Giovanni Petrone, John Axerio-Cilies, Domenico Quagliarella and Gianluca Iaccarino
A probabilistic non-dominated sorting genetic algorithm (P-NSGA) for multi-objective optimization under uncertainty is presented. The purpose of this algorithm is to create a…
Abstract
Purpose
A probabilistic non-dominated sorting genetic algorithm (P-NSGA) for multi-objective optimization under uncertainty is presented. The purpose of this algorithm is to create a tight coupling between the optimization and uncertainty procedures, use all of the possible probabilistic information to drive the optimizer, and leverage high-performance parallel computing.
Design/methodology/approach
This algorithm is a generalization of a classical genetic algorithm for multi-objective optimization (NSGA-II) by Deb et al. The proposed algorithm relies on the use of all possible information in the probabilistic domain summarized by the cumulative distribution functions (CDFs) of the objective functions. Several analytic test functions are used to benchmark this algorithm, but only the results of the Fonseca-Fleming test function are shown. An industrial application is presented to show that P-NSGA can be used for multi-objective shape optimization of a Formula 1 tire brake duct, taking into account the geometrical uncertainties associated with the rotating rubber tire and uncertain inflow conditions.
Findings
This algorithm is shown to have deterministic consistency (i.e. it turns back to the original NSGA-II) when the objective functions are deterministic. When the quality of the CDF is increased (either using more points or higher fidelity resolution), the convergence behavior improves. Since all the information regarding uncertainty quantification is preserved, all the different types of Pareto fronts that exist in the probabilistic framework (e.g. mean value Pareto, mean value penalty Pareto, etc.) are shown to be generated a posteriori. An adaptive sampling approach and parallel computing (in both the uncertainty and optimization algorithms) are shown to have several fold speed-up in selecting optimal solutions under uncertainty.
Originality/value
There are no existing algorithms that use the full probabilistic distribution to guide the optimizer. The method presented herein bases its sorting on real function evaluations, not merely measures (i.e. mean of the probabilistic distribution) that potentially do not exist.
Details
Keywords
Egidio D’Amato, Elia Daniele, Lina Mallozzi and Giovanni Petrone
The purpose of this paper is to propose a numerical algorithm able to describe the Stackelberg strategy for a multi level hierarchical three-person game via genetic algorithm (GA…
Abstract
Purpose
The purpose of this paper is to propose a numerical algorithm able to describe the Stackelberg strategy for a multi level hierarchical three-person game via genetic algorithm (GA) evolution process. There is only one player for each hierarchical level: there is an upper level leader (player L0), an intermediate level leader (player L1) who acts as a follower for L0 and as a leader for the lower level player (player F) that is the sole actual follower of this situation.
Design/methodology/approach
The paper presents a computational result via GA approach. The idea of the Stackelberg-GA is to bring together GAs and Stackelberg strategy in order to process a GA to build the Stackelberg strategy. Any player acting as a follower makes his decision at each step of the evolutionary process, playing a simple optimization problem whose solution is supposed to be unique.
Findings
A GA procedure to compute the Stackelberg equilibrium of the three-level hierarchical problem is given. An application to a Authority-Provider-User (APU) model in the context of wireless networks is discussed. The algorithm convergence is illustrated by means of some test cases.
Research limitations/implications
The solution to each level of hierarchy is supposed to be unique.
Originality/value
The paper demonstrates the possibility of using computational procedures based on GAs in hierarchical three level decision problems extending previous results obtained in the classical two level case.
Details
Keywords
Mauro Sciarelli, Giovanni C. Landi, Lorenzo Turriziani and Anna Prisco
This research focuses on the relationship between Top Management Team heterogeneity (TMT) and University Spin-Offs (USOs) economic performance according to a micro-foundational…
Abstract
Purpose
This research focuses on the relationship between Top Management Team heterogeneity (TMT) and University Spin-Offs (USOs) economic performance according to a micro-foundational perspective. The purpose consists in exploring whether a high academic representation in TMTs may improve USOs’ performance and how their competencies and backgrounds affect USOs’ economic success.
Design/methodology/approach
The authors employed data from the Italian platform Netval to identify the entire population of USOs in southern Italy. They selected both pure and hybrid spin-offs that had at least one academic member on the TMT. Applying these conditions to our sample selection, the authors came to a population of 136 firms. They applied a hierarchical regression analysis to test the hypotheses.
Findings
Our main findings reveal that the USOs’ economic performance improves with more academicians in the TMT and even in the same scientific field. Our data also shows that CEO duality has a negative impact on economic performance.
Originality/value
This work takes for the first time a micro-foundational perspective to analyze individual-level factors that affect USOs’ performance. The authors tried to bridge a research gap in the USO literature, shedding light on the relationship between TMT composition and new venture performance, considering some significant interactions between team members. Our expected findings also contribute to the general literature on entrepreneurial teams in new ventures and suggest a means to reconcile some inconsistent literature results on TMT heterogeneity and USO performance.