Privacy Preserving Demand Forecasting to Encourage Consumer Acceptance of Smart Energy Meters
This paper addresses the problem of consumer privacy concerns for smart meter adoption, which hinders the deployment of an infrastructure with potential environmental benefits.
This paper proposes using federated learning for energy demand forecasting to address consumer privacy concerns regarding smart meters. The goal is to enable load prediction while keeping raw energy consumption data private.
In this proposal paper we highlight the need for privacy preserving energy demand forecasting to allay a major concern consumers have about smart meter installations. High resolution smart meter data can expose many private aspects of a consumer's household such as occupancy, habits and individual appliance usage. Yet smart metering infrastructure has the potential to vastly reduce carbon emissions from the energy sector through improved operating efficiencies. We propose the application of a distributed machine learning setting known as federated learning for energy demand forecasting at various scales to make load prediction possible whilst retaining the privacy of consumers' raw energy consumption data.