Heuristic Optimization for the Discrete Virtual Power Plant Dispatch Problem

We consider a virtual power plant, which is given the task of dispatching a fluctuating power supply to a portfolio of flexible consumers. The flexible consumers are modeled as discrete batch processes, and the associated optimization problem is denoted the discrete virtual power plant dispatch problem (DVPPDP). First, the nondeterministic polynomial time (NP)-completeness of the discrete virtual power plant dispatch problem is proved formally. We then proceed to develop tailored versions of the meta-heuristic algorithms hill climber and greedy randomized adaptive search procedure (GRASP). The algorithms are tuned and tested on portfolios of varying sizes. We find that all the tailored algorithms perform satisfactorily in the sense that they are able to find sub-optimal, but usable, solutions to very large problems (on the order of \(10^{5}\) units) at computation times on the scale of just 10 s, which is far beyond the capabilities of the optimal algorithms we have tested. In particular, GRASP sorted shows with the most promising performance, as it is able to find solutions that are both agile (sorted) and well balanced, and consistently yields the best numerical performance among the developed algorithms.