A principal motivação para o surgimento do conceito de Smart Grid é a otimização do uso das redes de energia através da inserção de novas tecnologias de medição, automação e telecomunicações. A implementação desta complexa infra-estrutura produz ganhos em confiabilidade, eficiência e segurança operacional. Além disso, este sistema tem como principais objetivos promover a geração distribuída e a tarifa diferenciada de energia para usuários residenciais, provendo ferramentas para a participação dos consumidores no gerenciamento global do fornecimento de energia. Considerando também o uso de dispositivos de armazenamento de energia, o usuário pode optar por vender ou armazenar energia sempre que lhe for conveniente, reduzindo a sua conta de energia ou, quando a geração exceder a demanda de energia, lucrando através da venda deste excesso. Esta pesquisa propõe um Sistema Inteligente de Suporte à Decisão baseado em técnicas de aprendizado por reforço como uma solução para o problema de decisão sequencial referente ao gerenciamento de energia de uma Smart Home. Resultados obtidos mostram um ganho significativo na recompensa financeira a longo prazo através do uso de uma política obtida pela aplicação do algoritmo Q-Learning, que é um algoritmo de aprendizado por reforço on-line, e do algoritmo Fitted Q-Iteration, que utiliza uma abordagem diferenciada de aprendizado por reforço ao extrair uma política através de um lote fixo de transições adquiridas do ambiente. Os resultados mostram que a aplicação da técnica de aprendizado por reforço em lote é indicada para problemas reais, quando é necessário obter uma política de forma rápida e eficaz dispondo de uma pequena quantidade de dados para caracterização do problema estudado. / The main motivation for the emergence of the Smart Grid concept is the optimization of power grid use by inserting new measurement, automation and telecommunication technologies into it. The implementation of this complex infrastructure also produces gains in reliability, efficiency and operational safety. Besides, it has as main goals to encourage distributed power generation and to implement a differentiated power rate for residential users, providing tools for them to participate in the power grid supply management. Considering also the use of energy storage devices, the user can sell or store the power generated whenever it is convenient, reducing the electricity bill or, when the power generation exceeds the power demand, make profit by selling the surplus in the energy market. This research proposes an Intelligent Decision Support System as a solution to the sequential decision-making problem of residential energy management based on reinforcement learning techniques. Results show a significant financial gain in the long term by using a policy obtained applying the algorithm Q-Learning, which is an on-line Reinforcement Learning algorithm, and the algorithm Fitted Q-Iteration, which uses a different reinforcement learning approach called Batch Reinforcement Learning. This method extracts a policy from a fixed batch of transitions acquired from the environment. The results show that the application of Batch Reinforcement Learning techniques is suitable for real problems, when it is necessary to obtain a fast and effective policy considering a small set of data available to study and solve the proposed problem.

Smart homes are residences equipped with information and communication technologies that anticipate and respond to the needs of the occupants. Despite the numerous research and industrial efforts, today only few expensive smart homes have been built and sold. The reason behind this slow uptake is the technology-driven approach characterizing existing solutions. The doctoral Thesis aims at demonstrating that a smart home can provide functionalities designed with a user-centered approach, taking into account ergonomic considerations about domestic activity and human cognition. This is achieved in collaboration with cognitive ergonomists, which help "minding the gap" between human context and machine-understandable context. Using off-the-shelf and lightweight instrumentation (also minimizing privacy concerns), extending existing context modeling, reasoning and management tools and following the Ubiquitous Computing principles, the doctoral work led to the following achievements: (i) the inter-disciplinary design of suitable functionalities, in collaboration with cognitive ergonomists; (ii) the design of a context-aware system that captures and reasons about uncertain contextual information in a distributed fashion; (ii) the realization of a working prototype that demonstrates the provision of energy-saving and comfort-preserving functionalities.

IoT is a technology where different devices are equipped with internet connection which makes it possible to control them and exchange data over internet. IoT can be thought of as an umbrella term covering a broad and ever-growing range of services and technologies. One of the segments within IoT is the smart home ecosystem. The tremendous development the last decade within smartphones, wearable devices and broadband has created new ways to connect individual devices in the home (Qasim and Abu-Shanab, 2016; Jeong et al, 2016; Wilson et al, 2017; Hubert et al, 2017). This creates a synergy effect; by connecting multiple devices to a system new value is created. Energy, home controls, security, communication and entertainment services are all included in the smart home (Miller, 2015; Wilson et al, 2017). Even though the concept of smart homes has a large potential it seems like it has not reached its full potential and the diffusion of the innovation among the consumers is still at an early stage (Balta-Ozkan et.al, 2013; Yang et.al 2017). So far, many studies have been performed on the technical aspects of IoT and smart home ecosystems but less attention has been paid on the consumer point of view and what determinants that play a role in the intention to adopt the technology (Yang, Lee, and Zo. 2017). In addition, previous studies have mainly focused of one single device and has not considered the entire ecosystem (Yang, Lee, and Zo. 2017). Therefore, the purpose with this thesis is to study what are the key determinants for the intention to adopt smart homes from an ecosystem point of view. To fulfill the purpose known theoretical models regarding intention to adopt technology have been used to develop a research model. The basis to establish the research model has been the theory of innovation adoption, TRA, TPB, TAM, VAM and UTAUT. Based on the literature four determinants were selected to be included in the model; these were cost, perceived ease of use, perceived usefulness and individualization. The first three are all included in the mentioned theoretical models and have previously been proven to be important for intention to adopt. The last one, individualization is derived from the field of product differentiation. In the literature it is mentioned that the possibility to refine, adjust and modify may be crucial for the user (Dodgson et.al. 2008). With this background it was interested to include individualization as a determinant in the research model and study how it impacts intention to adopt. In addition to the determinants one moderator was included; the composition of the household. In order to collect the empirical data a survey was conducted using the snowball sampling approach via Facebook and LinkedIn. The survey consisted of two sections where the first section aimed to collect background information about the respondent and the second section consisted of questions regarding the determinants. In the second section the respondents were asked to respond according to a 5-point Likert scale. The used questions in the survey was predefined in the literature. Study results show that consumers’ use intention is shaped by individualization, perceived usefulness and perceived ease of use. Cost was found not to be statistically significant. Neither was the composition of the household.

abstract: This dissertation explores the role of smart home service provisions (SHSP) as motivational agents supporting goal attainment and human flourishing. Evoking human flourishing as a lens for interaction encapsulates issues of wellbeing, adaptation and problem solving within the context of social interaction. To investigate this line of research a new, motivation-sensitive approach to design was implemented. This approach combined psychometric analysis from motivational psychology's Personal Project Analysis (PPA) and Place Attachment theory's Sense of Place (SoP) analysis to produce project-centered motivational models for environmental congruence. Regression analysis of surveys collected from 150 (n = 150) young adults about their homes revealed PPA motivational dimensions had significant main affects on all three SoP factors. Model one indicated PPA dimensions Fearful and Value Congruency predicted the SoP factor Place Attachment (p = 0.012). Model two indicated the PPA factor Positive Affect and PPA dimensions Value Congruency, Self Identity and Autonomy predicted Place Identity (p = .0003). Model three indicated PPA dimensions Difficulty and Likelihood of Success predicted the SoP factor Place Dependency. The relationships between motivational PPA dimensions and SoP demonstrated in these models informed creation of a set of motivational design heuristics. These heuristics guided 20 participants (n = 20) through co-design of paper prototypes of SHSPs supporting goal attainment and human flourishing. Normative analysis of these paper prototypes fashioned a design framework consisting of the use cases "make with me", "keep me on task" and "improve myself"; the four design principles "time and timing", "guidance and accountability", "project ambiguity" and "positivity mechanisms"; and the seven interaction models "structuring time", "prompt user", "gather resources", "consume content", "create content", "restrict and/or restore access to content" and "share content". This design framework described and evaluated three technology probes installed in the homes of three participants (n = 3) for field-testing over the course of one week. A priori and post priori samples of psychometric measures were inconclusive in determining if SHSP motivated goal attainment or increased environmental congruency between young adults and their homes. / Dissertation/Thesis / Ph.D. Design 2013

A principal motivação para o surgimento do conceito de Smart Grid é a otimização do uso das redes de energia através da inserção de novas tecnologias de medição, automação e telecomunicações. A implementação desta complexa infra-estrutura produz ganhos em confiabilidade, eficiência e segurança operacional. Além disso, este sistema tem como principais objetivos promover a geração distribuída e a tarifa diferenciada de energia para usuários residenciais, provendo ferramentas para a participação dos consumidores no gerenciamento global do fornecimento de energia. Considerando também o uso de dispositivos de armazenamento de energia, o usuário pode optar por vender ou armazenar energia sempre que lhe for conveniente, reduzindo a sua conta de energia ou, quando a geração exceder a demanda de energia, lucrando através da venda deste excesso. Esta pesquisa propõe um Sistema Inteligente de Suporte à Decisão baseado em técnicas de aprendizado por reforço como uma solução para o problema de decisão sequencial referente ao gerenciamento de energia de uma Smart Home. Resultados obtidos mostram um ganho significativo na recompensa financeira a longo prazo através do uso de uma política obtida pela aplicação do algoritmo Q-Learning, que é um algoritmo de aprendizado por reforço on-line, e do algoritmo Fitted Q-Iteration, que utiliza uma abordagem diferenciada de aprendizado por reforço ao extrair uma política através de um lote fixo de transições adquiridas do ambiente. Os resultados mostram que a aplicação da técnica de aprendizado por reforço em lote é indicada para problemas reais, quando é necessário obter uma política de forma rápida e eficaz dispondo de uma pequena quantidade de dados para caracterização do problema estudado. / The main motivation for the emergence of the Smart Grid concept is the optimization of power grid use by inserting new measurement, automation and telecommunication technologies into it. The implementation of this complex infrastructure also produces gains in reliability, efficiency and operational safety. Besides, it has as main goals to encourage distributed power generation and to implement a differentiated power rate for residential users, providing tools for them to participate in the power grid supply management. Considering also the use of energy storage devices, the user can sell or store the power generated whenever it is convenient, reducing the electricity bill or, when the power generation exceeds the power demand, make profit by selling the surplus in the energy market. This research proposes an Intelligent Decision Support System as a solution to the sequential decision-making problem of residential energy management based on reinforcement learning techniques. Results show a significant financial gain in the long term by using a policy obtained applying the algorithm Q-Learning, which is an on-line Reinforcement Learning algorithm, and the algorithm Fitted Q-Iteration, which uses a different reinforcement learning approach called Batch Reinforcement Learning. This method extracts a policy from a fixed batch of transitions acquired from the environment. The results show that the application of Batch Reinforcement Learning techniques is suitable for real problems, when it is necessary to obtain a fast and effective policy considering a small set of data available to study and solve the proposed problem.

Driven by the Internet of Things, devices and appliances will be increasingly connected to each other and the people within the home. In order for the communication to be possible a standard for communication is needed. In many cases there are too many standards, and for other cases there may instead be an absence of standard. This thesis provides a contemporary view of future developments of homes and the current standardization progress. Four domains in homes are investigated: the automated home domain, the sustainable home domain, the healthy home domain and the manufacturing home domain. Trends and technologies are identified that drive a change in homes. Services are described that may be provided in homes. The thesis discusses how services from different domains may be integrated, with a further investigation of the networked manufacturing service and its underlying communication infrastructure. Finally standards are identified and analyzed in regard to the communication infrastructure of the networked manufacturing service. The standardization development is progressing for each home domain. However, potential standard gaps are still present for many of the cross domain device communication. No standard has been identified for integration of services and integration of the business ecosystem in the manufacturing home domain. Similarly there is no standard for the software of 3D printing. New standards or further development of existing standards is needed to realize the networked manufacturing service.

This thesis focuses on Internet of Things (IoT) and open-source technologies based on it. Specifically aims at software solutions relevant to smart home and compatible with Raspberry Pi platform and MQTT communication protocol. This thesis also focuses on studying Petri Net Virtual Machine (PNVM) and its potential application in IoT. The objective is to design integration of PNVM into IoT with help of existing software means compatible with MQTT and implement a demo application for smart home.

This work deals with connecting remote devices measure data of various types from physical quantities such as a temperature, a humidity to data displaying CPU or memory usage of the system to the user. The system uses Blockly to controlling logic and dependencies between devices. In the work is used lots of technologies for examples: MQTT, Websockets, GSM, Lightweight Mesh and others. The system is based on microservice which named is Flask. Flask service is an application interface for HTTP services of Python programming language. This can provide measured data by graphs and predefined components for viewing data. For controlling system was used single-board computer Raspberry Pi with a multitouch 7-inch display.

This master thesis describes the design of a battery-powered smart lock using IoT networks and NFC technology for user authentication. The first part of the thesis describes the individual components to be used for the device design and also deals with the design of matching circuits and the antenna for the NFC. The following part of the thesis describes the design of the hardware, particularly the design of the printed circuit board. The third part describes the firmware and the final part of the thesis is dedicated to the security analysis.

This master thesis deals with the integration of new devices from the manufacturers Revogi, Tabu Lumen, Sonoff and HomeMatic into the BeeeOn Gateway software. The theoretical part deals with the architecture of the BeeeOn Gateway software and describes the characteristics, behavior and way of communication with devices from the above mentioned manufacturers. This part of thesis also contains a description of the communication technologies used by these devices. They include Bluetooth Low Energy, the WiFi and the 868 MHz radio. The practical part mentions the way of extension of BeeeOn Gateway software to modules that implement support for smart devices. This section also describes how the correctness of implementation was verified and testing of the entire BeeeOn Gateway software. The testing of gateway is performed by unit and integration tests, which verify the behavior of individual gateway components as well as the whole gateway.