Search

Two-stage adaptive robust optimization (ARO) is a powerful approach for planning under uncertainty, balancing first-stage decisions with recourse decisions made after uncertainty is realized. To account for uncertainty, modelers typically define a simple uncertainty set over which potential outcomes are considered. However, classical methods for defining these sets unintentionally capture a wide range of unrealistic outcomes, resulting in overly-conservative and costly planning in anticipation of unlikely contingencies. In this work, we introduce AGRO, a solution algorithm that performs adversarial generation for two-stage adaptive robust optimization using a variational autoencoder. AGRO generates high-dimensional contingencies that are simultaneously adversarial and realistic, improving the robustness of first-stage decisions at a lower planning cost than standard methods. To ensure generated contingencies lie in high-density regions of the uncertainty distribution, AGRO defines a tight uncertainty set as the image of "latent" uncertainty sets under the VAE decoding transformation. Projected gradient ascent is then used to maximize recourse costs over the latent uncertainty sets by leveraging differentiable optimization methods. We demonstrate the cost-efficiency of AGRO by applying it to both a synthetic production-distribution problem and a real-world power system expansion setting. We show that AGRO outperforms the standard column-and-constraint algorithm by up to 1.8% in production-distribution planning and up to 11.6% in power system expansion.

We study the management of product transitions in a semiconductor manufacturing firm that requires the coordination of resource allocation decisions by multiple, autonomous Product Divisions using a multi-follower bilevel model to capture the hierarchical and decentralized nature of this decision process. Corporate management, acting as the leader, seeks to maximize the firm's total profit over a finite horizon. The followers consist of multiple Product Divisions that must share manufacturing and engineering resources to develop, produce and sell products in the market. Each Product Division needs engineering capacity to develop new products, and factory capacity to produce products for sale while also producing the prototypes and samples needed for the product development process. We model this interdependency between Product Divisions as a generalized Nash equilibrium problem at the lower level and propose a reformulation where Corporate Management acts as the leader to coordinate the resource allocation decisions. We then derive an equivalent single-level reformulation and develop a cut-and-column generation algorithm. Extensive computational experiments evaluate the performance of the algorithm and provide managerial insights on how key parameters and the distribution of decision authority affect system performance.

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.

Building heat electrification is central to economy-wide decarbonization efforts and directly affects energy infrastructure planning through increasing electricity demand and reducing the building sector's use of gas infrastructure that also serves the power sector. Here, we develop a modeling framework to quantify end-use demand for electricity and gas in the buildings sector under various electrification pathways and evaluate their impact on co-optimized bulk power-gas infrastructure investments and operations under deep decarbonization scenarios. Applying the framework to study the U.S. New England region in 2050 across 20 weather scenarios, we find high electrification of the residential sector can increase sectoral peak and total electricity demands by up to 56-158% and 41-59% respectively relative to business-as-usual projections. Employing demand-side measures like building envelope improvements under high electrification, however, can reduce the magnitude and weather sensitivity of peak load as well as induce overall efficiency gains, reducing the combined residential sector energy demand for power and gas by 28-30% relative to the present day. Notably, a combination of high electrification and envelope improvements yields the lowest bulk power-gas system cost outcomes. Accounting for \bt{midstream} methane emissions from gas supply chain increase the reliance on low-carbon fuels, which indirectly improves the cost-effectiveness of end-use electrification. Similarly, we find that demand flexibility programs can reduce the total system cost by up to 6.3%.

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.

The transition to a deeply decarbonized energy system requires coordinated planning of infrastructure investments and operations serving multiple end-uses while considering technology and policy-enabled interactions across sectors. Electricity and natural gas (NG), which are vital vectors of today's energy system, are likely to be coupled in different ways in the future, resulting from increasing electrification, adoption of variable renewable energy (VRE) generation in the power sector and policy factors such as cross-sectoral emissions trading. This paper develops a least-cost investment and operations model for joint planning of electricity and NG infrastructures that considers a wide range of available and emerging technology options across the two vectors, including carbon capture and storage (CCS) equipped power generation, low-carbon drop-in fuels (LCDF) as well as long-duration energy storage (LDES). The model incorporates the main operational constraints of both systems and allows each system to operate under different temporal resolutions consistent with their typical scheduling timescales. We apply the modeling framework to evaluate power-NG system outcomes for the U.S. New England region under different technology, decarbonization goals, and demand scenarios. Under a global emissions constraint, ranging between 80-95\% emissions reduction compared to 1990 levels, the least-cost solution disproportionately relies on using the available emissions budget to serve non-power NG demand and results in the power sector using only 15-43\% of the emissions budget.

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.