AI for Bill Reduction

MARKET NEED

AI for Bill Reduction investigates the use of AI for the task of optimising energy usage in both commercial and domestic settings. The idea is to use reinforcement learning (RL), given the potential it has shown in solving complex optimisation problems. Businesses have several incentives to reduce energy consumption. Lower consumption means lower energy bills and saved money. This is especially relevant to high consumption sectors such as manufacturing and heavy industry, and given the fact that most of the world’s energy is still produced from fossil fuel sources, reduced consumption also helps to combat climate change and lower environmental pollution. In order to clearly show the potential of RL for energy optimisation, we developed a demonstrator application as part of this project. This application provides a simple simulation environment which allows for the comparison between RL and traditional energy optimization methods in a domestic heating and cooling scenario.

TECHNOLOGY SOLUTION

AI for Bill Reduction is a web-based tool that offers state-of-the-art methods for energy optimisation based on deep reinforcement learning in a user-friendly manner:

• Cutting-edge methods: using a deep reinforcement learning method known as Deep Q-learning.
• Real simulation environment: building a testing environment for RL for the task of energy optimisation in a domestic heating and cooling task.
• Flexibility: using the OpenAI Gym Python RL framework,  user can customise environment to increase complexity of task.
• Individual and comparative analysis of the methods: RL method is compared to simple thermostat algorithm similar to that present in most homes.

APPLICABILITY

The tool is targeted to show to any company or organisation, especially high consumption sectors such as manufacturing and heavy industries, the potential of using reinforcement learning methods for bill reduction. The demonstrator presents a simple simulation environment and a series of visualisations and controls that allow understanding the functioning of these methods for reducing energy consumption depending on business considerations.

RESEARCH TEAM

• Mr Michael Spence, University College Dublin,
• Dr Oisin Boydell, University College Dublin