Tools: MATLAB, Python, GAMS, MapReduce, Hadoop, and Message Passing Interface (MIP)
- Utilized distributed optimization algorithms with consensus dynamics, specifically proximal point algorithms such as ADMM, in asynchronous scenarios to find near-optimal solutions to convex and non-convex problems using graph topology in the context of peer-to-peer energy market.
- Reformulated problems with non-convex constraints using convex analysis and found optimal solutions using ADMM with zero duality gap.
- Conducted rigorous literature review on convex analysis and optimization and meeting with my advisor weekly to present my findings.
More
I worked with a professor on this project since the beginning of March. The end goal is to create a prototype of an energy market that exists on the blockchain. My work mainly dealt with solving various optimization problems related to the energy market in a distributed manner and conducting literature review about distributed optimization.
To get me up to speed, professor has assigned me problem sets from his graduate course that involved solving optimal power flow problems using GAMS and MATLAB. Later on, I learnt about convex optimization by reading Stephen Boyd's and Tyrrell Rockafellar's works, among others, and coded optimization algorithms.