Appliances Load Pattern Reconstruction from Adaptive Delta-Driven Sampled Smart Meter Data

Abstract

In recent days the interest in the usage of smart meters is raising. It is evident from the widespread use of smart meters in contemporary society. The stakeholders in the smart grid must profit from the gathering and processing of fine-grained metering data. Time invariance characterizes the classical data sampling method. As a result, a significant volume of unnecessary data is gathered, sent, and analyzed. A method of adaptive delta-driven sampling (ADDS) of the smart meter data is proposed. It compensates the aforementioned shortfall and can lead towards a significant real-time compression without losing pertinent information. Subsequently, the compressed form of data can be efficiently processed, analyzed, stored and transmitted. It promises a significant transmission and computational effectiveness with a diminished latency. It is shown that the devised form of compressed data can be effectively reconstructed using a low complexity reconstruction algorithm. The reconstruction error is measured in terms of the root mean square error (RMSE) and the mean absolute error (MAE). The applicability is tested using the power consumption patterns of coffee machines, computer stations, fridges and freezers. The proposed solution attains an overall compression gain of 1.84-times, 2.49-times, 7.55-times respectively for the coffee machine, computer stations, and fridges and freezers. Moreover, the obtained values of RMSE and MAE confirm an appropriate reconstruction using the devised method.