Forecasting demand in the National Electricity Market. October 2017

Size: px
Start display at page:

Download "Forecasting demand in the National Electricity Market. October 2017"

Transcription

1 Forecasting demand in the National Electricity Market October 2017

2 Agenda

3 Trends in the National Electricity Market A review of AEMO s forecasting methods Long short-term memory (LSTM) neural networks Demand forecasting with LSTMs Final considerations

4 Trends in the National Electricity Market

5 Forecasting demand for electricity AEMO publishes forecasts for demand from as short as 5 minute intervals to long term horizons of 20 years. Long term forecasts of demand provide a basis for efficient network planning and for business investment decisions Short term forecasts of demand could help participants in the wholesale energy market make strategic bids or manage production to minimise risk / maximise profits. Scheduled 30min forecast and spot price for NSW Source: AEMO website AEMO Long term forecast for strong, weak and neutral economic and consumer outlooks Source: AEMO 2017 Energy Forecasting Insights

6 Long term forecast performance and implications In recent years, AEMO has made forecasts suggesting demand will continue to rise, which contributed to over-investment in network infrastructure. Meanwhile demand has continued to fall as rooftop solar adoption rises, appliances become more energy efficient and the manufacturing industry declines. Actual vs Forecast NEM demand Source: AEMO data Growth in Australian energy consumption 1961 to 2012 Source: BREE (2013)

7 Long term forecast performance and implications The result has been a continued in prices as a result of high network costs spread over a smaller consumption base. These recent changes to the dynamics of the energy market has rendered traditional forecasting techniques irrelevant and inaccurate, creating considerable future uncertainty Trends in electricity costs and consumption Source: Grattan (2013) Electricity price index compared with CPI Source: ABS (2013)

8 Short term forecast performance and implications In the shorter term, the network needs to be capable of coping with peak demand. Failure to do so can result in blackouts, which can destroy businesses and loss of life in extreme cases. Peak demand (which has also fallen) is typically driven by extreme weather events, triggering high air-conditioner (heaters in Tasmania) use at the same time as industry needs. Source: AEMO

9 An review of AEMO s forecasting methods

10 Econometric methods for long term forecasting AEMO has traditionally taken a top-down approach to developing long-term forecasts for key energy market measures (operational demand modelled using regression techniques; max and min demand are generated through weather simulations). These models are driven by factors such as economic activity, weather, income (as an indicator for air conditioner / heater usage) and electricity prices. Since 2014, they have shifted towards adopting a more bottom-up approach by including more granular data feeds (appliances, meters) beyond traditional grid measure such as bulk transmission data These models are segmented into residential and business with separate forecasts produced for shorter and longer term horizons

11 Neural networks for short term forecasting For their short term forecast of demand (5 minute), AEMO uses a neural network which was developed in 2014 (leveraging a 1997 model) It was chosen over other time series models (linear, moving average and spectral) for its ability relatively simply to incorporate nonlinear functional relationships The model uses the difference in the natural log of lags 5 time periods before, and 5 time periods a week ago Schematic diagram of load prediction neural network Predicted (X) vs Actual (Y) % change in demand for NSW Source: AEMO Source: AEMO

12 Neural networks for short term forecasting A December 2016 report prepared for the Australian Energy Market Commission by the University of Wollongong found that the neural network model was severely limited in capability: The model does not cope with contextual situations such as volatility, price responses or spikes in demand Advances in machine learning techniques since its development could provide a better alternative (current implementation is based off a 20 year old neural network) The report looks to experience in Germany where a neural network has been used for a 15 minute dispatch forecast Weather was found to be a useful inclusion for regional forecasts Inclusion of smart meter data also improved predictive accuracy Seasonality played a significant role in prediction accuracy (more so than climate) The strongest recommendation is to use a ensemble technique made up of a self-organising map (unsupervised learning) with a recurrent neural network to reduce the residual error of the SOM

13 Long Short-Term Memory Neural Networks

14 Recurrent neural networks (RNNs) RNNs are neural networks with loops, which distinguishes them from other neural network designs RNNs can be thought of as chain of the same network passing information to the next link. This chained structure lends itself to many sequence based applications, such as: Speech recognition (Google Translate, Amazon s Alexa, Siri), Text generation, Handwritten text recognition and generation, and Image captioning

15 Long Short-Term Memory (LSTM) networks One of the shortcomings of RNNs is their inability to connect relevant information to the point when it s needed as the gap between these two points grows. Clouds are in the predict[sky] The car arrived and waited outside. After ten minutes the driver turned off its predict[engine] LSTMs specifically address this issue of long term dependencies by changing the structure of its repeating layers to include a stream of information to flow through the chain. They also contain contextual long-term or short-term memory cells, that allow them to make predictions on historical context, in addition to recency. A series of gate structures help the network to learn when to remember information, and when to forget.

16 LSTMs using python, Tensorflow and Keras Tensorflow was released in early 2017 by Google as an open source machine learning library that can be used to build neural networks Released in 2015, Keras is higher level neural networks package for python It makes the assembly of neural networks easier, by creating a simplified interface for interacting with Tensorflow (and various other libraries)

17 Demand forecasting with LSTMs

18 Developing a LSTM for forecasting demand A LSTM neural network model has been trialled using historical demand and temperature data The data will be prepared as a series of sequences in multiple dimensions Using the 2016 calendar year for model development, create sequences of 3 weeks Normalisation of variables will be done within windows The neural network will have two hidden layers made up of 25 and 10 neurons respectively Historical demand by NEM region (5 min observations aggregated to 30 min for NSW) Air temperature by weather station (30 min Bankstown Airport) Use 10 epochs (iterations) for this proof of concept The output layer will predict a single value A window shifted along the sequence to predict subsequent values

19 Temperature and Energy Demand The relationship between air temperature and energy demand is well understood. Source: AEMO

20 Temperature and Energy Demand Demand is at its lowest when air temperature is mild (between 17 and 21 ) and rises when temperatures rise and fall. Source: AEMO

21 Temperature and Energy Demand Behaviours of the population are also evident when demand and temperature are segmented by time of day Source: AEMO

22 Types of time series prediction The sequences below describe the different methods of time series prediction considered

23 Outputs from univariate modelling MSE for each epoch suggests additional training is required Perhaps driven by dropout taking place in training set and not the validation set

24 Outputs from univariate modelling Historical demand was used to predict sequence windows of the next day (48 30min periods) Root Mean-Squared Error (RMSE):

25 Outputs from multivariate modelling Historical demand and air temperature was used to predict sequence windows of the next day (48 30min periods) RMSE:

26 Summary of model performance The table below compares performance (using RMSE) of univariate and multivariate models with respect to the different types of predictions made Prediction Type Univariate Model Multivariate Model Full test set (3 months) Multiple sequences (24 hours, for 3 months) Single step ( next 30 minute, for 3 months)

27 Next steps Optimise the parameters and structure of the LSTM Reframe the model to natively predict desired periods into the future (diagram below) Collect AEMO forecast data Compare LSTM forecast and AEMO forecast with actuals Currently the model predicts one, then shifts its window of prediction incrementally forward Benchmark performance with error measure Consider collecting additional measures (such as smart meter data) Consider developing an ensemble of machine learning techniques

28 Final considerations

29 Final points for consideration Neural networks typically require a lot of data and a take longer to train compared to traditional time series modelling techniques Efficient model development may require considerable CPU or GPU computing resources Interpretability is not a strength - typically traded off in return for better performance

30 Appendices and references

31 The NEM, AEMO and the spot market Since electricity is not easily stored, the National Electricity Market is a wholesale market where power supply (generators) and demand (retailers) are matched in real time through a centrally coordinated dispatch process. The Australian Energy Market Operator (AEMO) considers the bids offered to supply the network with electricity, before deciding which generators will be deployed to deliver that supply, using lowest price as a priority. Alongside the physical supply of electricity (the grid), there is a financial market where market participants enter into hedging contracts to manage price volatility risk.

32 Further information about the NEM The National Electricity Market (NEM) supplies approximately 200 terawatt hours to businesses and residences each year The network spans approx. 5,000 km along Australia s eastern and south-eastern coast with approx. 40,000km of transmission lines and cables. The network is divided into 5 price regions - QLD, NSW, SA, VIC and TAS

33 From generation to consumption

34 Trends in energy demand

35 AEMO model for residential consumption

36 Outputs from univariate modelling Historical demand was used to predict the next 30 minutes Prediction highly correlated with previous immediate lag, small but consistent error RMSE:

37 Outputs from multivariate modelling Historical demand and temperature was used to predict the next 30 minutes Prediction highly correlated with previous immediate lag, small but consistent error RMSE:

38 Outputs from univariate modelling Historical demand was used to predict the remaining training sequence Prediction errors continue to compound to a stasis RMSE:

39 Outputs from multivariate modelling Historical demand and temperature was used to predict the remaining training sequence Prediction errors continue to compound to a stasis, but better than univariate model model RMSE:

40 References

FORECAST ACCURACY REPORT 2017 FOR THE 2016 NATIONAL ELECTRICITY FORECASTING REPORT

FORECAST ACCURACY REPORT 2017 FOR THE 2016 NATIONAL ELECTRICITY FORECASTING REPORT FORECAST ACCURACY REPORT 2017 FOR THE 2016 NATIONAL ELECTRICITY FORECASTING REPORT Published: November 2017 Purpose The National Electricity Rules (Rules) require AEMO to report to the Reliability Panel

More information

NATIONAL ELECTRICITY FORECASTING REPORT UPDATE FOR THE NATIONAL ELECTRICITY MARKET

NATIONAL ELECTRICITY FORECASTING REPORT UPDATE FOR THE NATIONAL ELECTRICITY MARKET NATIONAL ELECTRICITY FORECASTING REPORT UPDATE FOR THE NATIONAL ELECTRICITY MARKET Published: December 2014 IMPORTANT NOTICE Purpose The purpose of this publication is to report on the accuracy of the

More information

peak half-hourly Tasmania

peak half-hourly Tasmania Forecasting long-term peak half-hourly electricity demand for Tasmania Dr Shu Fan B.S., M.S., Ph.D. Professor Rob J Hyndman B.Sc. (Hons), Ph.D., A.Stat. Business & Economic Forecasting Unit Report for

More information

peak half-hourly New South Wales

peak half-hourly New South Wales Forecasting long-term peak half-hourly electricity demand for New South Wales Dr Shu Fan B.S., M.S., Ph.D. Professor Rob J Hyndman B.Sc. (Hons), Ph.D., A.Stat. Business & Economic Forecasting Unit Report

More information

WEATHER DEPENENT ELECTRICITY MARKET FORECASTING WITH NEURAL NETWORKS, WAVELET AND DATA MINING TECHNIQUES. Z.Y. Dong X. Li Z. Xu K. L.

WEATHER DEPENENT ELECTRICITY MARKET FORECASTING WITH NEURAL NETWORKS, WAVELET AND DATA MINING TECHNIQUES. Z.Y. Dong X. Li Z. Xu K. L. WEATHER DEPENENT ELECTRICITY MARKET FORECASTING WITH NEURAL NETWORKS, WAVELET AND DATA MINING TECHNIQUES Abstract Z.Y. Dong X. Li Z. Xu K. L. Teo School of Information Technology and Electrical Engineering

More information

The Use of EDD for Weather Normalisation

The Use of EDD for Weather Normalisation The Use of EDD for Weather Normalisation January 2014 Core Energy Group 2014 January 2014 i Disclaimer Disclaimer This document has been prepared by Core Energy Group Pty Limited, A.C.N. 110 347 085, holder

More information

WIND INTEGRATION IN ELECTRICITY GRIDS WORK PACKAGE 3: SIMULATION USING HISTORICAL WIND DATA

WIND INTEGRATION IN ELECTRICITY GRIDS WORK PACKAGE 3: SIMULATION USING HISTORICAL WIND DATA WIND INTEGRATION IN ELECTRICITY GRIDS WORK PACKAGE 3: SIMULATION USING PREPARED BY: Strategy and Economics DATE: 18 January 2012 FINAL Australian Energy Market Operator Ltd ABN 94 072 010 327 www.aemo.com.au

More information

SOUTH AUSTRALIAN WIND STUDY REPORT SOUTH AUSTRALIAN ADVISORY FUNCTIONS

SOUTH AUSTRALIAN WIND STUDY REPORT SOUTH AUSTRALIAN ADVISORY FUNCTIONS SOUTH AUSTRALIAN WIND STUDY REPORT SOUTH AUSTRALIAN ADVISORY FUNCTIONS Published: October 2015 IMPORTANT NOTICE Purpose The purpose of this publication is to provide information about wind generation in

More information

LOADS, CUSTOMERS AND REVENUE

LOADS, CUSTOMERS AND REVENUE EB-00-0 Exhibit K Tab Schedule Page of 0 0 LOADS, CUSTOMERS AND REVENUE The purpose of this evidence is to present the Company s load, customer and distribution revenue forecast for the test year. The

More information

Warwick Business School Forecasting System. Summary. Ana Galvao, Anthony Garratt and James Mitchell November, 2014

Warwick Business School Forecasting System. Summary. Ana Galvao, Anthony Garratt and James Mitchell November, 2014 Warwick Business School Forecasting System Summary Ana Galvao, Anthony Garratt and James Mitchell November, 21 The main objective of the Warwick Business School Forecasting System is to provide competitive

More information

peak half-hourly South Australia

peak half-hourly South Australia Forecasting long-term peak half-hourly electricity demand for South Australia Dr Shu Fan B.S., M.S., Ph.D. Professor Rob J Hyndman B.Sc. (Hons), Ph.D., A.Stat. Business & Economic Forecasting Unit Report

More information

SMART GRID FORECASTING

SMART GRID FORECASTING SMART GRID FORECASTING AND FINANCIAL ANALYTICS Itron Forecasting Brown Bag December 11, 2012 PLEASE REMEMBER» Phones are Muted: In order to help this session run smoothly, your phones are muted.» Full

More information

SHORT TERM LOAD FORECASTING

SHORT TERM LOAD FORECASTING Indian Institute of Technology Kanpur (IITK) and Indian Energy Exchange (IEX) are delighted to announce Training Program on "Power Procurement Strategy and Power Exchanges" 28-30 July, 2014 SHORT TERM

More information

Integrated Electricity Demand and Price Forecasting

Integrated Electricity Demand and Price Forecasting Integrated Electricity Demand and Price Forecasting Create and Evaluate Forecasting Models The many interrelated factors which influence demand for electricity cannot be directly modeled by closed-form

More information

Sequence Modeling with Neural Networks

Sequence Modeling with Neural Networks Sequence Modeling with Neural Networks Harini Suresh y 0 y 1 y 2 s 0 s 1 s 2... x 0 x 1 x 2 hat is a sequence? This morning I took the dog for a walk. sentence medical signals speech waveform Successes

More information

NSP Electric - Minnesota Annual Report Peak Demand and Annual Electric Consumption Forecast

NSP Electric - Minnesota Annual Report Peak Demand and Annual Electric Consumption Forecast Page 1 of 5 7610.0320 - Forecast Methodology NSP Electric - Minnesota Annual Report Peak Demand and Annual Electric Consumption Forecast OVERALL METHODOLOGICAL FRAMEWORK Xcel Energy prepared its forecast

More information

DANIEL WILSON AND BEN CONKLIN. Integrating AI with Foundation Intelligence for Actionable Intelligence

DANIEL WILSON AND BEN CONKLIN. Integrating AI with Foundation Intelligence for Actionable Intelligence DANIEL WILSON AND BEN CONKLIN Integrating AI with Foundation Intelligence for Actionable Intelligence INTEGRATING AI WITH FOUNDATION INTELLIGENCE FOR ACTIONABLE INTELLIGENCE in an arms race for artificial

More information

Predicting Solar Irradiance and Inverter power for PV sites

Predicting Solar Irradiance and Inverter power for PV sites Area of Expertise: Industry: Name of Client: Predicting Solar Irradiance and Inverter power for PV sites Data Analytics Solar Project End Date: January 2019 Project Timeline: 1. Optimisation Scope InnovateUK

More information

Multivariate Regression Model Results

Multivariate Regression Model Results Updated: August, 0 Page of Multivariate Regression Model Results 4 5 6 7 8 This exhibit provides the results of the load model forecast discussed in Schedule. Included is the forecast of short term system

More information

Machine Learning Using Machine Learning to Improve Demand Response Forecasts

Machine Learning Using Machine Learning to Improve Demand Response Forecasts Machine Learning Using Machine Learning to Improve Demand Response Forecasts CONTENTS Introduction...2 What Is Machine Learning?...2 How Does Itron Use Machine Learning?...2 An Example: Improving Demand

More information

MODELLING ENERGY DEMAND FORECASTING USING NEURAL NETWORKS WITH UNIVARIATE TIME SERIES

MODELLING ENERGY DEMAND FORECASTING USING NEURAL NETWORKS WITH UNIVARIATE TIME SERIES MODELLING ENERGY DEMAND FORECASTING USING NEURAL NETWORKS WITH UNIVARIATE TIME SERIES S. Cankurt 1, M. Yasin 2 1&2 Ishik University Erbil, Iraq 1 s.cankurt@ishik.edu.iq, 2 m.yasin@ishik.edu.iq doi:10.23918/iec2018.26

More information

CHAPTER 5 - QUEENSLAND FORECASTS

CHAPTER 5 - QUEENSLAND FORECASTS CHAPTER 5 - QUEENSLAND FORECASTS Summary This chapter presents information about annual energy, maximum demand (summer and winter), and nonscheduled generation for the Queensland region. It also includes

More information

RESERVE LEVEL DECLARATION GUIDELINES

RESERVE LEVEL DECLARATION GUIDELINES RESERVE LEVEL DECLARATION GUIDELINES PREPARED BY: AEMO Operations DOCUMENT REF: RLDG-V2.1-FINAL VERSION: 2.1 EFFECTIVE DATE: 12 December 2018 STATUS: FINAL Approved for distribution and use by: APPROVED

More information

Nonparametric forecasting of the French load curve

Nonparametric forecasting of the French load curve An overview RTE & UPMC-ISUP ISNPS 214, Cadix June 15, 214 Table of contents 1 Introduction 2 MAVE modeling 3 IBR modeling 4 Sparse modeling Electrical context Generation must be strictly equal to consumption

More information

TRANSMISSION BUSINESS LOAD FORECAST AND METHODOLOGY

TRANSMISSION BUSINESS LOAD FORECAST AND METHODOLOGY Filed: September, 00 EB-00-00 Tab Schedule Page of 0 TRANSMISSION BUSINESS LOAD FORECAST AND METHODOLOGY.0 INTRODUCTION 0 This exhibit discusses Hydro One Networks transmission system load forecast and

More information

2013 Weather Normalization Survey. Itron, Inc El Camino Real San Diego, CA

2013 Weather Normalization Survey. Itron, Inc El Camino Real San Diego, CA Itron, Inc. 11236 El Camino Real San Diego, CA 92130 2650 858 724 2620 March 2014 Weather normalization is the process of reconstructing historical energy consumption assuming that normal weather occurred

More information

SYSTEM OPERATIONS. Dr. Frank A. Monforte

SYSTEM OPERATIONS. Dr. Frank A. Monforte SYSTEM OPERATIONS FORECASTING Dr. Frank A. Monforte Itron s Forecasting Brown Bag Seminar September 13, 2011 PLEASE REMEMBER» In order to help this session run smoothly, your phones are muted.» To make

More information

Understanding Travel Time to Airports in New York City Sierra Gentry Dominik Schunack

Understanding Travel Time to Airports in New York City Sierra Gentry Dominik Schunack Understanding Travel Time to Airports in New York City Sierra Gentry Dominik Schunack 1 Introduction Even with the rising competition of rideshare services, many in New York City still utilize taxis for

More information

Recurrent Neural Networks (Part - 2) Sumit Chopra Facebook

Recurrent Neural Networks (Part - 2) Sumit Chopra Facebook Recurrent Neural Networks (Part - 2) Sumit Chopra Facebook Recap Standard RNNs Training: Backpropagation Through Time (BPTT) Application to sequence modeling Language modeling Applications: Automatic speech

More information

Demand Forecasting Models

Demand Forecasting Models E 2017 PSE Integrated Resource Plan Demand Forecasting Models This appendix describes the econometric models used in creating the demand forecasts for PSE s 2017 IRP analysis. Contents 1. ELECTRIC BILLED

More information

HEALTHCARE. 5 Components of Accurate Rolling Forecasts in Healthcare

HEALTHCARE. 5 Components of Accurate Rolling Forecasts in Healthcare HEALTHCARE 5 Components of Accurate Rolling Forecasts in Healthcare Introduction Rolling Forecasts Improve Accuracy and Optimize Decisions Accurate budgeting, planning, and forecasting are essential for

More information

Variables For Each Time Horizon

Variables For Each Time Horizon Variables For Each Time Horizon Andy Sukenik Itron s Forecasting Brown Bag Seminar December 13th, 2011 Please Remember In order to help this session run smoothly, your phones are muted. To make the presentation

More information

DRIVING ROI. The Business Case for Advanced Weather Solutions for the Energy Market

DRIVING ROI. The Business Case for Advanced Weather Solutions for the Energy Market DRIVING ROI The Business Case for Advanced Weather Solutions for the Energy Market Table of Contents Energy Trading Challenges 3 Skill 4 Speed 5 Precision 6 Key ROI Findings 7 About The Weather Company

More information

POWER SYSTEM OPERATING PROCEDURE LOAD FORECASTING

POWER SYSTEM OPERATING PROCEDURE LOAD FORECASTING POWER SYSTEM OPERATING PROCEDURE LOAD FORECASTING PREPARED BY: PROCEDURE TYPE: DOCUMENT REFERENCE: FINAL APPROVER: Systems Capability System Operating Procedure SO_OP_3710 Christian Schaefer DOC. VERSION:

More information

CSC321 Lecture 15: Exploding and Vanishing Gradients

CSC321 Lecture 15: Exploding and Vanishing Gradients CSC321 Lecture 15: Exploding and Vanishing Gradients Roger Grosse Roger Grosse CSC321 Lecture 15: Exploding and Vanishing Gradients 1 / 23 Overview Yesterday, we saw how to compute the gradient descent

More information

WRF Webcast. Improving the Accuracy of Short-Term Water Demand Forecasts

WRF Webcast. Improving the Accuracy of Short-Term Water Demand Forecasts No part of this presentation may be copied, reproduced, or otherwise utilized without permission. WRF Webcast Improving the Accuracy of Short-Term Water Demand Forecasts August 29, 2017 Presenters Maureen

More information

Better Weather Data Equals Better Results: The Proof is in EE and DR!

Better Weather Data Equals Better Results: The Proof is in EE and DR! Better Weather Data Equals Better Results: The Proof is in EE and DR! www.weatherbughome.com Today s Speakers: Amena Ali SVP and General Manager WeatherBug Home Michael Siemann, PhD Senior Research Scientist

More information

THE POTENTIAL OF APPLYING MACHINE LEARNING FOR PREDICTING CUT-IN BEHAVIOUR OF SURROUNDING TRAFFIC FOR TRUCK-PLATOONING SAFETY

THE POTENTIAL OF APPLYING MACHINE LEARNING FOR PREDICTING CUT-IN BEHAVIOUR OF SURROUNDING TRAFFIC FOR TRUCK-PLATOONING SAFETY THE POTENTIAL OF APPLYING MACHINE LEARNING FOR PREDICTING CUT-IN BEHAVIOUR OF SURROUNDING TRAFFIC FOR TRUCK-PLATOONING SAFETY Irene Cara Jan-Pieter Paardekooper TNO Helmond The Netherlands Paper Number

More information

AUTO SALES FORECASTING FOR PRODUCTION PLANNING AT FORD

AUTO SALES FORECASTING FOR PRODUCTION PLANNING AT FORD FCAS AUTO SALES FORECASTING FOR PRODUCTION PLANNING AT FORD Group - A10 Group Members: PGID Name of the Member 1. 61710956 Abhishek Gore 2. 61710521 Ajay Ballapale 3. 61710106 Bhushan Goyal 4. 61710397

More information

Design of a Weather-Normalization Forecasting Model

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

More information

FIVE MINUTE ELECTRICITY DEMAND FORECASTING: NEURAL NETWORK MODEL DOCUMENTATION

FIVE MINUTE ELECTRICITY DEMAND FORECASTING: NEURAL NETWORK MODEL DOCUMENTATION FIVE MINUTE ELECTRICITY DEMAND FORECASTING: NEURAL NETWORK MODEL PREPARED BY: PROCEDURE TYPE: DOCUMENT REFERENCE: FINAL APPROVER: Forecasting Forecasting Document SO_FD_01 Joe Spurio DOC. VERSION: 2 DATE:

More information

Defining Normal Weather for Energy and Peak Normalization

Defining Normal Weather for Energy and Peak Normalization Itron White Paper Energy Forecasting Defining Normal Weather for Energy and Peak Normalization J. Stuart McMenamin, Ph.D Managing Director, Itron Forecasting 2008, Itron Inc. All rights reserved. 1 Introduction

More information

Pattern Matching and Neural Networks based Hybrid Forecasting System

Pattern Matching and Neural Networks based Hybrid Forecasting System Pattern Matching and Neural Networks based Hybrid Forecasting System Sameer Singh and Jonathan Fieldsend PA Research, Department of Computer Science, University of Exeter, Exeter, UK Abstract In this paper

More information

Modelling Time Series with Neural Networks. Volker Tresp Summer 2017

Modelling Time Series with Neural Networks. Volker Tresp Summer 2017 Modelling Time Series with Neural Networks Volker Tresp Summer 2017 1 Modelling of Time Series The next figure shows a time series (DAX) Other interesting time-series: energy prize, energy consumption,

More information

Long-Short Term Memory and Other Gated RNNs

Long-Short Term Memory and Other Gated RNNs Long-Short Term Memory and Other Gated RNNs Sargur Srihari srihari@buffalo.edu This is part of lecture slides on Deep Learning: http://www.cedar.buffalo.edu/~srihari/cse676 1 Topics in Sequence Modeling

More information

WEATHER NORMALIZATION METHODS AND ISSUES. Stuart McMenamin Mark Quan David Simons

WEATHER NORMALIZATION METHODS AND ISSUES. Stuart McMenamin Mark Quan David Simons WEATHER NORMALIZATION METHODS AND ISSUES Stuart McMenamin Mark Quan David Simons Itron Forecasting Brown Bag September 17, 2013 Please Remember» Phones are Muted: In order to help this session run smoothly,

More information

Prediction and Uncertainty Quantification of Daily Airport Flight Delays

Prediction and Uncertainty Quantification of Daily Airport Flight Delays Proceedings of Machine Learning Research 82 (2017) 45-51, 4th International Conference on Predictive Applications and APIs Prediction and Uncertainty Quantification of Daily Airport Flight Delays Thomas

More information

Caesar s Taxi Prediction Services

Caesar s Taxi Prediction Services 1 Caesar s Taxi Prediction Services Predicting NYC Taxi Fares, Trip Distance, and Activity Paul Jolly, Boxiao Pan, Varun Nambiar Abstract In this paper, we propose three models each predicting either taxi

More information

Short Term Load Forecasting Using Multi Layer Perceptron

Short Term Load Forecasting Using Multi Layer Perceptron International OPEN ACCESS Journal Of Modern Engineering Research (IJMER) Short Term Load Forecasting Using Multi Layer Perceptron S.Hema Chandra 1, B.Tejaswini 2, B.suneetha 3, N.chandi Priya 4, P.Prathima

More information

POWER SYSTEM OPERATING PROCEDURE LOAD FORECASTING

POWER SYSTEM OPERATING PROCEDURE LOAD FORECASTING POWER SYSTEM OPERATING PROCEDURE LOAD FORECASTING PREPARED BY: PROCEDURE TYPE: DOCUMENT REFERENCE: FINAL APPROVER: Systems Capability System Operating Procedure SO_OP_3710 Mark Stedwell DOC. VERSION: 19

More information

Bringing Renewables to the Grid. John Dumas Director Wholesale Market Operations ERCOT

Bringing Renewables to the Grid. John Dumas Director Wholesale Market Operations ERCOT Bringing Renewables to the Grid John Dumas Director Wholesale Market Operations ERCOT 2011 Summer Seminar August 2, 2011 Quick Overview of ERCOT The ERCOT Market covers ~85% of Texas overall power usage

More information

CHARTING SPATIAL BUSINESS TRANSFORMATION

CHARTING SPATIAL BUSINESS TRANSFORMATION CHARTING SPATIAL BUSINESS TRANSFORMATION An in-depth look at the business patterns of GIS and location intelligence adoption in the private sector EXECUTIVE SUMMARY The global use of geographic information

More information

BEFORE THE PUBLIC UTILITIES COMMISSION OF THE STATE OF COLORADO * * * *

BEFORE THE PUBLIC UTILITIES COMMISSION OF THE STATE OF COLORADO * * * * Exhibit No. 1 BEFORE THE PUBLIC UTILITIES COMMISSION OF THE STATE OF COLORADO * * * * IN THE MATTER OF THE APPLICATION OF PUBLIC SERVICE COMPANY OF COLORADO FOR APPROVAL OF ITS 0 ELECTRIC RESOURCE PLAN

More information

UPDATE ELECTRICITY STATEMENT OF OPPORTUNITIES FOR THE NATIONAL ELECTRICITY MARKET

UPDATE ELECTRICITY STATEMENT OF OPPORTUNITIES FOR THE NATIONAL ELECTRICITY MARKET UPDATE ELECTRICITY STATEMENT OF OPPORTUNITIES FOR THE NATIONAL ELECTRICITY MARKET Published: 26 October 2015 ELECTRICITY STATEMENT OF OPPORTUNITIES IMPORTANT NOTICE Purpose AEMO publishes the Electricity

More information

Advances in promotional modelling and analytics

Advances in promotional modelling and analytics Advances in promotional modelling and analytics High School of Economics St. Petersburg 25 May 2016 Nikolaos Kourentzes n.kourentzes@lancaster.ac.uk O u t l i n e 1. What is forecasting? 2. Forecasting,

More information

Data and prognosis for renewable energy

Data and prognosis for renewable energy The Hong Kong Polytechnic University Department of Electrical Engineering Project code: FYP_27 Data and prognosis for renewable energy by Choi Man Hin 14072258D Final Report Bachelor of Engineering (Honours)

More information

Design of a Weather- Normalization Forecasting Model

Design of a Weather- Normalization Forecasting Model Design of a Weather- Normalization Forecasting Model Progress Report Abram Gross Yafeng Peng Jedidiah Shirey 3/4/2014 TABLE OF CONTENTS 1.0 Introduction... 3 2.0 Problem Statement... 3 3.0 Scope... 3 4.0

More information

Multi-Model Ensemble for day ahead PV power forecasting improvement

Multi-Model Ensemble for day ahead PV power forecasting improvement Multi-Model Ensemble for day ahead PV power forecasting improvement Cristina Cornaro a,b, Marco Pierro a,e, Francesco Bucci a, Matteo De Felice d, Enrico Maggioni c, David Moser e,alessandro Perotto c,

More information

Day Ahead Hourly Load and Price Forecast in ISO New England Market using ANN

Day Ahead Hourly Load and Price Forecast in ISO New England Market using ANN 23 Annual IEEE India Conference (INDICON) Day Ahead Hourly Load and Price Forecast in ISO New England Market using ANN Kishan Bhushan Sahay Department of Electrical Engineering Delhi Technological University

More information

PREPARED DIRECT TESTIMONY OF GREGORY TEPLOW SOUTHERN CALIFORNIA GAS COMPANY AND SAN DIEGO GAS & ELECTRIC COMPANY

PREPARED DIRECT TESTIMONY OF GREGORY TEPLOW SOUTHERN CALIFORNIA GAS COMPANY AND SAN DIEGO GAS & ELECTRIC COMPANY Application No: A.1-0- Exhibit No.: Witness: Gregory Teplow Application of Southern California Gas Company (U 0 G) and San Diego Gas & Electric Company (U 0 G) for Authority to Revise their Natural Gas

More information

BEFORE THE PUBLIC UTILITY COMMISSION OF THE STATE OF OREGON UE 294. Load Forecast PORTLAND GENERAL ELECTRIC COMPANY. Direct Testimony and Exhibits of

BEFORE THE PUBLIC UTILITY COMMISSION OF THE STATE OF OREGON UE 294. Load Forecast PORTLAND GENERAL ELECTRIC COMPANY. Direct Testimony and Exhibits of UE 294 / PGE / 1200 Dammen - Riter BEFORE THE PUBLIC UTILITY COMMISSION OF THE STATE OF OREGON UE 294 Load Forecast PORTLAND GENERAL ELECTRIC COMPANY Direct Testimony and Exhibits of Sarah Dammen Amber

More information

2006 IRP Technical Workshop Load Forecasting Tuesday, January 24, :00 am 3:30 pm (Pacific) Meeting Summary

2006 IRP Technical Workshop Load Forecasting Tuesday, January 24, :00 am 3:30 pm (Pacific) Meeting Summary 2006 IRP Technical Workshop Load Forecasting Tuesday, January 24, 2006 9:00 am 3:30 pm (Pacific) Meeting Summary Idaho Oregon Utah Teri Carlock (IPUC) Ming Peng (OPUC), Bill Wordley (OPUC) Abdinasir Abdulle

More information

Load Forecasting Technical Workshop. January 30, 2004

Load Forecasting Technical Workshop. January 30, 2004 Load Forecasting Technical Workshop January 30, 2004 Agenda New Commercial Survey Results (20 Minutes) Changing Commercial Saturation s (20 Minutes) Conditional Demand Analysis (30 Minutes) Changing Commercial

More information

The Changing Landscape of Land Administration

The Changing Landscape of Land Administration The Changing Landscape of Land Administration B r e n t J o n e s P E, PLS E s r i World s Largest Media Company No Journalists No Content Producers No Photographers World s Largest Hospitality Company

More information

Estimation of extreme value dependence: application to Australian spot electricity prices. Nadezda Frolova

Estimation of extreme value dependence: application to Australian spot electricity prices. Nadezda Frolova Estimation of extreme value dependence: application to Australian spot electricity prices by Nadezda Frolova A thesis submitted in partial fulfillment of the requirements for the degree of Masters of Science

More information

Chapter 8 - Forecasting

Chapter 8 - Forecasting Chapter 8 - Forecasting Operations Management by R. Dan Reid & Nada R. Sanders 4th Edition Wiley 2010 Wiley 2010 1 Learning Objectives Identify Principles of Forecasting Explain the steps in the forecasting

More information

Abram Gross Yafeng Peng Jedidiah Shirey

Abram Gross Yafeng Peng Jedidiah Shirey Abram Gross Yafeng Peng Jedidiah Shirey Contents Context Problem Statement Method of Analysis Forecasting Model Way Forward Earned Value NOVEC Background (1 of 2) Northern Virginia Electric Cooperative

More information

Economic Benefit Study on Value of Spatial Information Australian Experience

Economic Benefit Study on Value of Spatial Information Australian Experience Economic Benefit Study on Value of Spatial Information Australian Experience Dr Zaffar Sadiq Mohamed-Ghouse Director, International Relations Cooperative Research Centre for Spatial Information zsadiq@crcsi.com.au

More information

Machine Learning. Boris

Machine Learning. Boris Machine Learning Boris Nadion boris@astrails.com @borisnadion @borisnadion boris@astrails.com astrails http://astrails.com awesome web and mobile apps since 2005 terms AI (artificial intelligence)

More information

Optimization of the forecasting of wind energy production Focus on the day ahead forecast

Optimization of the forecasting of wind energy production Focus on the day ahead forecast Optimization of the forecasting of wind energy production Focus on the day ahead forecast Market Processes, EnBW Transportnetze AG Mirjam Eppinger, Dietmar Graeber, Andreas Semmig Quantitative Methods,

More information

Power System Seminar Presentation Wind Forecasting and Dispatch 7 th July, Wind Power Forecasting tools and methodologies

Power System Seminar Presentation Wind Forecasting and Dispatch 7 th July, Wind Power Forecasting tools and methodologies Power System Seminar Presentation Wind Forecasting and Dispatch 7 th July, 2011 Wind Power Forecasting tools and methodologies Amanda Kelly Principal Engineer Power System Operational Planning Operations

More information

Short Term Load Forecasting Based Artificial Neural Network

Short Term Load Forecasting Based Artificial Neural Network Short Term Load Forecasting Based Artificial Neural Network Dr. Adel M. Dakhil Department of Electrical Engineering Misan University Iraq- Misan Dr.adelmanaa@gmail.com Abstract Present study develops short

More information

Recurrent Neural Networks. Jian Tang

Recurrent Neural Networks. Jian Tang Recurrent Neural Networks Jian Tang tangjianpku@gmail.com 1 RNN: Recurrent neural networks Neural networks for sequence modeling Summarize a sequence with fix-sized vector through recursively updating

More information

Advanced Weather Technology

Advanced Weather Technology Advanced Weather Technology Tuesday, October 16, 2018, 1:00 PM 2:00 PM PRESENTED BY: Gary Pokodner, FAA WTIC Program Manager Agenda Overview Augmented reality mobile application Crowd Sourcing Visibility

More information

FINAL REPORT EVALUATION REVIEW OF TVA'S LOAD FORECAST RISK

FINAL REPORT EVALUATION REVIEW OF TVA'S LOAD FORECAST RISK Memorandum from the Office of the Inspector General Robert Irvin, WT 9C-K FINAL REPORT EVALUATION 2012-14507 REVIEW OF TVA'S LOAD FORECAST RISK As part of a series of reviews to evaluate the Tennessee

More information

CONTEMPORARY ANALYTICAL ECOSYSTEM PATRICK HALL, SAS INSTITUTE

CONTEMPORARY ANALYTICAL ECOSYSTEM PATRICK HALL, SAS INSTITUTE CONTEMPORARY ANALYTICAL ECOSYSTEM PATRICK HALL, SAS INSTITUTE Copyright 2013, SAS Institute Inc. All rights reserved. Agenda (Optional) History Lesson 2015 Buzzwords Machine Learning for X Citizen Data

More information

A Wavelet Neural Network Forecasting Model Based On ARIMA

A Wavelet Neural Network Forecasting Model Based On ARIMA A Wavelet Neural Network Forecasting Model Based On ARIMA Wang Bin*, Hao Wen-ning, Chen Gang, He Deng-chao, Feng Bo PLA University of Science &Technology Nanjing 210007, China e-mail:lgdwangbin@163.com

More information

Predicting the Electricity Demand Response via Data-driven Inverse Optimization

Predicting the Electricity Demand Response via Data-driven Inverse Optimization Predicting the Electricity Demand Response via Data-driven Inverse Optimization Workshop on Demand Response and Energy Storage Modeling Zagreb, Croatia Juan M. Morales 1 1 Department of Applied Mathematics,

More information

Capacity Market Load Forecast

Capacity Market Load Forecast Capacity Market Load Forecast Date: November 2017 Subject: Capacity Market Load Forecast Model, Process, and Preliminary 2021 Results Purpose This memo describes the input data, process, and model the

More information

Demand forecasting methodology for Security of Supply

Demand forecasting methodology for Security of Supply Demand forecasting methodology for Security of Supply Consultation paper April 2007 Contents 1 EXECUTIVE SUMMARY...4 2 INTRODUCTION AND PROCESS...5 2.1 Background...5 2.2 Submission process...7 3 SCOPE...9

More information

Density forecasting for long-term. peak electricity demand

Density forecasting for long-term. peak electricity demand ISSN 1440-771X Department of Econometrics and Business Statistics http://www.buseco.monash.edu.au/depts/ebs/pubs/wpapers/ Density forecasting for long-term peak electricity demand Rob J Hyndman and Shu

More information

Putting the U.S. Geospatial Services Industry On the Map

Putting the U.S. Geospatial Services Industry On the Map Putting the U.S. Geospatial Services Industry On the Map December 2012 Definition of geospatial services and the focus of this economic study Geospatial services Geospatial services industry Allow consumers,

More information

About Nnergix +2, More than 2,5 GW forecasted. Forecasting in 5 countries. 4 predictive technologies. More than power facilities

About Nnergix +2, More than 2,5 GW forecasted. Forecasting in 5 countries. 4 predictive technologies. More than power facilities About Nnergix +2,5 5 4 +20.000 More than 2,5 GW forecasted Forecasting in 5 countries 4 predictive technologies More than 20.000 power facilities Nnergix s Timeline 2012 First Solar Photovoltaic energy

More information

A tale of two cities. John Daley, CEO, Grattan Institute Work and life in cities: City strategy in Australia Melbourne Economic Forum 27 October 2016

A tale of two cities. John Daley, CEO, Grattan Institute Work and life in cities: City strategy in Australia Melbourne Economic Forum 27 October 2016 A tale of two cities John Daley, CEO, Grattan Institute Work and life in cities: City strategy in Australia Melbourne Economic Forum 27 October 2016 A tale of two cities Shifts in consumption are driving

More information

Modelling residual wind farm variability using HMMs

Modelling residual wind farm variability using HMMs 8 th World IMACS/MODSIM Congress, Cairns, Australia 3-7 July 2009 http://mssanz.org.au/modsim09 Modelling residual wind farm variability using HMMs Ward, K., Korolkiewicz, M. and Boland, J. School of Mathematics

More information

A Bayesian Perspective on Residential Demand Response Using Smart Meter Data

A Bayesian Perspective on Residential Demand Response Using Smart Meter Data A Bayesian Perspective on Residential Demand Response Using Smart Meter Data Datong-Paul Zhou, Maximilian Balandat, and Claire Tomlin University of California, Berkeley [datong.zhou, balandat, tomlin]@eecs.berkeley.edu

More information

FORECASTING THE RESIDUAL DEMAND FUNCTION IN

FORECASTING THE RESIDUAL DEMAND FUNCTION IN FORECASTING THE RESIDUAL DEMAND FUNCTION IN ELECTRICITY AUCTIONS Dipartimento di Statistica Università degli Studi di Milano-Bicocca Via Bicocca degli Arcimboldi 8, Milano, Italy (e-mail: matteo.pelagatti@unimib.it)

More information

Enhancements and Validation of a Demand Forecast Tool for South Australian Water Corporation

Enhancements and Validation of a Demand Forecast Tool for South Australian Water Corporation ISSN 2206-1991 Volume 3 No 4 2018 https://doi.org/10.21139/wej.2018.041 Enhancements and Validation of a Demand Forecast Tool for South Australian Water Corporation Managing complexities in operations

More information

On the use of Long-Short Term Memory neural networks for time series prediction

On the use of Long-Short Term Memory neural networks for time series prediction On the use of Long-Short Term Memory neural networks for time series prediction Pilar Gómez-Gil National Institute of Astrophysics, Optics and Electronics ccc.inaoep.mx/~pgomez In collaboration with: J.

More information

Introduction to Forecasting

Introduction to Forecasting Introduction to Forecasting Introduction to Forecasting Predicting the future Not an exact science but instead consists of a set of statistical tools and techniques that are supported by human judgment

More information

Do we need Experts for Time Series Forecasting?

Do we need Experts for Time Series Forecasting? Do we need Experts for Time Series Forecasting? Christiane Lemke and Bogdan Gabrys Bournemouth University - School of Design, Engineering and Computing Poole House, Talbot Campus, Poole, BH12 5BB - United

More information

Forecasting Methods And Applications 3rd Edition

Forecasting Methods And Applications 3rd Edition We have made it easy for you to find a PDF Ebooks without any digging. And by having access to our ebooks online or by storing it on your computer, you have convenient answers with forecasting methods

More information

Recurrent Neural Networks

Recurrent Neural Networks Recurrent Neural Networks Datamining Seminar Kaspar Märtens Karl-Oskar Masing Today's Topics Modeling sequences: a brief overview Training RNNs with back propagation A toy example of training an RNN Why

More information

COMPARISON OF CLEAR-SKY MODELS FOR EVALUATING SOLAR FORECASTING SKILL

COMPARISON OF CLEAR-SKY MODELS FOR EVALUATING SOLAR FORECASTING SKILL COMPARISON OF CLEAR-SKY MODELS FOR EVALUATING SOLAR FORECASTING SKILL Ricardo Marquez Mechanical Engineering Applied Mechanics School of Engineering University of California Merced Merced, California 95343

More information

Ontario Demand Forecast

Ontario Demand Forecast Ontario Demand Forecast DECEMBER 12, 2017 December 12, 2017 Public Page i Executive Summary The IESO is responsible for forecasting electricity demand in Ontario and for assessing whether transmission

More information

Short-term water demand forecast based on deep neural network ABSTRACT

Short-term water demand forecast based on deep neural network ABSTRACT Short-term water demand forecast based on deep neural network Guancheng Guo 1, Shuming Liu 2 1,2 School of Environment, Tsinghua University, 100084, Beijing, China 2 shumingliu@tsinghua.edu.cn ABSTRACT

More information

Neural networks. Chapter 20. Chapter 20 1

Neural networks. Chapter 20. Chapter 20 1 Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms

More information

FORECASTING OF INFLATION IN BANGLADESH USING ANN MODEL

FORECASTING OF INFLATION IN BANGLADESH USING ANN MODEL FORECASTING OF INFLATION IN BANGLADESH USING ANN MODEL Rumana Hossain Department of Physical Science School of Engineering and Computer Science Independent University, Bangladesh Shaukat Ahmed Department

More information

FORECASTING: A REVIEW OF STATUS AND CHALLENGES. Eric Grimit and Kristin Larson 3TIER, Inc. Pacific Northwest Weather Workshop March 5-6, 2010

FORECASTING: A REVIEW OF STATUS AND CHALLENGES. Eric Grimit and Kristin Larson 3TIER, Inc. Pacific Northwest Weather Workshop March 5-6, 2010 SHORT-TERM TERM WIND POWER FORECASTING: A REVIEW OF STATUS AND CHALLENGES Eric Grimit and Kristin Larson 3TIER, Inc. Pacific Northwest Weather Workshop March 5-6, 2010 Integrating Renewable Energy» Variable

More information

Activation of unscheduled reserves for Victoria and South Australia 19 January 2018 May 2018

Activation of unscheduled reserves for Victoria and South Australia 19 January 2018 May 2018 Activation of unscheduled reserves for Victoria and South Australia 19 January 2018 May 2018 Event report for the National Electricity Market Annexure B of Summer 2017-18 operations review Important notice

More information