Policy function approximation for optimal power flow control issues

In nowadays operations research, dynamic optimization problems build a central and challenging research topic. Especially in real-world systems such as electric power grids, dynamic problems occur where robust solutions need to be found that enable (near-) optimal control over time in volatile as well as uncertain power grid operation. The authors of this work identified the application of policy function approximation for suchlike problems, where an analytic functions needs to be found that takes an arbitrary state of the dynamic system and outputs appropriate control actions aiming at system-wide goals. Such an approach is very fruitful for robust optimization over time. Applying this approach to two different problem classes in power grid research, this work aims at summarizing this work and identifying potential future issues.