Thesis defence V. Rostampour Samarin: smart energy
24 September 2018 10:00 - Location: Aula, TU Delft - By: webredactie
Distributed Data-Driven Decision Making in Uncertain Networked Systems with Applications in Smart Energy Systems. Promotor 1: Dr. T. Keviczky (3mE); Promotor 2: Prof.dr.ir. N. van de Wouw (3mE).
This dissertation aims to develop a rigorous distributed approach to decision making using scenario-based techniques forlarge-scale networks of interconnected uncertain dynamical systems (called agents). A scenario program is afinite-dimensional optimization problem in which an objective function is minimized under constraints that are associatedwith finitely many, independently and identically distributed (i.i.d.), scenarios of a random parameter. Theoretical andpractical interest in scenario programs originates from the fact that these problems are typically efficiently solvable whilebeing closely related to robust and chance-constrained programs. In the former, the constraint is enforced for alladmissible random parameters, whereas in the latter, the constraint is enforced up to a given level of probability.However, finding solutions of the resulting large-scale scenario optimization problem for uncertain networked systemsposes several difficulties, e.g., computational cost for a central control unit.The main contribution of this dissertation is the design of a technique to decompose a large-scale scenario program into small-scale distributed scenario programs for each agent. Building on existing results in literature, we provide novelguarantees to quantify the robustness of the resulting solutions in a distributed framework. In this setting, each agentneeds to exchange some information with its neighboring agents that is necessary due to the statistical learning featuresof the proposed setup. However, this inter-agent communication scheme might give rise to some concerns about theagents' private information. We therefore present a novel privatized distributed framework, based on the so-calleddifferential privacy concept, such that each agent can share requested information while preserving its privacy. In addition,a soft communication scheme based on a set parameterization technique, along with the notion of probabilisticallyreliable set, is introduced to reduce the required communication burden. Such a reliability measure is incorporated intothe feasibility guarantees of agent decisions in a probabilistic sense. The theoretical guarantees of the proposeddistributed scenario-based decision making framework coincide with the centralized counterpart, however the scaling ofthe results with the number of agents remains an issue.
For access to theses by the PhD students you can have a look in TU Delft Repository, the digital storage of publications of TU Delft. Theses will be available within a few weeks after the actual thesis defence.