Abstract—Recently introduced Colonial Competitive Algorithm (CCA) has shown its excellent capability on diverse optimization tasks. This optimization algorithm is inspired by socio-political process of imperialistic competition. In this study a uniform linear array (ULA) adaptive antenna that uses this global search heuristic is developed. The obtained results are compared with those of a Genetic Algorithm (GA) and Least Mean Square (LMS). The evolutionary algorithms are applied to the problem of beamforming in two separate parts based on minimizing signal-to-interference-plus-noise-ratio (SINR). First the antenna array is considered static. In the second part the antenna is assumed to be dynamic and is moving with a constant speed that an optimization task with a cost function varying over the time. The results show not only GA and CCA perform better than LMS in both parts, but also CCA outperforms GA and LMS in these parts. Key words—Smart antenna, Colonial Competitive Algorithm (CCA), Least Mean Square (LMS), Genetic Algorithms (GA), optimization I. INTRODUCTION Smart antennas have been widely used in the wireless communication systems and are proposed as a solution to enhance the capacity of the system [1]. They are also considerable due to their potential for decreasing the interference, improving quality of service [2], enhancing power control, and extending battery life in portable units of these systems. In an adaptive antenna system, developing efficient algorithms is crucial for estimating the Direction of Arrival (DOA) of all impinging signals and adaptive beamforming [3]. Fig. 1 shows an adaptive beamforming system. This paper focuses on beamforming algorithm for obtaining excitation weights that are shown as W 1 , W 2 , …, W N-1 in Fig. 1 such that the maximum pattern of the antenna and nulls are formed toward the desired and interference signals respectively. For obtaining optimal excitation weights, some of classic algorithms such as Least Mean Square (LMS), Recursive Least Square (RLS), and Normalized Least Mean Square (NLMS) are based on training sequence. Some other techniques that don’t require training sequence are differentiated from the blind adaptive algorithms such as Bussgang and adapting is performed to restore some known property of received signal [4]. Evolutionary algorithms, such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO) and simulated annealing are a set of algorithms that are suggested in the past decades for solving optimization problems in different fields. These methods are also applied to smart antenna related problems, recently [5-6]. Colonial Competitive Algorithm (CCA) is a new socio-politically motivated optimization algorithm that has recently been introduced for solving different optimization problems. This evolutionary optimization strategy has shown great performance in both convergence rate and better global optima achievement [7]. Nevertheless, its effectiveness, limitations and applicability in various domains are currently being extensively investigated. In this paper CCA is applied to solve the beamforming problem in a smart antenna system. In addition to static optimization, we have also used this algorithm for dynamic beamforming, and compared it with GA. Dynamic beamforming leads to the optimization of a cost function that is varying over the time. This paper is organized in the following sections: section 2 briefly describes the Uniform Linear Array’s (ULA) structure and the LMS algorithm. Section 3 states the problem of beamformin that is going to be solved by CCA and GA. A brief description of CCA is given in section 4. Simulation and comparisons results are shown in section 5 and finally, conclusion is presented. II. UNIFORM LINEAR ARRAY STRUCTURE A uniform linear array that is shown in Fig. 2, has N elements, numbered 0,1,…,N-1, with inter element spacing of half wavelength. Signal s(t) is carried by propagating wave that is received by each element of the array at a different times [1]. The difference in the time of arrival at the zeroth and the nth element is converted to phase difference between these elements. Having signal s(t), the received signal at the nth element, x n [k], can approximately be stated in the following form. [] [ ]exp( sin( )) [] () 0 x k sk jk nd ska n n      (1) Where d is the distance between two consecutive elements and   2 0  k , where λ is wavelength of the operating frequency of the signal. Having r signals, each of which arriving to the antenna with its specific angle of arrival, θ i {i = 0, 1, …,r-1} the equation (1) can be rewritten as: Adaptive beamforming using a novel numerical optimization algorithm Mahnaz Roshanaei and Esmaeil Atashpaz-Gargari School of Electrical and Computer Engineering University of Tehran, Tehran, Iran com . gmail @ e _ atashpaz , ir . ac . ut . ece @ roshanaei . m Caro Lucas Center of Excellence for Control and Intelligent Processing, Department of Electrical and Computer Engineering University of Tehran, PO Box 14395-515, Tehran, Iran lucas@ipm.ir Fig. 1. Adaptive Beamforming System