Risk is a critical consideration in many energy-related problems, where stakeholders are often sensitive to rare but costly events. However, traditional online algorithms typically optimize expected cost and can perform poorly in such risk-sensitive settings. Motivated by this challenge, we study the design of algorith...
Lukas Himmelreich, Nicolas H. Christianson, A. Wierman· ACM SIGMETRICS Performance E...· 1 citation
DCEmbed is proposed, a heuristic for optimization problems with embedded neural surrogates that leverages the difference-of-convex (DC) representation of the network and avoids adding activation binaries, and demonstrates much faster progress toward high-quality feasible solutions than approaches using exact mixed-inte...
Akshay Sreekumar, Nicolas H. Christianson, P. Donti et al.· 0 citations
A hierarchical receding-horizon controller is proposed that separates slow server reconfiguration from fast throttling recourse, and offers significant speedups compared to standard optimization solvers, computing near-optimal plans within a 20 second real-time control interval.
Akshay Sreekumar, Nicolas H. Christianson, Fiodar Kazhamiaka et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.