Strategic Federated Learning: Application to Smart Meter Data Clustering

TL;DR

This paper introduces a strategic federated learning framework where clients can add noise to model updates to influence the fusion center's decisions, especially applied to smart meter data clustering and power scheduling.

Contribution

It presents a novel FL approach considering strategic client behavior and utility alignment, with a specific focus on clustering and power consumption applications.

Findings

Clients can increase utility by adding strategic noise.

The framework models utility misalignment scenarios.

Numerical results demonstrate the impact of strategic noise addition.

Abstract

Federated learning (FL) involves several clients that share with a fusion center (FC), the model each client has trained with its own data. Conventional FL, which can be interpreted as an estimation or distortion-based approach, ignores the final use of model information (MI) by the FC and the other clients. In this paper, we introduce a novel FL framework in which the FC uses an aggregate version of the MI to make decisions that affect the client's utility functions. Clients cannot choose the decisions and can only use the MI reported to the FC to maximize their utility. Depending on the alignment between the client and FC utilities, the client may have an individual interest in adding strategic noise to the model. This general framework is stated and specialized to the case of clustering, in which noisy cluster representative information is reported. This is applied to the problem of power consumption scheduling. In this context, utility non-alignment occurs, for instance, when the client wants to consume when the price of electricity is low, whereas the FC wants the consumption to occur when the total power is the lowest. This is illustrated with aggregated real data from Ausgrid \cite{ausgrid}. Our numerical analysis clearly shows that the client can increase his utility by adding noise to the model reported to the FC. Corresponding results and source codes can be downloaded from \cite{source-code}.