Problem
Research questions and friction points this paper is trying to address.
implicit balancing
model predictive control
balancing market modeling
convexity
transmission system operators
Neural Network-Assisted Model Predictive Control for Implicit Balancing
🤖 AI Summary
Existing implicit balancing market models struggle to simultaneously achieve accuracy, integrability, and computational efficiency within model predictive control (MPC) frameworks, often neglecting transmission system operator (TSO) manual interventions and sub-15-minute dynamics. To address these limitations, this work proposes a novel data-driven approach that integrates input convex neural networks with an attention-based input gating mechanism into an MPC framework. The input convex neural network captures market uncertainty while preserving the convexity of the underlying optimization problem, and the attention-based gating mechanism enhances computational efficiency by selectively focusing on relevant inputs. Experimental evaluation using real-world Belgian market data demonstrates that the proposed method significantly improves MPC decision-making performance while reducing computational overhead.
📝 Abstract
In Europe, balance responsible parties can deliberately take out-of-balance positions to support transmission system operators (TSOs) in maintaining grid stability and earn profit, a practice called implicit balancing. Model predictive control (MPC) is widely adopted as an effective approach for implicit balancing. The balancing market model accuracy in MPC is critical to decision quality. Previous studies modeled this market using either (i) a convex market clearing approximation, ignoring proactive manual actions by TSOs and the market sub-quarter-hour dynamics, or (ii) machine learning methods, which cannot be directly integrated into MPC. To address these shortcomings, we propose a data-driven balancing market model integrated into MPC using an input convex neural network to ensure convexity while capturing uncertainties. To keep the core network computationally efficient, we incorporate attention-based input gating mechanisms to remove irrelevant data. Evaluating on Belgian data shows that the proposed model both improves MPC decisions and reduces computational time.
Innovation
Methods, ideas, or system contributions that make the work stand out.
input convex neural network
model predictive control
implicit balancing
attention-based input gating
balancing market modeling
🔎 Similar Papers
No similar papers found.
