4 papers
Neural networks for multi-horizon stochastic programming
Hongyu Zhang, Gabriele Sormani, Enza Messina +2
This paper proposes a machine-learning-based solution approach for solving multi-horizon stochastic programs. The approach embeds a deep learning neural network into a multi-horizo…
Adaptive Benders decomposition and enhanced SDDP for multistage stochastic programs with block-separable multistage recourse
Nicolò Mazzi, Ken Mckinnon, Hongyu Zhang
This paper proposes an algorithm to efficiently solve multistage stochastic programs with block separable recourse where each recourse problem is a multistage stochastic program wi…
Integrated investment, retrofit and abandonment energy system planning with multi-timescale uncertainty using stabilised adaptive Benders decomposition
Hongyu Zhang, Ignacio E. Grossmann, Ken McKinnon +3
We propose the REORIENT (REnewable resOuRce Investment for the ENergy Transition) model for energy systems planning with the following novelties: (1) integrating capacity expansion…
Modelling and analysis of multi-timescale uncertainty in energy system planning
Hongyu Zhang, Erlend Heir, Asbjørn Nisi +1
Recent developments in decomposition methods for multi-stage stochastic programming with block separable recourse enable the solution to large-scale stochastic programs with multi-…