Thomas Navidi

Thomas Navidi, Abbas El Gamal, Ram Rajagopal

This paper presents a two-layer distributed energy resource (DER) coordination architecture that allows for separate ownership of data, operates with data subjected to a large buffering delay, and employs a new measure of power quality. The two-layer architecture comprises a centralized model predictive controller (MPC) and several decentralized MPCs each operating independently with no direct communication between them and with infrequent communication with the centralized controller. The goal is to minimize a combination of total energy cost and a measure of power quality while obeying cyber-physical constraints. The global controller utilizes a fast AC optimal power flow (OPF) solver and extensive parallelization to scale the solution to large networks. Each local controller attempts to maximize arbitrage profit while following the load profile and constraints dictated by the global controller. Extensive simulations are performed for two distribution networks under a wide variety of possible storage and solar penetrations enabled by the controller speed. The simulations show that (i) the two-layer architecture can achieve tenfold improvement in power quality relative to no coordination, while capturing nearly all of the available arbitrage profit for a moderate amount of storage penetration, and (ii) both power quality and arbitrage profits are optimized when the solar and storage are distributed more widely over the network, hence it is more effective to install storage closer to the consumer.

Xiao Chen, Thomas Navidi, Ram Rajagopal

Personal devices such as mobile phones can produce and store large amounts of data that can enhance machine learning models; however, this data may contain private information specific to the data owner that prevents the release of the data. We want to reduce the correlation between user-specific private information and the data while retaining the useful information. Rather than training a large model to achieve privatization from end to end, we first decouple the creation of a latent representation, and then privatize the data that allows user-specific privatization to occur in a setting with limited computation and minimal disturbance on the utility of the data. We leverage a Variational Autoencoder (VAE) to create a compact latent representation of the data that remains fixed for all devices and all possible private labels. We then train a small generative filter to perturb the latent representation based on user specified preferences regarding the private and utility information. The small filter is trained via a GAN-type robust optimization that can take place on a distributed device such as a phone or tablet. Under special conditions of our linear filter, we disclose the connections between our generative approach and renyi differential privacy. We conduct experiments on multiple datasets including MNIST, UCI-Adult, and CelebA, and give a thorough evaluation including visualizing the geometry of the latent embeddings and estimating the empirical mutual information to show the effectiveness of our approach.

Xiao Chen, Thomas Navidi, Stefano Ermon et al.

Distributed devices such as mobile phones can produce and store large amounts of data that can enhance machine learning models; however, this data may contain private information specific to the data owner that prevents the release of the data. We wish to reduce the correlation between user-specific private information and data while maintaining the useful information. Rather than learning a large model to achieve privatization from end to end, we introduce a decoupling of the creation of a latent representation and the privatization of data that allows user-specific privatization to occur in a distributed setting with limited computation and minimal disturbance on the utility of the data. We leverage a Variational Autoencoder (VAE) to create a compact latent representation of the data; however, the VAE remains fixed for all devices and all possible private labels. We then train a small generative filter to perturb the latent representation based on individual preferences regarding the private and utility information. The small filter is trained by utilizing a GAN-type robust optimization that can take place on a distributed device. We conduct experiments on three popular datasets: MNIST, UCI-Adult, and CelebA, and give a thorough evaluation including visualizing the geometry of the latent embeddings and estimating the empirical mutual information to show the effectiveness of our approach.