 slides

Design of a Weather-Normalization Forecasting Model Final Briefing 09 May 2014 Abram Gross

Design of a Weather-Normalization Forecasting Model Final Briefing 09 May 2014 Abram Gross Sponsor: Jedidiah Shirey Northern Virginia Electric Cooperative Yafeng Peng OR-699 Agenda Methodology Background Excursions Problem

527 views • 24 slides

MIDN 1/C Warren Rooney Professor Svetlana Avramov-Zamurovic Find the beam from 1 camera

MIDN 1/C Warren Rooney Professor Svetlana Avramov-Zamurovic Find the beam from 1 camera location Determine propagation in xyz plane Extrapolate beam to find source Directed energy weapons of increased interest Necessary to find

326 views • 16 slides

I DAHO D EPARTMENT OF E NVIRONMENTAL QUALITY DEQ R ESPECTFULLY R EQUESTS The LBWC vote to

AQUATOX Model Calibration for the LBR TP TMDL Lower Boise Watershed Council March 13, 2014 I DAHO D EPARTMENT OF E NVIRONMENTAL QUALITY DEQ R ESPECTFULLY R EQUESTS The LBWC vote to support the AQUATOX model calibration

731 views • 31 slides

Puzzle on Graphs: Total Difference Labelings of Graphs Yufei Zhang Saint Marys College

Puzzle on Graphs: Total Difference Labelings of Graphs Yufei Zhang Saint Marys College Department of Math and Computer Science February 2, 2020 Yufei Zhang (Saint Marys College) Puzzle on Graphs: Total Difference Labelings of Graphs

183 views • 14 slides

U N I V O E T R O S Y I T K Y Kyoto Univ. 28

U N I V O E T R O S Y I T K Y Kyoto Univ. 28 , 2011. 1. 24, F KYOTO JAPAN 7 O 9 U 8 1 N D E D Progress

672 views • 37 slides

Stochastic Economic Dispatch for Power Stochastic Economic Dispatch for Power Grids with High

Stochastic Economic Dispatch for Power Stochastic Economic Dispatch for Power Grids with High Penetration of Wind Power Grids with High Penetration of Wind Power Ali Al Awami Awami Ali Al PhD Student PhD Student Department of Electrical

580 views • 40 slides

Section3.5 Solving Equations and Inequalities with Absolute Value AbsoluteValueEquations Method

Section3.5 Solving Equations and Inequalities with Absolute Value AbsoluteValueEquations Method To solve, put the equation into the standard form by isolating the absolute value on one side of the equation. It should look like | X | = c If c

80 views • 7 slides

OVERVIEW Wrote f firmware f for a an H n HP 2 20b c calc lcula lator, a , allo

OVERVIEW Wrote f firmware f for a an H n HP 2 20b c calc lcula lator, a , allo llowing ng i it t to d displa lay y user i input a and nd p process i inf nforma mation n Worked w with a h and nd u und nderstood

331 views • 13 slides

TEMPORARY ROAD SAFETY BARRIER SYSTEMS Julian Chisnall National Traffic & Safety Engineer

TEMPORARY ROAD SAFETY BARRIER SYSTEMS Julian Chisnall National Traffic & Safety Engineer Overview Performance and Specification (NZTA M23) Overview of available systems Selection criteria What Not To Do

477 views • 31 slides