Online Planning of Power Flows for Power Systems Against Bushfires Using Spatial Context

2024-04-20

arXiv.org

AI Summary

Forest fires induce severe disturbances in power systems, necessitating adaptive real-time optimal power flow (OPF) dispatch under spatiotemporal uncertainty. Method: We propose a spatiotemporally aware online OPF scheduling framework. It features a Moore-neighborhood-based wildfire propagation model, where fire geography is formalized as “spatial context” for the first time. We design a context-aware online learning algorithm that adapts to nonstationary environments with unknown propagation and suppression probabilities, and theoretically establish its regret bound—strictly superior to baseline methods. Integration of periodic state sensing and sequential OPF re-optimization enables fire-driven real-time dispatch. Results: Evaluated on real NSW wildfire data and two actual power grids, our approach significantly reduces dispatch cost and load-shedding risk while ensuring low-regret, robust operation under dynamic fire conditions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The 2019-20 Australia bushfire incurred numerous economic losses and significantly affected the operations of power systems. A power station or transmission line can be significantly affected due to bushfires, leading to an increase in operational costs. We study a fundamental but challenging problem of planning the optimal power flow (OPF) for power systems subject to bushfires. Considering the stochastic nature of bushfire spread, we develop a model to capture such dynamics based on Moore's neighborhood model. Under a periodic inspection scheme that reveals the in-situ bushfire status, we propose an online optimization modeling framework that sequentially plans the power flows in the electricity network. Our framework assumes that the spread of bushfires is non-stationary over time, and the spread and containment probabilities are unknown. To meet these challenges, we develop a contextual online learning algorithm that treats the in-situ geographical information of the bushfire as a 'spatial context'. The online learning algorithm learns the unknown probabilities sequentially based on the observed data and then makes the OPF decision accordingly. The sequential OPF decisions aim to minimize the regret function, which is defined as the cumulative loss against the clairvoyant strategy that knows the true model parameters. We provide a theoretical guarantee of our algorithm by deriving a bound on the regret function, which outperforms the regret bound achieved by other benchmark algorithms. Our model assumptions are verified by the real bushfire data from NSW, Australia, and we apply our model to two power systems to illustrate its applicability.

Problem

• Online planning of power flows against bushfires
• Optimizing power flow considering bushfire spread dynamics
• Minimizing operational costs with spatial context learning

Innovation

• Online optimization modeling framework
• Contextual online learning algorithm
• Theoretical guarantee on regret function