Particle swarm algorithm with adaptive constraint handling and integrated surrogate model for the management of petroleum fields

Abstract

a b s t r a c tThis paper deals with the development of effective techniques to automatically obtain the optimum management of petroleum fields aiming to increase the oil production during a given concession period of exploration. The optimization formulations of such a problem turn out to be highly multimodal, and may involve constraints. In this paper, we develop a robust particle swarm algorithm coupled with a novel adaptive constraint-handling technique to search for the global optimum of these formulations. However, this is a population-based method, which therefore requires a high number of evaluations of an objective function. Since the performance evaluation of a given management scheme requires a computationally expensive high-fidelity simulation, it is not practicable to use it directly to guide the search. In order to overcome this drawback, a Kriging surrogate model is used, which is trained offline via evaluations of a High-Fidelity simulator on a number of sample points. The optimizer then seeks the optimum of the surrogate model.

Self-organising swarms of firefighting drones: Harnessing the power of collective intelligence in decentralised multi-robot systems

“…3 (black region) can be found in [43], and the right boundary of the white region happens to be the same as φ mean for Behaviour Type 1 in Eq. ( 20) in [41].…”

“…It suffices to say that the attractors in Eq. ( 1) can be combined into a single attractor at a given time-step (t) as follows [43,41]:…”

Evolution Control for parallel ANN-assisted simulation-based optimization application to Tuberculosis Transmission Control

“…With the NEC approach, the EA only relies on the surrogate predictions [30] [36]. The surrogate is built using a historical database of simulations and only the best predicted solution returned by the EA is simulated.…”