Making home energy usage transparent for households using smart meters

Abstract

This article describes an approach for a system, which helps to increase energy efficiency in households by providing more transparency of energy consumption on single device level. The main idea is to analyze energy consumption using a smart meter and break it down into its individual characteristic components using an algorithm. Having such data, an online energy efficiency coach can provide households with personalized advice on saving energy on a single-device level with minimal time effort and great social experience. In order to develop such an algorithm, a simulation environment was created, which allows generating a huge number of virtual households based on real measurements of single devices. This article describes the simulation environment, how data is measured and collected and how the platform is set up. Smart home; energy transparency; smart meter; web interface; energy saving; social integration

The Concept of an Interactive Platform for Real Time Energy Consumption Analysis in a Complex Urban Environment

“…Model-based techniques represent the classical approach, where curve-fitting procedures, linear regression, multiplicative autoregressive models and state-space models have been mainly used due to their transparency where the end-user is able to examine its operational behaviour. Rule-based systems have primarily focused on short term forecasting [25][26][27].…”

“…One of the possibilities is to use an Incremental Pattern Characterization Learning (IPCL) algorithm, which is able to incrementally characterize patterns in energy consumption. This also features incremental knowledge accumulation that maintains a layer of summarized representations of patterns characterized from each phase and associates this layer with new learning [26]. Other possibilities include the use of a multi-layer artificial neural network based on a BP algorithm or more sophisticated genetic algorithms and RBF Neural Networks [28].…”

Performance Optimization LoRa Network by Artificial Bee Colony Algorithm to Determination of the Load Profiles in Dwellings

“…In this research, the LoRa Low Power Wide Area Network (LPWAN) network has been chosen, with transmission distances of up to 10 km. Comparison of standard load profiles with those obtained with SMs [27] Power consumption Optical sensor to SMs Analysis of measured data to improve electrical energy consumption [28] Energy consumption Commercial SMs Data analysis and clustering [29] Energy consumption ZigBee wireless Data analysis in different scenarios [30] Energy consumption Commercial SMs study and estimation of indicators of load profiles in dwellings [31] Energy consumption Commercial SMs Measure time 15 min Obtaining and analysis of load profiles in houses in Evora (Portugal) [32] Energy consumption Commercial SMs Measure time 15 min Obtaining and analysis of load profiles in 1000 houses in Poland [33] Energy consumption Commercial SMs Measure time 30 min Smart meter dataset Data Analysis and Clustering [34] Energy consumption Commercial SMs…”