A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization

Two-stage adaptive robust optimization is a powerful approach for planning under uncertainty that aims to balance costs of "here-and-now" first-stage decisions with those of "wait-and-see" recourse decisions made after uncertainty is realized. To embed robustness against uncertainty, modelers typically assume a simple polyhedral or ellipsoidal set over which contingencies may be realized. However, these simple uncertainty sets tend to yield highly conservative decision-making when uncertainties are high-dimensional. In this work, we introduce AGRO, a column-and-constraint generation algorithm that performs adversarial generation for two-stage adaptive robust optimization using a variational autoencoder. AGRO identifies realistic and cost-maximizing contingencies by optimizing over spherical uncertainty sets in a latent space using a projected gradient ascent approach that differentiates the optimal recourse cost with respect to the latent variable. To demonstrate the cost- and time-efficiency of our approach experimentally, we apply AGRO to an adaptive robust capacity expansion problem for a regional power system and show that AGRO is able to reduce costs by up to 7.8% and runtimes by up to 77% in comparison to the conventional column-and-constraint generation algorithm.

Learning-assisted Stochastic Capacity Expansion Planning: A Bayesian Optimization Approach

Solving large-scale capacity expansion problems (CEPs) is central to cost-effective decarbonization of regional-scale energy systems. To ensure the intended outcomes of CEPs, modeling uncertainty due to weather-dependent variable renewable energy (VRE) supply and energy demand becomes crucially important. However, the resulting stochastic optimization models are often less computationally tractable than their deterministic counterparts. Here, we propose a learning-assisted approximate solution method to tractably solve two-stage stochastic CEPs. Our method identifies low-cost planning decisions by constructing and solving a sequence of tractable temporally aggregated surrogate problems. We adopt a Bayesian optimization approach to searching the space of time series aggregation hyperparameters and compute approximate solutions that minimize costs on a validation set of supply-demand projections. Importantly, we evaluate solved planning outcomes on a held-out set of test projections. We apply our approach to generation and transmission expansion planning for a joint power-gas system spanning New England. We show that our approach yields an estimated cost savings of up to 3.8% in comparison to benchmark time series aggregation approaches.

Learning Spatio-Temporal Aggregations for Large-Scale Capacity Expansion Problems

Effective investment planning decisions are crucial to ensure cyber-physical infrastructures satisfy performance requirements over an extended time horizon. Computing these decisions often requires solving Capacity Expansion Problems (CEPs). In the context of regional-scale energy systems, these problems are prohibitively expensive to solve due to large network sizes, heterogeneous node characteristics, and a large number of operational periods. To maintain tractability, traditional approaches aggregate network nodes and/or select a set of representative time periods. Often, these reductions do not capture supply-demand variations that crucially impact CEP costs and constraints, leading to suboptimal decisions. Here, we propose a novel graph convolutional autoencoder approach for spatio-temporal aggregation of a generic CEP with heterogeneous nodes (CEPHN). Our architecture leverages graph pooling to identify nodes with similar characteristics and minimizes a multi-objective loss function. This loss function is tailored to induce desirable spatial and temporal aggregations with regard to tractability and optimality. In particular, the output of the graph pooling provides a spatial aggregation while clustering the low-dimensional encoded representations yields a temporal aggregation. We apply our approach to generation expansion planning of a coupled 88-node power and natural gas system in New England. The resulting aggregation leads to a simpler CEPHN with 6 nodes and a small set of representative days selected from one year. We evaluate aggregation outcomes over a range of hyperparameters governing the loss function and compare resulting upper bounds on the original problem with those obtained using benchmark methods. We show that our approach provides upper bounds that are 33% (resp. 10%) lower those than obtained from benchmark spatial (resp. temporal) aggregation approaches.

Graph Representation Learning for Energy Demand Data: Application to Joint Energy System Planning under Emissions Constraints

A rapid transformation of current electric power and natural gas (NG) infrastructure is imperative to meet the mid-century goal of CO2 emissions reduction requires. This necessitates a long-term planning of the joint power-NG system under representative demand and supply patterns, operational constraints, and policy considerations. Our work is motivated by the computational and practical challenges associated with solving the generation and transmission expansion problem (GTEP) for joint planning of power-NG systems. Specifically, we focus on efficiently extracting a set of representative days from power and NG data in respective networks and using this set to reduce the computational burden required to solve the GTEP. We propose a Graph Autoencoder for Multiple time resolution Energy Systems (GAMES) to capture the spatio-temporal demand patterns in interdependent networks and account for differences in the temporal resolution of available data. The resulting embeddings are used in a clustering algorithm to select representative days. We evaluate the effectiveness of our approach in solving a GTEP formulation calibrated for the joint power-NG system in New England. This formulation accounts for the physical interdependencies between power and NG systems, including the joint emissions constraint. Our results show that the set of representative days obtained from GAMES not only allows us to tractably solve the GTEP formulation, but also achieves a lower cost of implementing the joint planning decisions.

Interpretable Machine Learning Models for Modal Split Prediction in Transportation Systems

Modal split prediction in transportation networks has the potential to support network operators in managing traffic congestion and improving transit service reliability. We focus on the problem of hourly prediction of the fraction of travelers choosing one mode of transportation over another using high-dimensional travel time data. We use logistic regression as base model and employ various regularization techniques for variable selection to prevent overfitting and resolve multicollinearity issues. Importantly, we interpret the prediction accuracy results with respect to the inherent variability of modal splits and travelers' aggregate responsiveness to changes in travel time. By visualizing model parameters, we conclude that the subset of segments found important for predictive accuracy changes from hour-to-hour and include segments that are topologically central and/or highly congested. We apply our approach to the San Francisco Bay Area freeway and rapid transit network and demonstrate superior prediction accuracy and interpretability of our method compared to pre-specified variable selection methods.