Learning-assisted Stochastic Capacity Expansion Planning: A Bayesian Optimization Approach
This work addresses cost-effective decarbonization for regional energy systems by improving computational efficiency in handling uncertainty, though it is incremental as it builds on existing time series aggregation methods.
The paper tackles the computational intractability of stochastic capacity expansion planning for energy systems by proposing a learning-assisted method using Bayesian optimization to identify low-cost decisions, resulting in up to 3.8% cost savings compared to benchmarks.
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.