Promoting Social Behaviour in Reducing Peak Electricity Consumption Using Multi-Agent Systems

TL;DR

This paper presents a decentralized multi-agent system that uses social capital to incentivize households to spread out appliance usage, effectively reducing peak electricity demand based on real-world data.

Contribution

It extends previous work by integrating real household data and analyzing the effectiveness of smaller, diverse populations in peak load reduction.

Findings

Decentralized social capital mechanism reduces peak load effectively.

Smaller, diverse populations optimize energy usage more efficiently.

Real-world data integration enhances system adaptability.

Abstract

As we transition to renewable energy sources, addressing their inflexibility during peak demand becomes crucial. It is therefore important to reduce the peak load placed on our energy system. For households, this entails spreading high-power appliance usage like dishwashers and washing machines throughout the day. Traditional approaches to spreading out usage have relied on differential pricing set by a centralised utility company, but this has been ineffective. Our previous research investigated a decentralised mechanism where agents receive an initial allocation of time-slots to use their appliances, which they can exchange with others. This was found to be an effective approach to reducing the peak load when we introduced social capital, the tracking of favours, to incentivise agents to accept exchanges that do not immediately benefit them. This system encouraged self-interested agents to learn socially beneficial behaviour to earn social capital that they could later use to improve their own performance. In this paper we expand this work by implementing real world household appliance usage data to ensure that our mechanism could adapt to the challenging demand needs of real households. We also demonstrate how smaller and more diverse populations can optimise more effectively than larger community energy systems.