|
|
Effective management of domestic hot water heating using photovoltaics
Talajka, Martin ; Zachariáš, Michal (referee) ; Materna, Zdeněk (advisor)
This work solves the problem of efficient control of water heating using photovoltaic system. To solve the chosen problem, I designed an algorithm and implemented it in the form of integration into the Home Assistant system, which also serves as a central control device. And it provides the integration between the boiler and the PV system. Thanks to this integration, it is possible to automatically and comfortably heat water from the surplus energy of the photovoltaic system, or alternatively from batteries or the distribution network. At the same time, system status monitoring and remote device management are possible. For example, the user can monitor the temperature of the heated water, the status of the overall system, adjust the heating temperature or set the water heating for a specific time, using an app or a web interface. The results of the work show that the proposed system is easy to use and is able to efficiently manage the water heating using the PV system, thus saving energy and gas.
|
|
|
Aplikace posilovaného učení v řízení Smart Home
Biel, Gabriel ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
Táto práca skúma, ako môže strojové učenie zlepšiť riadenie inteligentných domácností s dôrazom na optimalizáciu riadenia teploty a zvýšenie energetickej účinnosti. Konkrétne sa porovnávajú dva pokročilé algoritmy posilňovaného učenia, Deep Q-Learning (DQL) a Proximal Policy Optimization (PPO). Tieto modely sú testované v simulovanom prostredí, ktoré napodobňuje reálne podmienky, aby sa zhodnotila ich schopnosť prispôsobiť sa správaniam užívateľov a zmenám v prostredí. Ukázalo sa, že model PPO je obzvlášť účinný vďaka svojej stabilite a schopnosti predpovedať návrat obyvateľov. Tento výskum ponúka cenné poznatky o praktických aplikáciách AI technológií v inteligentných domácnostiach.
|
|
|
Design of a smart house control system
Ovesný, David ; Burian, František (referee) ; Fiedler, Petr (advisor)
This bachelor thesis deals with the comprehensive design solution of a smart home using Loxone technology. Through the appropriate implementation of sensors, actuators, and a central control system, a comprehensive solution for home automation processes is proposed. The theoretical part introduces Loxone technology and briefly compares it with the competing ABB free@home technology. The practical section involves the selection of suitable hardware components and the description of control algorithms. The conclusion of the thesis is dedicated to a cost comparison with the competing technology.
|
|
|
Smart home in a family house
Boháč, Kryštof ; Benešl, Tomáš (referee) ; Sýkora, Tomáš (advisor)
This thesis deals with the implementation of the control of a family house built on Loxone technology. The first part of the thesis describes the concept of building management systems, the Loxone system and alternatives that could also be used for the implementation. In the following part the components for the final implementation of the house are selected. Furthermore, the thesis deals with the project documentation and the implementation of the control algorithm for the selected building. Finally, the resulting cost and comparison with other types of installations is then addressed.
|
|
|
Extensible Rust Library for the Development of Embedded Sensor Applications on ESP32 Platform
Mikhailov, Kirill ; Tinka, Jan (referee) ; Šimek, Václav (advisor)
Tato práce představuje rozšiřitelnou knihovnu jazyka Rust určenou pro vestavěné senzorové aplikace na platformě ESP32, která řeší potřebu zjednodušeného vývoje reálných vestavěných systémů v prostředí jazyka Rust na této platformě. Významným přínosem této práce je vývoj uživatelsky přívětivého rozhraní pro správu senzorů. Toto rozhraní umožňuje jednoduchou instalaci, aktivaci a monitorování senzorů, což vyhovuje aplikacím, jako jsou inteligentní domy a automatizace, aniž by vyžadovalo hluboké technické znalosti periferií. Architektura knihovny je pečlivě navržena s ohledem na modularitu a rozšiřitelnost a dodržuje zásady bezpečnosti a efektivity Rustu. Projekt je doprovázen rozsáhlou dokumentací a je zveřejněn na platformě GitHub pod open-source licencí Apache, doplněn unit-testy a příklady použití. V závěru práce je zhodnocena funkčnost knihovny a její případná budoucí vylepšení, která ukazují její praktičnost pro vývojáře vestavných systémů.
|
|
|
System for Automatic Heating Control in Holiday Homes
Ježek, Lukáš ; John, Petr (referee) ; Hynek, Jiří (advisor)
The goal of this bachelor thesis was to design and implement a system for controlling heating and water heating in buildings divided into multiple zones with multiple heating sources. Typically larger and older holiday homes such as farmhouses or larger cottages that do not have only one heat source, however, the system will also be applicable to newer buildings. This system can be controlled either remotely or locally. RaspberryPi 4B was chosen as the platform from the IoT sector. This system solves, for example, the integration of a fireplace insert into a heating circuit together with a boiler, combi boiler or other heat source. Of the existing solutions, none allow efficient use of multiple sources with zoning, or the solution is expensive and inefficient. Moreover, the system offers extensibility to other IoT circuits.
|
|
|
Adaptivní systém pro řízení osvětlení ve Smart Home
Valík, Tomáš ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The thesis deals with the issue of lighting control in smart homes. In most smart homes, it is necessary to manually control the lighting using switches or mobile devices. The thesis introduces an adaptive control system based on recurrent neural networks, which gradually learns user manipulation with the lighting and eventually begins to independently control the lighting after a certain period of time.
|
|
|
Aquarium control system for smart home
Tatýrek, Marek ; Rusnák, František (referee) ; Baštán, Ondřej (advisor)
The semestral thesis is aimed at understanding the issues of procedural management of aquarium in context. The methods of measurement and control of aquarium variables are described. At the same time, the probelmatic of smart home is discussed. In relation to smart home, the Matter protocol, which is the current trend in smart home, is described. The main objective of this work is to survey commercially available solutions and to propose an own solution. One that is reliable, user-friendly and allows easy integration into a smart home environment. This is where the already mentioned Matter protocol is supposed to help. For this purpose, HW will be designed and the corresponding FW will be implemented. The benefit of this work will be to facilitate aquarium management and monitoring for aquarists, easy smart home capable devices expandability, while maintaining maximum environmental quality in the tank.
|
|
|
Using machine learning methods to save energy in a smart home
Grünwald, Adam ; Herout, Adam (referee) ; Materna, Zdeněk (advisor)
This thesis addresses the use of machine learning for energy saving in the home, specifically focusing on the use of hot water boiler consumption prediction for smart heating. A sequential neural network with an LSTM layer is used to predict the consumption, which is trained on data such as hot water consumption over time, presence of users in the home, time of day or current weather information. Data were collected in two test households. This prediction is then used in an implemented algorithm that ensures that the water in the boiler is heated to a higher temperature, the value of which is determined by the amount of predicted heat extracted, before the predicted hot water consumption. Thanks to this smart heating, the heat loss of the boiler has been reduced and thus the energy consumption has been reduced by almost 27% while maintaining the thermal comfort of the household members. This solution, which allows its users to save more than 1500 Kč annually, has also been released as an add-on as part of the Home Assistant platform.
|
|
|
Inteligentní řízení pro chytrá prostředí
Horil, Denis ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
The aim of this thesis is to design and implement a smart home control system using ROS. The work includes the implementation of smart home control software and explores the possibilities of efficient storage of sensor data. The implementation includes communication and data transfer between the systems using MQTT protocol. The thesis explores the possibilities of using multi-agent systems in smart environments.
|
guest ::
