Landscape Properties and Hybrid Evolutionary Algorithm for Optimum Multiuser Detection Problem
Optimum multiuser detection (OMD) for CDMA systems is an NP-complete problem. Fitness landscape has been proven to be very useful for understanding the behavior of combinatorial optimization algorithms and can help in predicting their performance. This paper analyzes the statistic properties of the fitness landscape of the OMD problem by performing autocorrelation analysis, fitness distance correlation test and epistasis measure. The analysis results, including epistasis variance, correlation length and fitness distance correlation coefficient in different instances, explain why some random search algorithms are effective methods for the OMD problem and give hints how to design more efficient randomized search heuristic algorithms for it. Based on these results, a multi-start greedy algorithm is proposed for multiuser detection and simulation results show it can provide rather good performance for cases where other suboptimum algorithms perform poorly.
KeywordsLogarithm Likelihood Function Fitness Landscape Multiuser Detection Multiple Access Interference Landscape Property
- 10.Stadler, P.F.: Fitness Landscape. Lecture Notes in Physics, pp. 183–204. Springer, Heidelberg (2002)Google Scholar
- 11.Reeves, C., Wright, C.: An experimental design perspective on genetic algorithms. In: Whitley, L.D., Vose, M.D. (eds.) Foundations of Genetic Algorithms, vol. 3, pp. 7–22. Morgan Kaufmann, San Mateo (1995)Google Scholar