Home Appliance Load Modeling From Aggregated Smart Meter Data

Abstract

Abstract-With recent developments in the infrastructure of smart meters and smart grid, more electric power data is available and allows real time easy data access. Modeling individual home appliance loads is important for tasks such as non-intrusive load disaggregation, load forecasting, and demand response support. Previous methods usually require sub-metering individual appliances in a home separately to determine the appliance models, which may not be practical, since we may only be able to observe aggregated real power signals for the entire-home through smart meters deployed in the field. In this paper, we propose a model, named Explicit-Duration Hidden Markov Model with differential observations (EDHMM-diff), for detecting and estimating individual home appliance loads from aggregated power signals collected by ordinary smart meters. Experiments on synthetic data and real data demonstrate that the EDHMM-diff model and the specialized forward-backward algorithm can effectively model major home appliance loads.

Load Decomposition at Smart Meters Level Using Eigenloads Approach

“…Based on this study, the data available from the smart meters have a high potential to be useful for load disaggregation purposes. The utilization of smart meters data for load disaggregation has been recently reported, for example, in [10] and [11]. The smart meter data was utilized in [10] and an Explicit-Duration Hidden-Markov Model with differential observations was applied to the data for detecting and estimating individual home appliance loads.…”

“…The utilization of smart meters data for load disaggregation has been recently reported, for example, in [10] and [11]. The smart meter data was utilized in [10] and an Explicit-Duration Hidden-Markov Model with differential observations was applied to the data for detecting and estimating individual home appliance loads. An event windowbased mechanism was proposed in [11] which uses the power waveforms and clusters the signatures based on some features in a selected time window.…”

Investigation of Load Frequency Relief From Field Measurements and Its Impact on Contingency Reserve Evaluation

“…The implication of voltage in load modelling has been widely considered in the literature [5][6][7][8][9][10][11][12][13][14][15][16][17]. Different techniques have been developed and reported in this regard.…”

“…Different techniques have been developed and reported in this regard. They include signature identification of loads [5,6], dynamic modelling of loads for studying power system damping [7,8], linear, polynomial and exponential representations of loads [9], composite models via measurement approach [10][11][12], characterisation and profiling of load patterns [13][14][15] and Markov models [16,17]. It is to be mentioned that the above papers mainly focused on the voltage dependency of loads.…”

Quasi real-time ZIP load modeling for Conservation Voltage Reduction of smart distribution networks using disaggregated AMI data

“…Diverse mathematical techniques have been presented for load disaggregation in recent year [52]- [62]. One of the common mathematical disaggregation techniques is Non-Intrusive Load Monitoring (NILM) [52], [55], [57]- [58], [60]- [61].…”