Why another thermostat

HVAC operation constitutes 45-55% of house energy, due to inefficient conventional thermostats. This amounts to an incredible energy waste which our generation cannot afford.

Although a lot of progress has been made in renewable energy, still a lot of our energy today comes from fossil fuels. By helping save energy, it gives us more time to wean off these fossil fuels, as we reduce our rate of fossil fuel consumption. Climate change problem is real and we should do anything and everything in our power to help mitigate this issue. Lets start here by using a thermostat that helps save lot of energy. It is not only noble, but also very cost effective!

There are two primary ways to conserve energy:

  1. Avoid running HVAC system when not needed.
  2. Run HVAC system such that it achieves similar results using less energy.

Lately, newer breed of thermostats attempt to do the first part. That does help, but it doesn't conserve energy when you do need heating/cooling, which may be most of the time for many people. To do the second part, you need to identify how an HVAC system can effectively operate in a specific building and then ideally optimize its operation to get similar performance. Although ideal, this is not pragmatic as there are too many combination to consider.

A thermostat that understands the HVAC usage requirements and fine tunes HVAC operation by leveraging patterns that help conserve energy is needed for the second part. This project is based on a patented technology that precisely does that for any thermostat in any building. By having such an intelligent thermostat, it becomes possible to have very deep energy savings for everyone.

Thermostats are not just for energy savings - but also for maximizing comfort. Comfort and energy savings are conflicting goals and therefore, a technology is needed to help users automatically balance these conflicting goals. The patented technology for this smart thermostat enables users to seamlessly balance these goals and offers users an excellent means to predictably control the outcome.

Patented Technology

Thermocloud is based on a patented technology (US Patent 10948210: Systems and methods for intelligent thermostat) as described here. In order to promote conservation of energy throughout the world, the inventor of this patent, Harshal, is making this patent available for users of this project free of charge. Please refer here for additional details.

Overview

The project's goal is to offer a cloud-based collaborative learning thermostat that optimizes HVAC operation and maximizes comfort and energy savings using machine learning. A two-tiered learning approach – adaptive clustering to dissect huge problem space, and dynamic collaboration strategy between units rapidly enhances performance. Thermostat uses cost-effective hardware and user-specifiable cost-comfort trade-off with cost-saving features, like user-specified temperature range and comfort-level, blackout mitigation, and multi-story equalizer.

A Raspberry-Pi Zero based hardware module, uses GPIO and sensors to operate HVAC system under guidance of Android application, comprising local and collaborating machine-learning algorithms and automatic access-token based security. Locally, probe creates thermal-profile, sustain maintains interval's temperature, and transit enables transitioning between intervals. Two-tiered learning with automatic clustering enables client consult right cloud server node and dynamic collaboration learning strategy at the node provides best optimization. Grad-learn strategy learns progressively using domain-specific algorithms, neural-strategy optimizes using deep neural-network learning, and hybrid-strategy dynamically uses best optimization strategy.

Hybrid-strategy can offer around 34% savings over conventional from day one. Grad-learn excels for identical conditions, neural regresses best with training, but hybrid is most reliable. Thermocloud’s huge energy saving can have a substantial positive impact on society.