This thesis presents the development of techniques which enable appliance recognition in an Advanced Electricity Meter (AEM) to aid individuals reduce their domestic electricity consumption. The key aspect is to provide immediate and disaggregated information, down to appliance level, from a single point of measurement. Three sets of features including the short term time domain, time dependent finite state machine behaviour and time of day are identified by monitoring step changes in the power consumption of the home. Associated with each feature set is a membership which depicts the amount to which that feature set is representative of a particular appliance. These memberships are combined in a novel framework to effectively identify individual appliance state changes and hence appliance energy consumption. An innovative mechanism is developed for generating short term time domain memberships. Hierarchical and nearest neighbour clustering is used to train the AEM by generating appliance prototypes which contain an indication of typical parameters. From these prototypes probabilistic fuzzy memberships and possibilistic fuzzy typicalities are calculated for new data points which correspond to appliance state changes. These values are combined in a weighted geometric mean to produce novel memberships which are determined to be appropriate for the domestic model. A voltage independent feature space in the short term time domain is developed based on a model of the appliance’s electrical interface. The components within that interface are calculated and these, along with an indication of the appropriate model, form a novel feature set which is used to represent appliances. The techniques developed are verified with real data and are 99.8% accurate in a laboratory based classification in the short term time domain. The work presented in this thesis demonstrates the ability of the AEM to accurately track the energy consumption of individual appliances.

Cette thèse présente une méthode pour désagréger les appareils électriques dans le profil des bâtiments résidentiels de charge. Au cours des dernières années, la surveillance de l’énergie a obtenu beaucoup de popularité dans un environnement privé et industriel. Avec des algorithmes de la désagrégation, les données mesurées à partir de soi-disant compteurs intelligents peuvent être utilisés pour fournir de plus amples informations de la consommation d’énergie. Une méthode pour recevoir ces données est appelé non-intrusifs charge identification. La majeure partie de la thèse peut être divisée en trois parties. Dans un premier temps, un système de mesure propre a été développé et vérifié. Avec ce système, les ensembles de données réelles peuvent être générés pour le développement et la vérification des algorithmes de désagrégation. La deuxième partie décrit le développement d’un détecteur de flanc. Différentes méthodes sont présentées et évaluées, avec lequel les temps de commutation des appareils peuvent être détectés dans le profil de la charge. La dernière partie décrit un procédé de classification. Différents critères sont utilisés pour la classification. Le classificateur reconnaît et étiquette les appareils individuels de la courbe de charge. Pour les classifications différentes structures de réseaux de neurones artificiels sont comparés. / This thesis presents a method to disaggregate electrical appliances in the load profile of residential buildings. In recent years, energy monitoring has obtained significantly popularity in private and industrial environment. With algorithms of the disaggregation, the measured data from so-called smart meters can be used to provide more information of the energy usage. One method to receive these data is called non-intrusive appliance load monitoring.The main part of the thesis can be divided into three parts. At first, an own measurement system was developed and verified. With that system, real data sets can be generated for the development and verification of the disaggregation algorithms. The second part describes the development of an event detector. Different methods are presented and evaluated, with which the switching times of the appliances can be detected in the load profile. The last part describes a classification method. Different features are used for the classification. The classifier recognizes and labels the individual appliances in the load profile. For the classification different structures of artificial neural network (ANN) are compared.

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-08-06T18:59:56Z No. of bitstreams: 1 PEDRO YÓSSIS SILVA BARBOSA - DISSERTAÇÃO PPGCC 2014..pdf: 17089632 bytes, checksum: 4623777c293a51dbb1b392f37d2dd75e (MD5) / Made available in DSpace on 2018-08-06T18:59:56Z (GMT). No. of bitstreams: 1 PEDRO YÓSSIS SILVA BARBOSA - DISSERTAÇÃO PPGCC 2014..pdf: 17089632 bytes, checksum: 4623777c293a51dbb1b392f37d2dd75e (MD5) Previous issue date: 2014-02-27 / Capes / Companhias de energia começaram a substituir os medidores de energia tradicionais pelos Smart Meters, que podem transmitir valores de consumo para as companhias em curtos intervalos de tempo. Com uma insfraestrutura de Smart Meters, existem muitas motivações para as concessionárias de energia coletarem dados de consumo em alta resolução. Entretanto, isto implica em informações bastante detalhadas sobre os consumidores sendo monitoradas. Consequentemente, um problema sério precisa ser resolvido: como preservar a privacidade dos consumidores sem afetar a prestação de certos serviços pelas concessionárias? Claramente, este é um tradeoff entre privacidade e utilidade. Existem diversas abordagens para preservar a privacidade, porém muitas delas afetam a utilidade dos dados ou possuem um alto custo computacional. Neste trabalho, nós propomos e avaliamos uma abordagem computacionalmente barata que preserva a privacidade e utilidade dos dados através de adição de ruído. Para validar a privacidade, nós avaliamos possíveis ataques (tal como Monitoramento Não-Intrusivo de Carga de Eletrodomésticos - NIALM, do inglês Non-Intrusive Appliance Load Monitoring) utilizando dados reais de consumidores. Para validar a utilidade, nós avaliamos a influência da abordagem em vários benefícios que podem ser providos com o uso de Smart Meters. / Power providers have started replacing traditional electricity meters for Smart Meters, which can transmit power consumption levels to the provider within short intervals. With a Smart Metering infrastructure, there are many motivations for power providers to collect highresolution data of electricity usage from consumers. However, this implies in very detailed information about the consumers being monitored. Consequently, a serious issue needs to be addressed: how to preserve the privacy of consumers but making the provision of certain services still possible? Clearly, this is a tradeoff between privacy and utility. There are several approaches for privacy preserving, but many of them affect the data usefulness or are computationally expensive. In this work, we propose and evaluate a lightweight approach for privacy and utility based on the addition of noise. To validate the privacy, we evaluate possible attacks (such as a NIALM - Non-Intrusive Appliance Load Monitoring) using real consumers' data. To validate the utility, we analyze the influence of the approach in various benefits that can be provided through the use of Smart Meters.