In this paper, an LSTM-aided hybrid random access scheme (LSTMH-RA) is proposed to support diverse quality of service (QoS) requirements in machine-type communication (MTC) networks where massive MTC (mMTC) devices and ultra-reliable low latency communications (URLLC) devices coexist. In the proposed LSTMH-RA scheme, mMTC devices access the network via a timing advance (TA)-aided four-step procedure to meet massive access requirement, while the access procedure of the URLLC devices is completed in two steps coupled with the mMTC devices' access procedure to reduce latency. In addition, the resource allocated to mMTC and URLLC devices are isolated to avoid interference between them by using 6G network slicing. Furthermore, we propose an attention-based LSTM prediction model to predict the number of active URLLC devices, thereby determining the parameters of the multi-user detection algorithm to guarantee the latency and reliability access requirements of URLLC devices. We analyze the successful access probability of the LSTMH-RA scheme. Numerical results show that, compared with the benchmark schemes, the proposed LSTMH-RA scheme can significantly improve the successful access probability, and thus satisfy the diverse QoS requirements of URLLC and mMTC devices.
翻译:在本文件中,提议采用LSTMTM辅助的混合随机访问计划(LSTMTMH-RA),以支持机型通信网络中大型MTC(MMTC)装置和超可靠低潜伏通信(URLLLC)装置共存的机型通信网络的服务质量要求多样化;在拟议的LSTMH-RA办法中,MMTC装置通过一个时间先先先行(TA)辅助的四步程序进入网络,以满足大规模访问要求,而URLLLC装置的准入程序则在与MMTC装置接入程序相结合的两个步骤中完成,以减少延迟性;此外,分配给MMMTC和URLC装置的资源被隔离,以避免它们之间的干扰;此外,我们提出一个基于关注的LSTM预测模型,以预测运行中的URLLC装置的数目,从而确定多用户检测算法的参数,以保证URLLLC装置的通关性和可靠性要求;我们分析了LSTMH-RA装置的成功访问概率,我们分析了LMS-RA办法的多样化计划、NMTMT的概率,从而与基准计划相比,可以大大改进LS-RA要求。