【摘要】 在LTE-A中采用异构网络能提高用户的性能,但是由于小区间使用相同的频谱资源,产生了小区间干扰,影响了用户性能,从而需要采用小区间干扰协调技术来控制小区间干扰(ICI)。虽然现有的小区间干扰协调技术可以降低小区间干扰,但是存在Macro用户性能影响较大的问题。为此,提出了基于Q学习的ETPS算法,在不影响Macro用户性能的前提下,降低小区间干扰。仿真结果表明,QL-ETPS算法较传统固定ABS/RP-ABS子帧配置方案性能更优,可以在尽量不影响Macro基站用户的前提下,提高Pico基站边缘用户的吞吐量。更多还原

【Abstract】 The heterogeneous network adopted by long-term evolution-advance(LTE-A)system can improve the user performance. The inter-cell interference(ICI) is generated and the user performance is influenced due to the shared frequency spectrum among the inter-cells,so it is necessary to adopt the inter-cell interference coordination(IC)technology to control the ICI.Although the existing inter-cell interference coordination technology can reduce the ICI efficiently,but influence the Macro user performance greatly. To solve this problem,a Q-learning based enhance transmission power subframe(QL-ETPS)algorithm is proposed,which can reduce the ICI on the premise of ensuring the Macro user performance. The simulation results show that the performance of the proposed QL-ETPS algorithm is better than that of the conventional fixed ABS/RP-ABS configuration scheme,and can improve the throughput of the Pico base station edge user while ensuring the performance of Macro base station user.更多还原