An Event Matching Energy Disaggregation Algorithm Using Smart Meter Data

Abstract

Energy disaggregation algorithms disintegrate aggregate demand into appliance-level demands. Among various energy disaggregation approaches, non-intrusive load monitoring (NILM) algorithms requiring a single sensor have gained much attention in recent years. Various machine learning and optimization-based NILM approaches are available in the literature, but bulk training data and high computational time are their respective drawbacks. Considering these drawbacks, we devised an event matching energy disaggregation algorithm (EMEDA) for NILM of multistate household appliances using smart meter data. Having limited training data, K-means clustering was employed to estimate appliance power states. These power states were accumulated to generate an event database (EVD) containing all combinations of appliance operations in their various states. Prior to matching, the test samples of aggregate demand events were decreased by event-driven data compression for computational effectiveness. The compressed test events were matched in the sorted EVD to assess the contribution of each appliance in the aggregate demand. To counter the effects of transient spikes and/or dips that occurred during the state transition of appliances, a post-processing algorithm was also developed. The proposed approach was validated using the low-rate data of the Reference Energy Disaggregation Dataset (REDD). With better energy disaggregation performance, the proposed EMEDA exhibited reductions of 97.5 and 61.7% in computational time compared with the recent smart event-based optimization and optimization-based load disaggregation approaches, respectively.

Adaptive threshold event detection method based on standard deviation

“…The researchers of a study [31] combined an event-based approach with an optimization-based approach to reduce the computation time of the optimization algorithm, with a significant improvement on small training sets. Liaqat et al (2022) [32] designed an Event Matching Energy Disaggregation Algorithm to evaluate the weight of each device in the aggregated load data by matching the test events to an Event Database. This method significantly reduces the computation time compared to the optimization algorithm.…”

Regularized NCA based Prominent Feature Selection for Load Identification Using Boosted Tree Classifier

“…Non-intrusive load monitoring (NILM) has been a growing field of research in recent years. NILM provides energy consumption for all the target appliances by using a single measurement of their aggregate demand usually obtained from the energy meter [1]. Once the load has been disaggregated through a proper NILM technique, the disaggregated data can be used for flexibility assessment [2], load demand forecasting [3], energy management system [4][5][6], etc.…”

Monitoring Energy and Power Quality of the Loads in a Microgrid Laboratory Using Smart Meters

“…The management and control of microgrids require monitoring the status of various components of the system. A pivotal part is upgrading energy effectiveness by providing detailed, real-time information on electricity consumption [7][8][9][10]. These advanced devices not only provide accurate measurements of electricity consumption, but also enable the implementation of algorithms for the optimal operation of the microgrid [10].…”

“…A pivotal part is upgrading energy effectiveness by providing detailed, real-time information on electricity consumption [7][8][9][10]. These advanced devices not only provide accurate measurements of electricity consumption, but also enable the implementation of algorithms for the optimal operation of the microgrid [10]. For instance, non-intrusive load monitoring (NILM) techniques are commonly employed to identify the energy consumption patterns of specific appliances and to detect the operational state (on/off) of devices by analyzing the overall power consumption [11,12].…”