S3TS: Stochastic Scenario-Structured Tree Search for Advanced Planning Under Uncertainty
2026-06-01 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed a new planning method called S3TS to help manage energy systems better by dealing with both complicated system behaviors and uncertainties from things like renewable energy. Their method uses a special tree structure to represent different uncertain future scenarios while allowing the use of complex models. They tested S3TS on a simulated energy demand problem similar to one used in Belgium and found it works very well, especially when the system is non-linear, saving costs compared to other common methods. This approach bridges a gap between existing tools that handle either uncertainty or complexity, but not both together.
energy schedulingstochastic optimizationscenario treesnon-linear modelsMonte Carlo Tree Searchdemand responserenewable energy uncertaintyimbalance settlementenergy dispatch
Authors
Fabio Pavirani, Bert Claessens, Pierre Pinson, Chris Develder
Abstract
Effective scheduling in the energy sector is essential to ensure the reliable operation of electrical grids and their connected assets by, for instance, optimizing the dispatch of generation units and storage systems. An effective planning strategy must (a) accommodate advanced and potentially non-linear system models -- exploiting the increasing data availability of modern grids, and (b) explicitly handle uncertainties arising, for instance, from the integration of renewable energy sources. While existing approaches can address either non-linearity (e.g., Monte Carlo Tree Search) or uncertainty (e.g., stochastic mathematical optimization), there is a lack of planning techniques capable of addressing both challenges simultaneously. To bridge this gap, we propose a Stochastic Scenario-Structured Tree Search (S3TS) algorithm that explicitly represents uncertainty through scenario trees while enabling the integration of advanced non-linear models. We evaluate S3TS on a simulated demand response signal publication problem, largely mimicking the imbalance settlement mechanism in Belgium. The results demonstrate near-optimal performance in linear, analytically tractable settings, with costs within 14% of the mathematically optimal solution conditioned to the scenario trees. In highly non-linear scenarios, S3TS significantly outperforms baseline methods, achieving cost reductions of up to 51% and 5.4% compared to a myopic algorithm and deterministic MCTS, respectively.