Neural Two-Stage Stochastic Volt-VAR Optimization for Three-Phase Unbalanced Distribution Systems with Network Reconfiguration
This addresses computational intractability in large-scale stochastic optimization for distribution systems, offering a scalable solution for grid operators, though it is incremental as it builds on existing methods with a learning-based acceleration.
The paper tackled the challenge of voltage regulation and reactive power management in distribution networks with intermittent energy resources by proposing a neural two-stage stochastic Volt-VAR optimization method, achieving over 50 times speedup with an optimality gap below 0.30% in simulations.
The increasing integration of intermittent distributed energy resources (DERs) has introduced significant variability in distribution networks, posing challenges to voltage regulation and reactive power management. This paper presents a novel neural two-stage stochastic Volt-VAR optimization (2S-VVO) method for three-phase unbalanced distribution systems considering network reconfiguration under uncertainty. To address the computational intractability associated with solving large-scale scenario-based 2S-VVO problems, a learning-based acceleration strategy is introduced, wherein the second-stage recourse model is approximated by a neural network. This neural approximation is embedded into the optimization model as a mixed-integer linear program (MILP), enabling effective enforcement of operational constraints related to the first-stage decisions. Numerical simulations on a 123-bus unbalanced distribution system demonstrate that the proposed approach achieves over 50 times speedup compared to conventional solvers and decomposition methods, while maintaining a typical optimality gap below 0.30%. These results underscore the method's efficacy and scalability in addressing large-scale stochastic VVO problems under practical operating conditions.