Scribd Logo
Carica

Benvenuto in Scribd!

  • Load & Price Forecasting Webinar Slides Australia

    Caricato da

    reza
    57 visualizzazioni20 pagine
    This example demonstrates building a short term electricity load (or price) forecasting system with MATLAB. Two non-linear regression models (Neural Networks and Bagged Regression Trees) are calibrated to forecast hourly day-ahead loads given temperature forecasts, holiday information and historical loads. The models are trained on hourly data from the NEPOOL region (courtesy ISO New England) from 2004 to 2007 and tested on out-of-sample data from 2008. The models are shown to produce highly accurate day-ahead forecasts with average errors around 1-2%. The demo includes publishable reports as well as an Excel front end which enables users to call the trained load forecasting models through a MATLAB-deployed DLL.

    Copyright

    © © All Rights Reserved

    Formati disponibili

    PDF, TXT o leggi online da Scribd

    Hai trovato utile questo documento?

    Questo contenuto è inappropriato?

    Segnala questo documento
    This example demonstrates building a short term electricity load (or price) forecasting system with MATLAB. Two non-linear regression models (Neural Networks and Bagged Regression Trees) are calibrated to forecast hourly day-ahead loads given temperature forecasts, holiday information and historical loads. The models are trained on hourly data from the NEPOOL region (courtesy ISO New England) from 2004 to 2007 and tested on out-of-sample data from 2008. The models are shown to produce highly accurate day-ahead forecasts with average errors around 1-2%. The demo includes publishable reports as well as an Excel front end which enables users to call the trained load forecasting models through a MATLAB-deployed DLL.

    Copyright:

    © All Rights Reserved
    Scarica in formato PDF, TXT o leggi online su Scribd
    Segnala contenuti inappropriati
    57 visualizzazioni20 pagine

    Load & Price Forecasting Webinar Slides Australia

    Caricato da

    reza
    This example demonstrates building a short term electricity load (or price) forecasting system with MATLAB. Two non-linear regression models (Neural Networks and Bagged Regression Trees) are calibrated to forecast hourly day-ahead loads given temperature forecasts, holiday information and historical loads. The models are trained on hourly data from the NEPOOL region (courtesy ISO New England) from 2004 to 2007 and tested on out-of-sample data from 2008. The models are shown to produce highly accurate day-ahead forecasts with average errors around 1-2%. The demo includes publishable reports as well as an Excel front end which enables users to call the trained load forecasting models through a MATLAB-deployed DLL.

    Copyright:

    © All Rights Reserved
    Scarica in formato PDF, TXT o leggi online su Scribd
    Segnala contenuti inappropriati
    di 20

    Electricity Load & Price Forecasting for

    the Australian Market

    David Willingham
    david.willingham@mathworks.com.au

    2011 The MathWorks, Inc.1

    The Need for Accurate Load & Price Forecasts

    Utilities

    System Operators

    Generators

    Power Marketers

    Case Study: Short-term Load Forecaster

    Goal:
    Implement a tool for easy and accurate computation of dayahead system load forecast

    Requirements:
    Accurate predictive model
    Automated Report

    Challenges in Implementing a Load & Price Forecasting System

    Traditional Approaches

    Challenges

    Off-the-shelf software

    Inability to customize

    Third-party consulting

    Lack of transparency

    In-house development with


    traditional languages

    Long development time


    4

    Case Study: Short-term Load Forecaster

    Goal:
    Implement a tool for easy and accurate computation of dayahead system load forecast

    Requirements:
    Accurate predictive model
    Automated Report

    Model Architecture

    Step 1: Access Historical Data


    Step 2: Select & Calibrate Model
    Step 3: Run Model Live
    Forecast Inputs
    Temperature Forecast
    Previous Loads

    Weather
    Dry Bulb
    Dew Point

    Seasonality
    Hour, Weekday
    Holidays

    Historical Load
    Previous Day
    Previous Week

    Calibration
    Neural Networks
    Time Series
    Fuzzy Logic
    Regression Trees

    Forecasting
    Model

    Forecaster

    Load
    Forecast
    Calibration
    Report

    Model Development Workflow


    Access

    Research and Quantify

    Files

    Share
    Reporting

    Data Analysis
    & Visualization

    Databases

    Datafeeds

    Model
    Development

    Application
    Development

    Applications

    Production

    Automate
    7

    Modeling Tasks
    Step 1: Access Historical Data
    Step 2: Select & Calibrate Model
    Step 3: Published Report

    Modeling Tasks
    Step 1: Access Historical Data
    Temperature data from BOM (Bureau of Meteorology)
    Load and Price (RRP) data from AEMO
    Step 2: Select & Calibrate Model
    Step 3: Published Report

    Modeling Tasks
    Step 1: Access Historical Data
    Temperature data from BOM (Bureau of Meteorology)
    Load and Price (RRP) data from AEMO
    Step 2: Select & Calibrate Model
    Step 3: Published Report

    10

    Modeling Tasks
    Step 1: Access Historical Data
    Temperature data from BOM (Bureau of Meteorology)
    Load and Price (RRP) data from AEMO
    Step 2: Select & Calibrate Model
    Leverage numerous built-in functions
    Focus on modeling not programming
    Capture as-you-go and automate the process
    Step 3: Published Report

    11

    Modeling Tasks
    Step 1: Access Historical Data
    Temperature data from BOM (Bureau of Meteorology)
    Load and Price (RRP) data from AEMO
    Step 2: Select & Calibrate Model
    Leverage numerous built-in functions
    Focus on modeling not programming
    Capture as-you-go and automate the process
    Step 3: Published Report

    12

    Modeling Tasks
    Step 1: Access Historical Data
    Temperature data from BOM (Bureau of Meteorology)
    Load and Price (RRP) data from AEMO
    Step 2: Select & Calibrate Model
    Leverage numerous built-in functions
    Focus on modeling not programming
    Capture as-you-go and automate the process
    Step 3: Published Report
    Point-and-click publishing
    13

    Forecasting Electricity Loads

    Forecast Inputs
    Temperature Forecast
    Previous Loads

    Weather
    Dry Bulb
    Dew Point

    Seasonality
    Hour, Weekday
    Holidays

    Calibration

    Forecasting
    Model

    Forecaster

    Load
    Forecast

    Historical Load
    Previous Day
    Previous Week

    14

    Forecasting Electricity Prices

    Forecast Inputs

    Fuel Prices

    Temperature Forecast

    Nat. Gas Price


    Coal Price

    Previous Loads, Fuel


    & Power Prices

    Weather
    Dry Bulb
    Dew Point

    Seasonality
    Hour, Weekday
    Holidays

    Calibration

    Forecasting
    Model

    Forecaster

    Price
    Forecast

    Historical Load
    Previous Day
    Previous Week

    Power Prices
    Previous Day
    Previous Week

    15

    Other considerations:

    Pre Processing Data


    Batch importing
    Cleaning
    Deployment
    Stand Alone Application
    Excel Add In
    Java, .NET

    16

    MATLAB Solutions

    Traditional Approaches

    Challenges

    Off-the-shelf software

    Inability to customize

    Third-party consulting

    Lack of transparency

    In-house development with


    traditional languages

    Long development time

    17

    MATLAB Solutions

    Challenges

    Solutions

    Inability to customize

    Flexible modeling

    Lack of transparency

    White-box modeling

    Long development time

    Complete development environment


    Libraries of customizable functions

    Viewable-source functions
    Interactive debugging

    Quick prototyping

    Focus on modeling not programming


    Point-and-click deployment
    18

    Additional Resources

    Recorded webinars:
    Energy Load & Price Forecasting (US Version)

    Energy Trading & Risk Management


    and other recorded webinars, at mathworks.com.au/events

    User stories:
    Horizon Wind Energy Develops Revenue Forecasting and Risk Analysis
    Tools for Wind Farms
    GAS NATURAL FENOSA Predicts Energy Supply and Demand Using
    MathWorks Tools
    and others, at http://mathworks.com/energy-production
    19

    Questions?
    My Email:
    david.willingham@mathworks.com.au

    2011 The MathWorks, Inc.


    20

    Potrebbero piacerti anche