No abstract

No abstract

Wind energy is a rapidly growing source of renewable energy generation. However, the current extra-market approach to its assimilation into the electric grid will not scale at deep penetration levels. In this paper, we investigate how an independent wind power producer might optimally offer its variable power into a competitive electricity market for energy. Starting with a stochastic model for wind power production and a model for a perfectly competitive two-settlement market, we derive explicit formulae for optimal contract offerings and the corresponding optimal expected profit. As wind is an inherently variable source of energy, we explore the sensitivity of optimal expected profit to uncertainty in the underlying wind process. We also examine the role of forecast information and recourse markets in this setting. We quantify the role of reserves in increasing reliability of offered contracts and obtain analytical expressions for marginal profits resulting from investments in improved forecasting and local auxiliary generation. The formulae make explicit the relationship between price signals and the value of such firming strategies.

We developed an accurate deep learning framework to automatically localize solar photovoltaic panels from satellite imagery and estimate their sizes. We used it to construct a comprehensive and publicly available solar installation database of the contiguous US. We demonstrated its value by identifying key environmental and socioeconomic factors correlating with solar deployment, such as income and education. We also found that the solar deployment density can be accurately estimated at the microscopic level with these factors using a novel predictive model.

Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but often lead to a significant reduction in utility. On the other hand, context-aware privacy solutions, such as information theoretic privacy, achieve an improved privacy-utility tradeoff, but assume that the data holder has access to dataset statistics. We circumvent these limitations by introducing a novel context-aware privacy framework called generative adversarial privacy (GAP). GAP leverages recent advancements in generative adversarial networks (GANs) to allow the data holder to learn privatization schemes from the dataset itself. Under GAP, learning the privacy mechanism is formulated as a constrained minimax game between two players: a privatizer that sanitizes the dataset in a way that limits the risk of inference attacks on the individuals' private variables, and an adversary that tries to infer the private variables from the sanitized dataset. To evaluate GAP's performance, we investigate two simple (yet canonical) statistical dataset models: (a) the binary data model; and (b) the binary Gaussian mixture model. For both models, we derive game-theoretically optimal minimax privacy mechanisms, and show that the privacy mechanisms learned from data (in a generative adversarial fashion) match the theoretically optimal ones. This demonstrates that our framework can be easily applied in practice, even in the absence of dataset statistics.