Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning

  title={Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning},
  author={Mohammadhadi Shateri and Francisco Messina and Pablo Piantanida and Fabrice Labeau},
  journal={2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe)},
Smart meters (SMs) play a pivotal rule in the smart grid by being able to report the electricity usage of consumers to the utility provider (UP) almost in real-time. However, this could leak sensitive information about the consumers to the UP or a third-party. Recent works have leveraged the availability of energy storage devices, e.g., a rechargeable battery (RB), in order to provide privacy to the consumers with minimal additional energy cost. In this paper, a privacy-cost management unit… 

Figures from this paper

Privacy-Cost Management in Smart Meters with Mutual Information-Based Reinforcement Learning
This paper adopts the mutual information (MI) between the user’s demand load and the masked load seen by the power grid as a reliable and general privacy measure and uses a neural network to estimate the MI-based reward signal to guide the PCMU learning process.
Privacy-Cost Management in Smart Meters: An Information-Theoretic Deep Reinforcement Learning Approach
A novel privacy-aware method which exploits the availability of a rechargeable battery is proposed, based on a Markov decision process (MDP) formulation in which the reward received by the agent is designed to control the trade-off between privacy and electricity cost.
Learning Sparse Privacy-Preserving Representations for Smart Meters Data
This study proposes a privacy-preserving approach based on non-uniform down-sampling of SMs data that performs better in terms of the privacy-utility trade-off while releasing much less data, thus also being more efficient.
On the Impact of Side Information on Smart Meter Privacy-Preserving Methods
The results show that, although they perform similarly when the attacker does not exploit the SI, in general, the CAL method is less sensitive to the inclusion of SI, while privacy levels are significantly affected, particularly when multiple sources of SI are included.


Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning series
  • 2018
Smart Meter Privacy: Exploiting the Potential of Household Energy Storage Units
A load hiding approach that obscures household consumption with the help of energy storage units is designed and the results show that the opportunistic joint use of EV and HVAC units can reduce the need of dedicated large-capacity or fast-charging-cycle batteries for load hiding.
Reinforcement Learning: An Introduction
This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Privacy-Aware Smart Metering: Progress and Challenges
The next-generation energy network, the so-called smart grid (SG), promises tremendous increases in efficiency, safety, and flexibility in managing the electricity grid as compared to the legacy
Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release
The Directed Information (DI) is introduced as a more meaningful measure of privacy in the considered setting and a novel loss function is proposed and validated to show the existing trade-offs between privacy and utility.
On-Line Building Energy Optimization Using Deep Reinforcement Learning
The benefits of using deep reinforcement learning, a hybrid type of methods that combines reinforcement learning with deep learning, to perform on-line optimization of schedules for building energy management systems, are explored for the first time in the smart grid context.
Privacy-cost Trade-off in a Smart Meter System with a Renewable Energy Source and a Rechargeable Battery
This work reformulates the privacy-cost trade-off in a smart meter system with a renewable energy source (RES) and a finite-capacity rechargeable battery (RB) as a Markov decision process (MDP), and solves it by dynamic programming (DP) to design battery charging and discharging policies that minimize a linear combination of the privacy leakage and energy cost.
Adaptive Computation and Machine Learning series
  • 2018
An Introduction to Deep Reinforcement Learning
This manuscript provides an introduction to deep reinforcement learning models, algorithms and techniques and particular focus is on the aspects related to generalization and how deep RL can be used for practical applications.
Information-Theoretic Privacy for Smart Metering Systems with a Rechargeable Battery
This paper investigates the use of a rechargeable battery in order to provide privacy to the user, and studies the optimal battery charging policy that minimizes the leakage rate among the class of battery policies that satisfy causality and charge conservation.