Deokwoo Jung Estimating Building Consumption Breakdowns using ON/OFF State Sensing and Incremental Sub-Meter Deployment Deokwoo Jung and Andreas Savvides Embedded Networks & Applications Lab (ENALAB) Yale University Nov 4, 2010
Deokwoo Jung Nov 4, 2010 Sensing Loads on Electricity Network Living Room Kitchen Bed Room Breaker Box Electricity Network Electric Meter Electrical Outlet How to Estimate Electrical Loads of Appliances ?
Deokwoo Jung Electricity Energy Monitoring Systems Direct Monitoring : Expensive and brute-force method Watts up?.Net –$ 230 –Internet enabled –Power switching Watts up? –$100-$130 –Data Logging Kill-A-Watt EZ –$45 –Data display only Indirect Monitoring – Total Load Disaggregation + Load Signature Detection NALM (Hart.et.al): Nonintrusive Appliance Load Monitoring A ElectriSense (Sidhant et.all) : Single-Point Sensing Using EMI for Electrical Event Detection and Classification in the Home Nov 4, 2010
Deokwoo Jung Load Disaggregation Data Flow Event Detection Load Disaggregation Partial Load Information High frequency electromagnetic interference Edge detection Heat Vibration Light intensity Voltage and current waveforms at Electrical outlets or Power entry point How do we compute the load disaggregation ? ON/OFF state e.g. Total Power consumption Nov 4, 2010
Deokwoo Jung Nov 4, 2010 The Diverse Nature of Loads Resistive vs. Inductive -> Short-term property Stationary vs. Non-stationary -> Long-term property Inductive Resistive Non- Stationary Stationary Short-term property Long-term property Refrigerator Bulb heater Washing Machine TV Air Conditioner Dehumid ifier Electri c Kettle Water Pump Hard to measure power consumption Hard to estimate energy breakdown Laptop DVD Player
Deokwoo Jung Nov 4, 2010 Our Approach: Energy Breakdown per Unit Time Actual Power Consumption Profile Actual Average Power Consumption Estimated Average Power Consumption Estimation Error Example appliance: LCD TV Estimation Period k-1 Estimation Period k Estimation Period k+1 Instead of instantaneous measurements, use average consumption over a time window
Deokwoo Jung Nov 4, 2010 Problem Setup Goal: Estimate the average power consumption for a time window Select an appropriate time window to get the best estimate of energy consumption Time Appliance Consumption fluctuation properties Three Tier Tree Network
Deokwoo Jung Nov 4, 2010 Prototype System Implementation TED 5000 Monitor BehaviorScope Portal Active RFID Dry Contact Sensor One Energy Meter and ON/OFF Sensors Consumption measurements Appliance ON/OFF Information
Deokwoo Jung Nov 4, 2010 Main Idea ON/OFF sequence of appliances occurs between the worst (Perfectly Synch) and the best case (Perfectly Desynch) appliance A appliance B Worst CaseBest CaseObserved Binary Data Approach – Variant of Weighted Linear Regression –Accounting for Diversity Design Optimal Weight Matrix, W –Metric Driven Data Selection Regression data set is adaptively chosen according to active power consumption property, stationary vs. non-stationary Using Prediction Metric for Estimation Error
Deokwoo Jung Nov 4, 2010 Problem Formulatio n Sample Index On/Off state of TV On/Off state of Microwave On/Off state of Lamp The Average of Power meter measurement (Watt) # of samples observed Objective Function: Solve Opt. Problem:
Deokwoo Jung Nov 4, 2010 Designing Weights and Selecting Appropriate Time Window No WeightUnit Sum MatrixEstimated Variance Sum Matrix Exact Variance Sum Matrix W Optimal Choice of Weight Matrix, W Account for (Non-) Stationary Property –Stationary Load : larger window of measurements is better –Non-Stationary Load: small window of measurements is better –Automatically select to use either of the entire estimation periods (Cumulative Data) or only the current period (Current Data)
Deokwoo Jung Nov 4, 2010 Evaluation - Case Study A small electricity Network with single power meter Collecting data from 12 appliances in one-bedroom Apt from Thu-Sat A large variation of energy load –the heater accounts for more than 60% of the total energy consumption –the laptop consumed the least, less than 1% of the total load. The hourly energy consumption ground truth in one-bedroom apartment from an experiment from Thursday to Saturday Daily energy consumption ground truth in one-bedroom apartment from an experiment from Thursday to Saturday Histogram of power consumption of appliances during their On state The number of meter samples observed given composite binary states
Deokwoo Jung Nov 4, 2010 Evaluation - Case Study : A small electricity Network with single power meter Estimated hourly energy consumption profile of each appliance –Average 10% of relative error
Deokwoo Jung Nov 4, 2010 Performance over Estimation Periods With different weight matrix Lower bound Algorithm performance No Weight Unit Sum Weight
Deokwoo Jung Nov 4, 2010 Performance over Estimation Periods With different data selection schemes Lower bound Algorithm performance Current Data Selection Cumulative Data Selection
Deokwoo Jung Nov 4, 2010 Performance by Data Selection, Weight Matrix, and Estimation Period The maximum, minimum, and average value of relative error of active power consumption for all estimation periods with various combination of weighted matrix and data selection schemes
Deokwoo Jung Nov 4, 2010 Increasing Accuracy on Larger Networks with Additional Meters How many power meters we need and where should place them? –Tree Decomposition Problem Depending on sensor duty cycles –Combinatorial Optimization Problem Use Stochastic Search Algorithm : Simulated Annealing Cost function of Simulated Annealing – Evaluated against the initial solution, Z 0 =(1,1…,1) : Placing meters on all available electrical outlets. Node EfficiencyEstimation Quality Weight Coefficient: # of meters vs performance ?
Deokwoo Jung Nov 4, 2010 Evaluation - Case Study 2: A large scale electricity network with meter deployment Performance evaluation by increasing the number of Apt units from 1 to 12 With a single power meter for a large electricity network Meter Deployment by Algorithm Compared by random deployment –For λ= 0.5, x10 in performance –Or reduce x 2~3 in # of meters –λ = 0 Single power meter –λ = 1 Full deployment
Deokwoo Jung Conclusions and Future Work Developed an energy breakdown estimation algorithm for a single power meter and the knowledge of ON/OFF states 10% of relative error for 12 home appliances and a single power meter Developed an algorithm for optimally placing additional power meters to improve estimation accuracy in large networks Deployment algorithm can reduce 3-4 times of the number of power meter for the simulation of 12 households Future work: - Experimental deployment on a Yale building in January Handle incomplete binary state sensing - Leverage history information and user inputs Nov 4, 2010
Deokwoo Jung Discussion & Comparison with Related Work The question on high frequency systems makes some sense. Assuming that you can detect signatures, if the frequency of measurement is high enough you may have enough information to computer itemized consumption. The key argument to make is that this approach could work today with existing low-frequency meters. The central meter in a home only has to same using 1Hz. Also, in the home, we may be able to do this without any additional hardware by just completing forms on a GUI. While we work out details for a journal version it is important to identify and propose the next problem to solve on load disaggregation Nov 4, 2010