The Parallel Algorithm Based on Genetic Algorithm for Improving the Performance of Cognitive Radio

Abstract

The intercarrier interference (ICI) problem of cognitive radio (CR) is severe. In this paper, the machine learning algorithm is used to obtain the optimal interference subcarriers of an unlicensed user (un-LU). Masking the optimal interference subcarriers can suppress the ICI of CR. Moreover, the parallel ICI suppression algorithm is designed to improve the calculation speed and meet the practical requirement of CR. Simulation results show that the data transmission rate threshold of un-LU can be set, the data transmission quality of un-LU can be ensured, the ICI of a licensed user (LU) is suppressed, and the bit error rate (BER) performance of LU is improved by implementing the parallel suppression algorithm. The ICI problem of CR is solved well by the new machine learning algorithm. The computing performance of the algorithm is improved by designing a new parallel structure and the communication performance of CR is enhanced.

The Optimization Algorithm for CR System Based on Optimal Wavelet Filter

“…The nodes of the optimal wavelet filter include (5,31)(5,30)(6,59)(6,58)(6,57)(6,56)(5, 27)(5,26)(4,12)(2,2) (6,31)(6,30)(6,29)(6,28)(6,27)(6,26)(5,12) (6,23)(6,22)(6,21)(6,20)(4,4)(3,1)(6,7) (6,6)(6,5)(7,9)(7,8)(5, 1)(6,26) (7,3)(7,2)(6,0). The ICI energy of system using our optimization algorithm is compared with deactivating the adjacent subcarriers algorithm [10], the optimal deactivated subcarriers algorithm [11], and the ICI suppression algorithm based on GA [12] in Figure 4. It is shown that these masking subcarriers algorithms and our optimal wavelet filter algorithm all can reduce the ICI energy of system and the ICI energy is decreased with the number of masked subcarriers increasing.…”

“…But the advantage of new optimal wavelet filter algorithm proposed in the paper does not need to sacrifice any bandwidth of un-LU. For scene 1, the BER performance of system using our optimization algorithm is compared with deactivating the adjacent subcarriers algorithm [10], the optimal deactivated subcarriers algorithm [11], and the ICI suppression algorithm based on GA [12] with 4 subcarriers masked in Figure 5. It is shown that the BER performance of the new optimal wavelet filter algorithm without sacrificing any un-LU's subcarriers is better than other three masking subcarriers algorithms with 4 subcarriers of un-LU wasted.…”

“…To simulate we use the two path wireless channel model as the wireless channel environment. The impulse response of channel is defined as follows [12]:…”

“…The machine learning algorithm also is designed to obtain the optimal interference subcarriers. Masking the optimal interference subcarriers can suppress ICI [12]. All these three algorithms realize ICI suppression by sacrificing the bandwidth of the un-LU.…”

One‐to‐Many Relationship Based Kullback Leibler Divergence against Malicious Users in Cooperative Spectrum Sensing

“…Detection results of the orthogonal frequency division multiplexing (OFDM) signals in the frequency selective fading channels are considered in [9,10]. Optimal interference subcarriers are obtained based on Genetic Algorithm (GA) to suppress intercarrier interference of the unlicensed user to the licensee [11]. In [12], side-lobes reduction using generalized side-lobe canceller combined with GA and differential evolution is proposed.…”