Occupancy-aided energy disaggregation

Tang, Guoming; Ling, Zhen; Li, Fengyong; Tang, Dian; Tang, Jiuyang

doi:10.1016/j.comnet.2016.11.019

Cited by 15 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous machine learning and signal processing methods have been investigated to solve the NILM problem, including stochastic finite state machines (Hidden Markov Model and its variants) [19,20], support vector machine (SVM) [21], decision tree [21,22], dynamic time warping [22], k-nearest neighbours (K-NN) [16,21,[23][24][25], sparse coding [26,27], neural networks [9,[28][29][30], graph signal processing (GSP) [18,31], and optimisation via learning of appliance models and occupancy information [32][33][34][35][36]. Furthermore, advanced hybrid approaches have been proposed for improving core NILM performance, e.g., k-means clustering based training followed by disaggregation using SVM [37], GSP with result refinement using simulated annealing [17], deep neural network utilised to learn deeper and multiple layers of sparse signal representation [38].…”

Section: Introductionmentioning

confidence: 99%

Non-intrusive load disaggregation solutions for very low-rate smart meter data

Zhao

Stanković

2020

Applied Energy

View full text Add to dashboard Cite

With the active large-scale roll-out of smart metering worldwide, details about the type of smart meter data that will be available for analysis are emerging.Consequently, focus has steadily been shifting from analysis of high-rate power readings (usually in kHz to MHz) to low-rate power readings (sampled at 1 to 60 sec) and very low-rate meter readings of the order of 15-60 minutes. This has triggered renewed research into practical non-intrusive load disaggregation of low-to very-low granularity meter readings to address challenges not addressed by existing disaggregation approaches, namely, indistinct appliance ON/OFF transitions, increased likelihood of overlapping appliance usage within a sample and noise due to unknown appliances. In this paper, focusing on smart meter readings at hourly resolution, three load disaggregation solutions are proposed based on: (i) optimisation (minimisation of error between aggregate and disaggregated loads), (ii) graph signal processing and (iii) convolutional neural network. These are benchmarked with state-of-the-art approaches, based on factorial hidden Markov model and combinatorial optimisation implemented in the NILMTK toolbox, and discriminative disaggregation sparse coding. The hourly electricity profile data is obtained from real-world active power readings from the REFIT dataset 1 over a period of longer than one year. All proposed

show abstract

Section: Introductionmentioning

confidence: 99%

Non-intrusive load disaggregation solutions for very low-rate smart meter data

Zhao

Stanković

2020

Applied Energy

View full text Add to dashboard Cite

show abstract

“…With this information, a data mining program can extract the behavior and rules that a resident follows during the day related to their home appliances. There are a lot of works that try to identify the electronic appliances in a home in order to predict the future use of the device by a user; for examples, see Brown et al [3], Chen et al [4], and Tang et al [5]. The main objective of these investigations is to use energy efficiently.…”

Section: Introductionmentioning

confidence: 99%

Multi-Agent Recommendation System for Electrical Energy Optimization and Cost Saving in Smart Homes

et al. 2019

View full text Add to dashboard Cite

The European Union Establishes that for the next few years, a cleaner and more efficient energy system should be used. In order to achieve this, this work proposes an energy optimization method that facilitates the achievement of these objectives. Existing technologies allow us to create a system that optimizes the use of energy in homes and offers some type of benefit to its residents. Specifically, this study has developed a recommendation system based on a multiagent system that allows to obtain consumption data from electronic devices in a home, obtain information on electricity prices from the Internet, and provide recommendations based on consumption patterns of users and electricity prices. In this way, the system recommends new hours in which to use the appliances, offering the economic benefit that it would propose recommendations for the user. In this way, it is possible to distribute and optimize the use of energy in homes and reduce the peaks in electricity consumption. The system provides encouraging results in order to resolve the problem proposed by the European Union by optimizing the use of energy among different hours of the day and saving money for the customer.

show abstract

“…These two groups are environmental agents and processing agents. Belley et al [3] Lin et al [4] De Baets et al [1] Tang et al [5] Brown et al [6] Liang et al [7] Lee et al [8] Chen et al [9] Chen and Tan [10] Batra et al [11] Our proposal Use NILM techniques (i) Environmental Agents. These agents communicate with the measuring systems that are connected to the global system.…”

Section: Proposed Architecturementioning

confidence: 99%

“…The researchers Tang et al [5] suggested that the state of the building must be taken into account; it can be either occupied or unoccupied. Thus, a system that is capable of considering these two situations will not operate when there are no people in the building.…”

Section: Introductionmentioning

confidence: 99%

Dealing with Demand in Electric Grids with an Adaptive Consumption Management Platform

et al. 2018

View full text Add to dashboard Cite

The control of consumption in homes and workplaces is an increasingly important aspect if we consider the growing popularity of smart cities, the increasing use of renewable energies, and the policies of the European Union on using energy in an efficient and clean way. These factors make it necessary to have a system that is capable of predicting what devices are connected to an electrical network. For demand management, the system must also be able to control the power supply to these devices. To this end, we propose the use of a multiagent system that includes agents with advanced reasoning and learning capacities. More specifically, the agents incorporate a case-based reasoning system and machine learning techniques. Besides, the multiagent system includes agents that are specialized in the management of the data acquired and the electrical devices. The aim is to adjust the consumption of electricity in networks to the electrical demand, and this will be done by acting automatically on the detected devices. The proposed system provides promising results; it is capable of predicting what devices are connected to the power grid at a high success rate. The accuracy of the system makes it possible to act according to the device preferences established in the system. This allows for adjusting the consumption to the current demand situation, without the risk of important home appliances being switched off.

show abstract

Occupancy-aided energy disaggregation

Cited by 15 publications

References 14 publications

Non-intrusive load disaggregation solutions for very low-rate smart meter data

Non-intrusive load disaggregation solutions for very low-rate smart meter data

Multi-Agent Recommendation System for Electrical Energy Optimization and Cost Saving in Smart Homes

Dealing with Demand in Electric Grids with an Adaptive Consumption Management Platform

Contact Info

Product

Resources

About