Quote of the day

A person who never made a mistake never tried anything new.

- Albert Einstein

Contact

Federated Non-Intrusive Load Monitoring for Privacy-Preserving Demand Response

Open Energy

Federated Non-Intrusive Load Monitoring for Privacy-Preserving Demand Response

Federated Non-Intrusive Load Monitoring for Privacy-Preserving Demand Response

Description

Disaggregate household electricity consumption by appliance without transmitting raw load curves and quantify the residual privacy risk through empirical attacks.

Details

Context and Problem Statement

Non-intrusive load monitoring can infer appliance-level consumption from aggregate household meters, but high-resolution load curves may reveal occupancy and daily routines. Centralized learning therefore creates significant privacy risk.

Research Question

What disaggregation-performance loss must be accepted to measurably reduce inference of household occupancy patterns under federated learning and smart-meter computing constraints?

Proposed Approach

Train sequential disaggregation models federatively across simulated households, apply differential privacy to model updates, and audit privacy using attacks designed to infer occupancy or appliance behavior. Relate retained model utility to achievable demand-response benefits.

Expected Contribution

An empirical performance-privacy curve for NILM and an assessment of demand-response value retained at different privacy levels.

Expected Prototype

A federated demonstrator with multiple embedded clients, appliance-level usage outputs, and privacy-budget reporting.

Datasets

UK-DALE, REFIT, and measurements from an instrumented domestic testbed.

Challenges

Appliance heterogeneity, low smart-meter sampling rates, utility degradation under privacy, and social acceptance of fine-grained monitoring.

Research Question

Can useful appliance-level energy disaggregation be achieved while empirically preventing reliable inference of household occupancy patterns?

Innovation

The project combines NILM performance, formal privacy mechanisms, and empirical attack-based auditing rather than treating privacy as a declarative property.

Expected Deliverable

A federated NILM platform, a privacy-audit protocol, and an analysis of the demand-response benefits achievable at different privacy levels.

Technologies

Non-Intrusive Load Monitoring Federated Learning Differential Privacy Sequential Models (Dilated CNNs, Transformers) Smart Metering and Edge Computing

Required Skills

  • Signal Processing and Time Series
  • Federated Learning and Privacy
  • Embedded Systems
  • Electricity Markets and Demand Response Fundamentals

Datasets

  • UK-DALE
  • REFIT Electrical Load Measurements
  • Measurements from an instrumented domestic testbed

Morocco & Africa Relevance

The progressive deployment of smart meters in Morocco raises immediate questions about governance of household load data, making privacy-preserving architectures timely.