Equitable solutions in QoS-aware service optimization

Abstract

Web services QoS optimization problem using the concept of Lorenz dominance is addressed. Lorenz solutions are equitable and well balanced. Such an approach could simplify the Decision Maker's choice. Evolutionary detection of Lorenz solution seem to be an appealing one. Some stateof-the art MOEAs are slightly modified for addressing the QoS optimization problem. Lorenz solutions drastically reduce the number of solutions in the Pareto set, and thus the decision costs.

Complexity in Adaptive Systems

“…Approaches based on Lorenz dominance have been also experimented in [Suciu et al, 2012]. This type of approach reduces the number of final solutions found by a multiobjective algorithm to a limited set of equitable, wel balanced solutions.…”

“…Source: [Cremene et al, 2012c] attributes aggregation operators examples are presented in [Pop et al, 2011b] and [Suciu et al, 2012]. An example about how the physical distance may be included also as S-C attribute is given in [Pop et al, 2011a].…”

“…The contribution presented in [Suciu et al, 2012] However, the end user may not be an expert in decision making. Thus, providing a large set of solutions could confuse him/her.…”

“…Strength Lorenz Evolutionary Algorithm, SLEA [Suciu et al, 2012], is a variant of SPEA 2 [Zitzler et al, 2001]. SPEA2 is an elitist multi-objective optimization algorithm.…”

“…L-GDE3 [Suciu et al, 2012] The processes corresponding to composite web services have various complexity and are randomly generated. The complexity is adjusted by increasing the number of abstract services from 10 to 50.…”