SMARTCLIMA: Reinforcement Learning Residential Thermostat-Less Heating Control System
- Resource Type
- Conference
- Authors
- Tsenis, Theocharis Theo; Kapsimanis, George; Kappatos, Vassilios
- Source
- 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2021 International Conference on. :1-6 Oct, 2021
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Energy consumption
Renewable energy sources
Mechatronics
Heat engines
Green products
Europe
Reinforcement learning
Reinforcement Learning
Deep Neural Net
DQN
energy
thermal
heating
consumption
value function
policy function
- Language
Residential energy consumption from latest reports accounts for the 26.1% of the total European energy consumption and 36% of Global Greenhouse Emissions. EU has set the policy of carbon neutral by 2030. It is emerging need not only to provide clean renewable energy sources but also in an intelligent way to handle the energy and thermal residential consumption which eventually will lead to low energy consumption. In this study we aim in a holistic way to focus on achieving tenants thermal comfort through our proposed management system, and in addition reducing the required energy consumption. This focus on tenants thermal comfort introduce additional sensoring requirements which eventually lead to multi parameter and complex problems that only Reinforcement Learning method can solve consistently.