Non-Intrusive Appliance Load Monitoring (NIALM): Review and Outlook *
|
|
- Daisy Dean
- 6 years ago
- Views:
Transcription
1 Fraunhofer Center for Sustainable Energy Systems Non-Intrusive Appliance Monitoring (NIALM): Review and Outlook * Michael Zeifman, Ph.D. Kurt Roth, Ph.D. International Conference on Consumer Electronics Las Vegas 1 January 211 * Supported in part by US DOE through a subcontract with Lawrence Berkley National Laboratory (LBNL). We are grateful to Rich Brown of LBNL for helpful discussions. Fraunhofer USA 211
2 Fraunhofer: A Leading Force in Applied R&D Fraunhofer Gesellschaft: Europe s largest contract research organization 17, employees Annual research budget: US$2.2B 59 institutes provide contract R&D and certification services for clients Research Themes: health, security, communication, mobility, energy, environment Fraunhofer USA: 7 Centers, >2 employees, Annual research budget >$5M Fraunhofer CSE is located in Cambridge, MA Three focus areas: Building Energy Efficiency PV Modules Smart Grid Fraunhofer USA 211 2
3 What Is NIALM? Non-Intrusive Appliance Monitoring A.k.a. Non-Intrusive Monitoring Power, W 4 2 Coffee Maker 7: 7:3 8: 8:3 9: 9:3 Po ower, W : 7:3 8: 8:3 9: 9:3 Time Power, W Power, W 1 5 Refrigerator 7: 7:3 8: 8:3 9: 9:3 4 2 TV 7: 7:3 8: 8:3 9: 9:3 Time Main breaker/circuit level Data acquisition (hardware) and disaggregation algorithms (software) Fraunhofer USA 211 3
4 NIALM: Interest Number of US granted patents exponential growth Patents/year Year Both large (Belkin, GE, IBM, Intel,) and small (4home, Emme, Enetics, Navetas) companies Fraunhofer USA 211 4
5 NIALM: Motivation Energy saving potential Residential buildings consume ~ 2% of primary energy in USA Electricity constitutes ~ 7% of residential energy consumption Feedback on energy usage can result in 5-15% saving Smart Grid unique business opportunity ~ 8 M smart meters in USA are projected by 213 Hardware can be used by NIALM Non-intrusive manual alternative to home automation Time-of-use electricity pricing Transition from fixed to time-dependent pricing in Europe and North America More people are concerned with energy monitoring and management Fraunhofer USA 211 5
6 How Does NIALM Work? Data Acquisition Appliance Signal Features Disaggregation Algorithm NIALM Fraunhofer USA 211 6
7 Data for NIALM: Sampling Rate Typical daily number of switching events in a household: up to ~ [Baranski, 24].1 Hz minimum sampling rate Inexpensive hardware: 1 Hz 15 More expensive hardware: > 5 khz.1.5 Power, W 1 Current, A :35 22:4 22:45 22:5 22:55 23: 23: Time, s Fraunhofer USA 211 7
8 NIALM: Types of Appliances Permanent On/off Multi State Variable Fraunhofer USA 211 8
9 I. Low Sampling Rate, Features: Power Change Real Power Reactive Power 2 2 Voltage Voltage Current Current Power 1 Power Time Time Fraunhofer USA 211 9
10 I. Power Change: Basic Method Hart, 1992 (MIT method) On/off appliances Multi State Variable Permanent Same- Appliances Accuracy: ~8% Fraunhofer USA 211 1
11 I. Change of Real Power Only Baranski and Voss, Hart s Method: single - P single + P Baranski s Method: multiple - P i multiple + P i Baranski s algorithm error term minimization (optimization by genetic algorithm) On/off appliances Multi State Variable Permanent Same- Appliances Accuracy: ~85% Fraunhofer USA
12 I. Change of Power + Additional Features Albicki and Cole, 1998 Edges and slopes as additional features On/off appliances Multi State Variable Permanent Same- Appliances Accuracy: ~N/A Fraunhofer USA
13 II. High Sampling Rate, Harmonics as Features Basic Idea: Fourier Transform 1 Current Signal waveform rrent Cur Time, s 1 1 st 3 rd Signal harmonics Time, s FFT Frequency, Hz Fourier transform Fraunhofer USA
14 II. Features: Harmonics for Transients (1/2) Laughman et al., 23 (MIT).1.8 On/off appliances.6.4 Current Multi State Time, s 1) Detect transients 2) Subtract pre-transient from posttransient 3) Take Fourier transform and compare with template 4) Set of harmonics = power envelope Variable Permanent Same- Appliances Accuracy: ~N/A Fraunhofer USA
15 II. Features: Harmonics for Transients (2/2) Lee et al., 25 (MIT) On/off appliances P harmonic Multi State Variable P total 1) Strong correlation between harmonics and power draw 2) Estimate harmonics then estimate load Permanent Same- Appliances Accuracy: ~N/A Fraunhofer USA
16 II. Features: Harmonics for Steady and Transients Srinivasan et al., 26 (Singapore) Basic idea: Set of harmonics for all combinations of appliances 1) Obtain Fourier transform continuously 2) Compare with templates On/off appliances Multi State Variable Permanent Harmonic number Same- Appliances Accuracy: 77% (phone charger) 99% (PC) Fraunhofer USA
17 II. Features: Fourier Transform of Noise (1/2) Patel et al., 27 (Ga. Tech.) Basic idea: appliance connected to a socket induces noise (electromagnetic interference) in another socket On/off appliances Multi State Variable 1) Measure signal at high rate (5 khz) 2) Calculate Fourier transform continuously 3) Compare with templates Permanent Same- Appliances Accuracy: 85-9% Fraunhofer USA
18 II. Features: Fourier Transform of Noise (2/2) Patel et al., 21 (Now U. Wash.) Basic idea: switch mode power supplies (SMPS) generate distinctive noises On/off appliances Multi State Variable Distinctive features ( applicable across homes ) Yet features variable enough to differentiate between similar devices in a home Permanent Same- Appliances Accuracy: up to 93.8% Fraunhofer USA
19 II. Features: Beyond Harmonics / Fourier Transform Liang et al., 21 (China Light & Power) Waveform: On/off appliances Multi State Power waveform Variable Permanent Same- Appliances Accuracy: 92.7% Fraunhofer USA
20 NIALM Algorithms (1/3) Single-matching (pattern recognition) Example: Waveform On/off appliances Current, a.u. Before Time, ms - Current, a.u. After Time, ms Multi State Variable = Current, a.u Time, ms Pattern recognition methods used: N-nearest neighbor Bayes classifier Neural networks Permanent Same- Appliances Fraunhofer USA 211 2
21 NIALM Algorithms (2/3) Start Multiple-matching (Optimization) Stop On/off appliances 8 Power, W Power, W Refrigerator Coffeemaker? Power, W Multi State Variable Power, W : 7:3 8: 8:3 9: 9:3 Time Permanent TV Optimization methods used: Least squares Integer programming Genetic algorithms Same- Appliances Fraunhofer USA
22 NIALM Algorithms (3/3) True disaggregation A.k.a. blind source separation On/off appliances Possible methods: Independent Component Analysis (ICA) Singular Value Decomposition Non-negative Matrix Factorization Yet has to be tried! Multi State Variable Permanent Same- Appliances Fraunhofer USA
23 Promising Directions Combination of various orthogonal features On/off appliances Combination of orthogonal algorithms Only one publication so far (Liang et al., 21) The curse of false positives Use of techniques known elsewhere Information Fusion Dempster-Shafer Evidence Theory Multi State Variable Permanent Same- Appliances Fraunhofer USA
24 NIALM Accuracy Metrics Only one paper discusses: Liang et al., 21 Can be appliance-related or overall Example: Devices were turned on 8 times over monitoring period. 7 out of 8 detected as events (no classification yet) AND also 15 false positive detections. Out of 7, 5 were correctly classified. What is the accuracy??? Detection accuracy: 5/(7+15) = 58.8% Classification accuracy: 5/7 = 71.4% Overall accuracy: 5/8 = 62.5% Fraunhofer USA
25 NIALM Accuracy Metrics ROC We suggest: Receiver operating characteristic (ROC) Fraunhofer USA
26 Conclusions and Future Trends No complete NIALM solution is available No complete set of robust, widely accepted appliance features is available Using more orthogonal features improves accuracy, albeit with higher false positive rates Using several orthogonal disaggregation algorithms may improve accuracy, but optimal fusion needs to be implemented ROC curves could be used for algorithm benchmarking rather than the ambiguous accuracy Fraunhofer USA
27 Our (Fraunhofer CSE) Research Directions Exploration of device signatures to identify new orthogonal features Development of identification/tracking algorithms suitable for the new features Optimal fusion of new algorithm(s) with the algorithms available for traditional features Testing and benchmarking device, whole home & branch circuit levels Exploration of transient event detection techniques Exploration of signal processing techniques for reconstruction of sources Results to be presented at: Viterbi Algorithm with Sparse Transitions (VAST) for Nonintrusive Monitoring, IEEE Symposium Series on Computational Intelligence, Paris, 211 Nonintrusive appliance load monitoring (NIALM) for energy control in residential buildings, Energy Efficiency in Domestic Appliances and Lighting Conference, Copenhagen, 211 Fraunhofer USA
Adrian Albert. Disaggregation: a Survey
Disaggregation: Brief Survey Adrian Albert What Should We Focus On >75W loads: 99% of consumed US energy Appliances by energy consumed (US) and difficulty to disambiguate from noisy signal. Source: Hart
More informationNonintrusive Load Monitoring using TT-Transform and Neural Networks
Nonintrusive Load Monitoring using TT-Transform and Neural Networks Khairuddin Khalid 1, Azah Mohamed 2 Department of Electrical, Electronic and Systems Engineering Faculty of Engineering and Built Environment,
More informationWireless Best Kept Secret For Now
Wireless Best Kept Secret For Now IoT Event June 2014 Gilles Thonet Managing Director Europe, ZigBee Alliance 2014 ZigBee Alliance. All rights reserved. 1 ZigBee Alliance at 10 Years Who we are Open, global,
More informationAn Approach for Unsupervised Non-Intrusive Load Monitoring of Residential Appliances
An Approach for Unsupervised Non-Intrusive Load Monitoring of Residential Appliances Karim Said Barsim, Roman Streubel, and Bin Yang Institute for Signal Processing and System Theory University of Stuttgart
More informationA new approach for supervised power disaggregation by using a deep recurrent LSTM network
A new approach for supervised power disaggregation by using a deep recurrent LSTM network GlobalSIP 2015, 14th Dec. Lukas Mauch and Bin Yang Institute of Signal Processing and System Theory University
More informationHome Energy Management: Products and Trends
Home Energy Management: Products and Trends Kurt Roth, Ph.D. October 10 th, 2012 Home Energy Management Home Energy Management (HEM): A class of technologies including sensors, control systems, and feedback
More informationEvaluating Classifiers
Evaluating Classifiers Charles Elkan elkan@cs.ucsd.edu January 18, 2011 In a real-world application of supervised learning, we have a training set of examples with labels, and a test set of examples with
More informationBEYOND THE SMART METERS
BEYOND THE SMART METERS Davide Brunelli Dept. of Industrial Engineering DII University of Trento, Italy davide.brunelli@unitn.it How use IoT People in general for different purposes: Industry Production
More informationA Fully Unsupervised Appliance Modelling Framework for NILM
A Fully Unsupervised Appliance Modelling Framework for NILM Bo Liu, Wenpeng Luan, Senior Member, IEEE, Yixin Yu *, Senior Member, IEEE Abstract Most of the existing Non-Intrusive Load Monitoring (NILM)
More informationInternational Journal of Scientific & Engineering Research Volume 9, Issue 6, June ISSN
International Journal of Scientific & Engineering Research Volume 9, Issue 6, June-2018 1569 ELECTRICITY AUDIT INCORPORATING NON-INTRUSIVE LOAD MONITORING Farah Andleeb Siddiqui Electrical Engineering
More informationZigBee extension to support NIALM
ZigBee extension to support NIALM Increased energy efficiency through Non-Intrusive Appliance Load Monitoring (NIALM) 6th European ZigBee Developers Conference June 28, 2012 - Munich Pascal Walther R&D
More informationForward-Looking and Cautionary Statements
Peter F. Volanakis President and Chief Operating Officer February 8, 28 Forward-Looking and Cautionary Statements Certain statements in this presentation constitute forwardlooking statements within the
More informationTCL International Holdings Limited FY2000 Review & Outlook
TCL International Holdings Limited FY2000 Review & Outlook Mr. Vincent Yan, Executive Director March 2001 Agenda Company Background FY2000 Overview PRC Economic Outlook Home Appliances IT Business Corporate
More informationIoT Based Smart Energy Meter Monitoring and Theft Detection for Home Management System
This work by IJARBEST is licensed under Creative Commons Attribution 4.0 International License. Available at https://www.ijarbest.com/archive IoT Based Smart Energy Meter Monitoring and Theft Detection
More informationMIT Samberg Center Cambridge, MA, USA. May 30 th June 2 nd, by C. Rea, R.S. Granetz MIT Plasma Science and Fusion Center, Cambridge, MA, USA
Exploratory Machine Learning studies for disruption prediction on DIII-D by C. Rea, R.S. Granetz MIT Plasma Science and Fusion Center, Cambridge, MA, USA Presented at the 2 nd IAEA Technical Meeting on
More informationArtificial Neural Networks (Feedforward Nets)
Artificial Neural Networks (Feedforward Nets) y w 03-1 w 13 y 1 w 23 y 2 w 01 w 21 w 22 w 02-1 w 11 w 12-1 x 1 x 2 6.034 - Spring 1 Single Perceptron Unit y w 0 w 1 w n w 2 w 3 x 0 =1 x 1 x 2 x 3... x
More informationThe Economics of Delivering Triple Play to the Home
The Economics of Delivering Triple Play Panelists Boyd Peterson Senior Vice President, Consumer Research, Yankee Group Bob Bissell Consultant, CTO Group, BT Kurt Eckles Director of Marketing, Residential
More informationMatrices and Digital Images
Matrices and Digital Images Dirce Uesu Pesco and Humberto José Bortolossi Institute of Mathematics and Statistics Fluminense Federal University 1 Binary, grayscale and color images The images you see on
More informationTutorial 3. Jun Xu, Teaching Asistant csjunxu/ February 16, COMP4134 Biometrics Authentication
Tutorial 3 Jun Xu, Teaching Asistant http://www4.comp.polyu.edu.hk/ csjunxu/ COMP4134 Biometrics Authentication February 16, 2017 Table of Contents Problems Problem 1: Answer the questions Problem 2: Pattern
More informationFrequently Asked Questions
Frequently Asked Questions Q1. SunEdison strongly emphasizes its delivery of renewable electricity services as opposed to solar equipment to its customer base. Why is this an important distinction to draw
More informationDesigning a Smarter and Greener Electric Grid: AS Sensor-Data Driven Approach. Study of Power Consumption
Designing a Smarter and Greener Electric Grid: AS Sensor-Data Driven Approach Study of Power Consumption Monitoring Systems Organisation of the Presentation About CDAC CDAC s component in the project-designing
More informationTotal Building Solution Welcome everyone. Chris Vandebrouck June 2017
Total Building Solution Welcome everyone Chris Vandebrouck Megatrends Challenges that are transforming our world Digitalization By 2020, the digital universe will reach 44 zettabytes a tenfold increase
More informationCloud Networked Robotics and Acceleration Based Sensing
robotics/2012-12-14 Cloud Networked Robotics and Acceleration Based Sensing Miwako Doi, Toshiba Corporation Tokyo, Japan Robotics DTF, OMG Dec. 11, 2012 1 2012 Toshiba Corporation Mega Trends 2012 Toshiba
More informationADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N.
ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. Dartmouth, MA USA Abstract: The significant progress in ultrasonic NDE systems has now
More informationFebruary Investor Presentation
February 2015 Investor Presentation Forward-Looking Statements This document contains forward-looking statements that involve risks and uncertainties. These forward-looking statements include statements
More informationFacilities Evaluation Detailed Standards for New Renewable Energy
1/52 Facilities Evaluation Detailed Standards for New Renewable Energy Small Photovoltaic Inverter (Grid-connected, Stand-alone) New & Renewable Energy Assessment Center, Digital Industry Division, Korea
More informationHome Electric Energy Monitoring System - Design and Prototyping -
Home Electric Energy Monitoring System - Design and Prototyping - João Gil Josué, João Murta Pina and Mário Ventim Neves Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa Monte de Caparica,
More informationThe Different Types of UPS Systems
White Paper 1 Revision 7 by Neil Rasmussen > Executive summary There is much confusion in the marketplace about the different types of UPS systems and their characteristics. Each of these UPS types is
More informationTHE FRAUNHOFER MODEL BRIDGING THE GAP BETWEEN SCIENCE AND INDUSTRY
THE FRAUNHOFER MODEL BRIDGING THE GAP BETWEEN SCIENCE AND INDUSTRY German Science Day in Iran 27 February 2018 Teheran Denise Kaske Business Development Manager Fraunhofer-Gesellschaft Fraunhofer-Gesellschaft,
More informationThis is a licensed product of Ken Research and should not be copied
1 TABLE OF CONTENTS 1. South Korea LED Lighting Market Introduction 2. South Korea LED Lighting Market Value Chain 3. Key Factors Influencing the Success of Companies in LED Lighting Market 4. South Korea
More informationE.ON Strategic Co-Investments Adding value to Start-ups and E.ON Group
E.ON Strategic Co-Investments Adding value to Start-ups and E.ON Group Konrad Augustin Head of SCI US July 2015 An Overview of E.ON At facilities across Europe, Russia, and North America, our more than
More informationNetworks TN, TT, IT networks 3 and 4-phase networks Up to 4 single-phase networks
Memory 256 MB 8 Tariffs Harmonics Pulse inputs and outputs Measurement accuracy 0.5 UMG 96RM Multifunction power analyser Communication (device-specific) Modbus (RTU) Profibus DP V0 Profinet TCP/IP M-Bus
More informationEnergy efficiency within data centers Is your IT organization capitalizing on the latest technology options and best practices?
This is a photographic template your photograph should fit precisely within this rectangle. Energy efficiency within data centers Is your IT organization capitalizing on the latest technology options and
More informationSmarter Energy for a Better Life. Huawei FusionHome Smart Energy Solution. For End Users
Smarter Energy for a Better Life Huawei FusionHome Smart Energy Solution For End Users FusionHome Smart Energy Solution Overview Huawei integrates the latest digital and internet technology with residential
More informationIntegrated Distributed Energy Resources Management Pilot
Integrated Distributed Energy Resources Management Pilot Said Abboudi Chief Business Development Officer BP Global l EMEA December 9, 2008 Outline Jersey Central Power & ight / FirstEnergy Facts BP Global
More informationSIM Home Home of the Future
California Plug Load Research Center Workshop SIM Home Home of the Future November 9, 2016 Linyi Xia California Plug Load Research Center California Institute for Telecommunications and Information Technology
More informationA Neural Network for Real-Time Signal Processing
248 MalkofT A Neural Network for Real-Time Signal Processing Donald B. Malkoff General Electric / Advanced Technology Laboratories Moorestown Corporate Center Building 145-2, Route 38 Moorestown, NJ 08057
More informatione-solutions Benchmarking Technical Report
October 2010 e-solutions Benchmarking Technical Report Broadband for Energy Management Selections from E-Solutions Benchmarking Technical Report for North Carolina Prepared for: e-nc Authority Executive
More informationProData DATA LOGGER. Chapter 03 ProData data logger. Ethernet. Pulse inputs and Pulse outputs. Modbus-Ethernet gateway. Thermistor input.
ProData DATA LOGGER Ethernet Pulse inputs and Pulse outputs Modbus-Ethernet gateway Thermistor input Memory 32 MB Threshold value monitoring 139 Smart and compact: Save energy costs through the universal
More informationInformation Fusion Based Fault Location Technology for Distribution Network
826 JOURNAL OF SOFTWARE, VOL. 6, NO. 5, MA 211 Information Fusion Based Fault Location Technology for Distribution Network Qingle Pang 1, 2 1. School of Information and Electronic Engineering, Shandong
More informationSEQUENTIAL CLUSTERING-BASED EVENT DETECTION FOR NON- INTRUSIVE LOAD MONITORING
ABSTRACT SEQUENTIAL CLUSTERING-BASED EVENT DETECTION FOR NON- INTRUSIVE LOAD MONITORING Karim Said Barsim and Bin Yang Institute of Signal Processing and System Theory, University of Stuttgart, Germany
More informationProData data logger. Ethernet. Pulse inputs and Pulse outputs. Thermistor input. Modbus-Ethernet gateway. Memory 32 MB. Threshold value monitoring
Ethernet Pulse inputs and Pulse outputs Modbus-Ethernet gateway Thermistor input Memory 32 MB Threshold value monitoring ProData data logger 1 Smart and compact: Save energy costs through the universal
More informationMarket Snapshot: Smart TVs & the User Experience
Market Snapshot: Smart TVs & the User Experience A Parks Associates Snapshot Market Snapshot: Smart TVs & the User Experience Streaming media player adoption and smart TV adoption experienced sustained
More informationEditor s Day 2010 Intel Overview
Editor s Day 2010 Intel Overview Continuing our commitment to the highest performance in all we do from product innovation to corporate responsibility is good business. Paul Otellini President and Chief
More informationMicro Control Unit (MCU) Market Report, 2007
Micro Control Unit (MCU) Market Report, 2007 This report provides a detailed study of MCU market in 2007, covering following detailed information. 1. MCU structure, MCU function and MCU applications &
More informationTechnical Advances in the Off-Grid Solar Sector
Technical Advances in the Off-Grid Solar Sector Dr. Arne Jacobson Director, Schatz Energy Research Center Technical Lead, Lighting Global Quality Assurance January 22, 2018 Key Off-Grid Solar Technology
More informationSanDisk Enterprise Storage Solutions
SanDisk Enterprise Storage Solutions Mike Chenery Senior Fellow Deutsche Bank Technology Conference Las Vegas, Nevada September 14, 2011 Forward-looking Statement During our meeting today we will be making
More informationStrong performance in a growing market
KONE CMD 2016 Strong performance in a growing market LARRY WASH, EXECUTIVE VICE PRESIDENT, THE AMERICAS SEPTEMBER 28, 2016 Agenda Market development Business performance Long term growth drivers Smart
More informationApplying Supervised Learning
Applying Supervised Learning When to Consider Supervised Learning A supervised learning algorithm takes a known set of input data (the training set) and known responses to the data (output), and trains
More informationUNIVERSITY OF NORTH CAROLINA AT CHARLOTTE Department of Electrical and Computer Engineering
UNIVERSITY OF NORTH CAROLINA AT CHARLOTTE Department of Electrical and Computer Engineering EXPERIMENT 5 ZENER DIODE VOLTAGE REGULATOR, DIODE CLIPPERS AND CLAMPERS OBJECTIVES The purpose of this experiment
More informationWho is Haier? by Fortune and Forbes the world fastest growing company
Who is Haier? World fastest growing company World s s 4th largest white goods manufacturer World's Most Admired Companies Average Annual Growth 60% 984 994 995 996 997 998 999 2000 200 2002 200 2004 2005
More informationThe SIEM That Gives SIEM a Good Name. Avi Chesla Founder & CTO
The SIEM That Gives SIEM a Good Name Avi Chesla Founder & CTO The Sad Story of SIEM Right idea. Bad execution. SIEM came on the scene 10 years ago, but failed, why? The dot-com boom - attacks grew sky-high
More informationUltra-Accurate Measurement for Temperature and Voltage
Ultra-Accurate Measurement for Temperature and Voltage MEASURpoint is an ultra-accurate instrument for measuring any combination of thermocouple, RTD, and voltage inputs. MEASURpoint is available as a
More informationProfile. Building a New Electric World
Profile 2006 Building a New Electric World 1 A World Leader in Power & Control Headquartered in Palatine, Ill., the North American Operating Division of Schneider Electric had sales of $2.8 billion (U.S.)
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
More informationFraunhofer Centers in the USA
Fraunhofer Centers in the USA Dr. Christina Treeger / Fraunhofer Gesellschaft e.v., Munich Fraunhofer worldwide Gothenburg San José East Lansing Plymouth Londo n Boston Cambridg Newark e Maryland Brussels
More informationSpecific Topics of Smart BME Introduction and Proposals II.
Specific Topics of Smart Grids @ BME Introduction and Proposals II. Session 4, Workshop Energy, Successful R&I in Europe 2014-6th European Networking Event Dr. Dávid RAISZ, Associate Professor Head of
More informationArticle Deducing Energy Consumer Behavior from Smart Meter Data
future internet Article Deducing Energy Consumer Behavior from Smart Meter Data Emad Ebeid 1, *, Rune Heick 2 and Rune Hylsberg Jacobsen 2 1 The Mærsk Mc-Kinney Møller Institute, University of Southern
More informationIFC ENERGY STORAGE MARKET REPORT
IFC ENERGY STORAGE MARKET REPORT DEVELOPMENTS AND OPPORTUNITIES FOR ENERGY STORAGE IN EMERGING MARKETS JANUARY 9, 2016 ANISSA DEHAMNA PRINCIPAL RESEARCH ANALYST NAVIGANT RESEARCH 1 / 2016 NAVIGANT CONSULTING,
More informationCogniSight, image recognition engine
CogniSight, image recognition engine Making sense of video and images Generating insights, meta data and decision Applications 2 Inspect, Sort Identify, Track Detect, Count Search, Tag Match, Compare Find,
More informationFace Recognition using Eigenfaces SMAI Course Project
Face Recognition using Eigenfaces SMAI Course Project Satarupa Guha IIIT Hyderabad 201307566 satarupa.guha@research.iiit.ac.in Ayushi Dalmia IIIT Hyderabad 201307565 ayushi.dalmia@research.iiit.ac.in Abstract
More informationPanel: Enabling Consumer Visibility into Energy Usage
Panel: Enabling Consumer Visibility into Energy Usage Matthew Laherty Cisco Systems Shahram Mehraban Intel Mike Ballard Microchip Moderator Clayton Pillion Microchip Wendy Furchak Verizon Wireless A New
More informationEvaluating Battery Run-down Performance Using the Agilent 66319D or 66321D with Option # A Device Characterization Software
Evaluating Battery Run-down Performance Using the Agilent 66319D or 66321D with Option #053 14565A Device Characterization Software Application Note 1427 The Agilent 66319D and 66321D Mobile Communications
More informationHarder case. Image matching. Even harder case. Harder still? by Diva Sian. by swashford
Image matching Harder case by Diva Sian by Diva Sian by scgbt by swashford Even harder case Harder still? How the Afghan Girl was Identified by Her Iris Patterns Read the story NASA Mars Rover images Answer
More informationIncreasing Data Center Efficiency by Using Improved High Density Power Distribution
Increasing Data Center Efficiency by Using Improved High Density Power Distribution By Neil Rasmussen White Paper #128 Revision 1 Executive Summary A new approach to power distribution for high density
More informationClassification of Hyperspectral Breast Images for Cancer Detection. Sander Parawira December 4, 2009
1 Introduction Classification of Hyperspectral Breast Images for Cancer Detection Sander Parawira December 4, 2009 parawira@stanford.edu In 2009 approximately one out of eight women has breast cancer.
More informationVP ELECTRONIQUE MASSY
Rev: 86-653/1 Date: 28 Oct 08 2008 Voltech Instruments. All rights reserved. Contents 1 What is Standby Power? 2 Why is standby power important? 3 Which appliances consume standby power? 4 How to measure
More informationSwift Responses with Accurate Measurement
Swift Responses with Accurate Measurement The /1503D are equipped with the excellent transient recovery time, which can, in less than 40us, recover the output voltage to within 100mV of the previous voltage
More informationSamsung Electronics Announces Fourth Quarter & FY 2015 Results
Samsung Electronics Announces Fourth Quarter & FY 2015 Results SEOUL, Korea January 28, 2016 Samsung Electronics announced financial results for the fourth quarter ended December 31, 2015. Samsung posted
More informationData Mining Classification: Alternative Techniques. Imbalanced Class Problem
Data Mining Classification: Alternative Techniques Imbalanced Class Problem Introduction to Data Mining, 2 nd Edition by Tan, Steinbach, Karpatne, Kumar Class Imbalance Problem Lots of classification problems
More informationInfinisolar V Hybrid-On Grid Inverter with Energy Storage
Infinisolar V Hybrid-On Grid Inverter with Energy Storage Pure sine wave output Self-consumption and Feed-in to the grid Programmable supply priority for PV, Battery or Grid User-adjustable charging current
More informationServer Technology Inc.
Server Technology Inc. Power Efficiency Gains by Deploying 415 VAC Power Distribution in North American Data Centers White Paper STI-100-008 2011-Sept-22 Headquarters Server Technology, Inc. 1040 Sandhill
More informationSolutions for office buildings
Solutions for office buildings Office buildings are a mess! They use way too much energy They are very hard to monitor They are not flexible They generate dissatisfaction They have a strong negative impact
More informationGLOBAL SOLAR OUTLOOK Dr. Shawn Qu Charmain and CEO
GLOBAL SOLAR OUTLOOK Dr. Shawn Qu Charmain and CEO Solar Power International, Las Vegas September 14, 2016 CSIQ NASDAQ Listed Company Overview! Founded in Ontario, 2001! Listed on NASDAQ (CSIQ) in 2006!
More informationLoopy Belief Propagation
Loopy Belief Propagation Research Exam Kristin Branson September 29, 2003 Loopy Belief Propagation p.1/73 Problem Formalization Reasoning about any real-world problem requires assumptions about the structure
More informationFACTS AND OPPORTUNITIES IN BRAZIL. Gartner IT Security Summit Washington DC, June 2008
FACTS AND OPPORTUNITIES IN BRAZIL Gartner IT Security Summit Washington DC, June 2008 OUR OBJECTIVE TODAY Raise your awareness that there are several Brazilian IT Services and Solutions Providers that
More informationUnited States Smart Grid: Market Forecast ( )
northeast group, llc United States Smart Grid: Market Forecast (2017 2027) October 2017 www.northeast-group.com US Smart Grid: Market Forecast (2017-2027) The United States has one of the most mature smart
More informationConnected & Smart Home Research Package
TECHNOLOGY, MEDIA & TELECOMMUNICATION KEY COMPONENTS Intelligence Services Real-time access to continually updated market data and forecasts, analyst insights, topical research reports and analyst presentations.
More informationGraph Matching Iris Image Blocks with Local Binary Pattern
Graph Matching Iris Image Blocs with Local Binary Pattern Zhenan Sun, Tieniu Tan, and Xianchao Qiu Center for Biometrics and Security Research, National Laboratory of Pattern Recognition, Institute of
More informationFinancial Information
Financial Information sales led by improving momentum in new economies New economies: 10 points better than mature countries Solution and services: 6 points above group average Demand in mature countries
More informationThe Future of Home Automation
This report examines how consumers and governments are creating a booming market for 'smart home' devices. It analyzes the companies, technologies, and products behind automation in energy, entertainment,
More informationA Class of Instantaneously Trained Neural Networks
A Class of Instantaneously Trained Neural Networks Subhash Kak Department of Electrical & Computer Engineering, Louisiana State University, Baton Rouge, LA 70803-5901 May 7, 2002 Abstract This paper presents
More information3M China Overview. Stephen Shafer Vice President & Managing Director Greater China Area. December 12, 2017
3M China Overview Stephen Shafer Vice President & Managing Director Greater China Area December 12, 2017 1 Agenda The attractive China opportunity How our Playbook is helping us win in China Our 2018 outlook
More informationChris Hickman President, Energy Services
focused on the part of the energy web that can be built out now, for profit, with near-term ROI and a growth path that could eventually produce macro-level network effects. Chris Hickman President, Energy
More informationImage Compression with Singular Value Decomposition & Correlation: a Graphical Analysis
ISSN -7X Volume, Issue June 7 Image Compression with Singular Value Decomposition & Correlation: a Graphical Analysis Tamojay Deb, Anjan K Ghosh, Anjan Mukherjee Tripura University (A Central University),
More informationDifferentiating with services
KONE CMD 2017 Differentiating with services HUGUES DELVAL, EXECUTIVE VICE PRESIDENT, SERVICE BUSINESS SEPTEMBER 29, 2017 AGENDA STRONG PERFORMANCE IN SERVICES EXCELLENT GROWTH OPPORTUNITIES FURTHER IMPROVING
More informationCyber Security in Smart Commercial Buildings 2017 to 2021
Smart Buildings Cyber Security in Smart Commercial Buildings 2017 to 2021 Published: Q2 2017 Cyber Security in Smart Buildings Synopsis 2017 This report will help all stakeholders and investors in the
More informationUltra-Accurate Measurement for Temperature and Voltage
Ultra-Accurate Measurement for Temperature and Voltage MEASURpoint is an ultra-accurate instrument for measuring any combination of thermocouple, RTD, and voltage inputs. MEASURpoint is available as a
More informationINTEGRATION OF DR INTO TITLE 20 FOR LAPTOP BATTERIES
Design & Engineering Services INTEGRATION OF DR INTO TITLE 20 FOR LAPTOP BATTERIES AND DOCKING STATIONS Phase1: Demand Response Potential DR 09.05.13 Report Prepared by: Design & Engineering Services Customer
More informationSmart Gas Grids. Manuel Sánchez, Ph.D. Team Leader Smart Grids Directorate General for Energy European Commission
Smart Gas Grids Manuel Sánchez, Ph.D. Team Leader Smart Grids Directorate General for Energy European Commission Smart Gas Grids in practice Brussels 1st December 2015 Energy Low carbon economy requires
More informationTraining Algorithms for Robust Face Recognition using a Template-matching Approach
Training Algorithms for Robust Face Recognition using a Template-matching Approach Xiaoyan Mu, Mehmet Artiklar, Metin Artiklar, and Mohamad H. Hassoun Department of Electrical and Computer Engineering
More informationSmartSacramento Distribution Automation
SmartSacramento Distribution Automation Presented by Michael Greenhalgh, Project Manager Lora Anguay, Sr. Project Manager Agenda 1. About SMUD 2. Distribution Automation Project Overview 3. Data Requirements
More informationSIMEAS Q80 quality recorder: Voltage quality starts with measurement.
SIMEAS Q80 quality recorder: Voltage quality starts with measurement. Answers for energy. 1 Energy with quality crucial for utilities and for industry A reliable supply of electrical power is the backbone
More informationAn Object Detection System using Image Reconstruction with PCA
An Object Detection System using Image Reconstruction with PCA Luis Malagón-Borja and Olac Fuentes Instituto Nacional de Astrofísica Óptica y Electrónica, Puebla, 72840 Mexico jmb@ccc.inaoep.mx, fuentes@inaoep.mx
More informationUser Activity Recognition Based on Kalman Filtering Approach
User Activity Recognition Based on Kalman Filtering Approach EEC 592, Prosthesis Design and Control Final Project Report Gholamreza Khademi khademi.gh@gmail.com December 2, 214 Abstract Different control
More informationAn Integrated Pan-European Research Infrastructure for Validating Smart Grid Systems
1 An Integrated Pan-European Research Infrastructure for Validating Smart Grid Systems Thomas Strasser Coordinator H2020 ERIGrid Electric Energy Systems Center for Energy AIT Austrian Institute of Technology
More informationNew Approaches for EEG Source Localization and Dipole Moment Estimation. Shun Chi Wu, Yuchen Yao, A. Lee Swindlehurst University of California Irvine
New Approaches for EEG Source Localization and Dipole Moment Estimation Shun Chi Wu, Yuchen Yao, A. Lee Swindlehurst University of California Irvine Outline Motivation why EEG? Mathematical Model equivalent
More information10-701/15-781, Fall 2006, Final
-7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly
More informationCOMPUTER AND ROBOT VISION
VOLUME COMPUTER AND ROBOT VISION Robert M. Haralick University of Washington Linda G. Shapiro University of Washington A^ ADDISON-WESLEY PUBLISHING COMPANY Reading, Massachusetts Menlo Park, California
More informationWiser for C-Bus Automation Controller
Wiser for C-Bus Automation Controller Residential IP network controller for automation & control in homes & small commercial buildings clipsal.com/c-bustrade Wiser for C-Bus Automation Controller 3 Make
More information