没有合适的资源?快使用搜索试试~ 我知道了~
基于图形表示的异构超密集网络的机器学习技术研究.docx
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 1 下载量 53 浏览量
2022-12-15
14:24:19
上传
评论 1
收藏 569KB DOCX 举报
温馨提示
试读
16页
基于图形表示的异构超密集网络的机器学习技术研究.docx
资源推荐
资源详情
资源评论
Driven by the astounding development of smart phones, mobile applications and the Internet
of Things (IoT), traffic demand grows exponentially in mobile networks. Heterogeneous ultra-
dense networks (H-UDNs) [such as femtocell/picocell, cloud radio access network (Cloud-RAN),
and fog radio access network (Fog-RAN)] have emerged as a promising solution to sustain the
enormous mobile traffic demand. The coverage and capacity of wireless networks are improved
through densified access points (APs) and communication links, which greatly enhances the
spatial reuse of limited frequency resources.
H-UDNs, however, bring opportunities as well as formidable challenges. An H-UDN is
expected to support an abundance of new applications with various new service requirements. For
instance, massive machine-type communications require high connection density; auto pilot cars
require low latency and ultra-high reliability; augmented reality requires both high throughput and
low latency. To effectively and efficiently sustain these manifold requirements in a complicated
system like an H-UDN is undoubtedly a mission worth pursuing. In addition, the existing
advanced techniques, such as multi-cell coordination and massive multiple-input multiple-output
(MIMO), cannot be easily extended to a H-UDN. This is because many assumptions used in the
existing techniques are no longer valid or accurate in H-UDNs. For example, the law of large
numbers and the random matrix theory have been widely used to simplify the analysis of massive
MIMO. However, due to random scattering of APs and users, the channels between APs and users
follow heavy-tailed distributions that are not analyzable for algorithm design using the existing
random matrix theory
[1]
. Moreover, the high density of devices leads to prohibitively high
complexity if the existing algorithms are directly applied. Consider, for example, a system
supporting thousands or even tens of thousands of machine-type devices in a small area. The
complexity of jointly detecting the signals sent by the devices using, say, a simple linear minimum
mean square error (LMMSE) detector would cause unaffordable computational complexity, since
the complexity of LMMSE grows cubically in the number of terminals.
Machine learning is a family of promising techniques to address the above-mentioned
challenges. Unlike the traditional model-based approaches that are optimized based on
mathematically convenient models, machine-learning based approaches are driven by real-world
data, and thus are less sensitive to model imperfections. Previously, machine learning has been
extensively used to solve a wide variety of problems in image/audio processing, social behavior
analysis, project management, etc. The applications of machine learning in wireless networks start
to attract research interests in recent years. As discussed in Ref. [2-3] and the references therein,
machine learning approaches have potential applications in cognitive radios, massive MIMOs,
device-to-device communications, etc. The goal of this paper is to complement their contributions
by investigating the use of machine learning in H-UDNs, especially for solving collaborative
signal processing and resource allocation problems. Specifically, we discuss how to utilize
graphical representations of H-UDNs to design efficient machine learning algorithms. We first
introduce several recently proposed signal processing algorithms (namely, randomized message
passing
[1]
, bilinear generalized approximate message passing (BIG-AMP)
[4]
, and deep learning
[5]
)
based on the coverage graph of APs. Then, we extend the discussion to resource management
problems, such as radio resource allocation, power allocation, and cache placement.
Reinforcement learning, deep learning, and semi-supervised learning are introduced as potential
solutions, where the graphical models based on certain features of H-UDNs can help greatly
improve the efficiency of the solutions.
1. H-UDNs and Graphical Representations
In this section, we first introduce the main entities of an H-UDN. Then, H-UDNs are
modelled as graphs that depict various interactions between network entities. Based on these
graphs, machine learning algorithms will be discussed in later sections for efficient network
operations.
1.1 H-UDNs
An H-UDN consists of various types of network architectures as illustrated in Fig. 1. In the
following part, we introduce typical network architectures as well as their unique features.
1) Macrocell and Picocell/Femtocell: Macrocells are cells that provide radio coverage served
by high power base stations (BSs) in a cellular network. Picocells and femtocells are served by
small and low-power BSs to provide uninterrupted coverage for end users even in areas difficult
or expensive to be covered by macrocells. In particular, femtocells are deployed, powered, and
connected by end users or small businesses with less active control from network operators.
Hence, the operation of femtocells is more autonomous than picocells and macrocells. As such,
multi-cell coordination in an H-UDN must consider different levels of processing power, backhaul
limitation, information availability, controllability, and willingness of participation of different
cells.
图 1 An H-UDN consists of a femtocell, a picocell, a macrocell, a Cloud-RAN, and a Fog-RAN,
where the Fog-RAN incorporates the macrocell and part of the Cloud-RAN. A coverage graph and
a conflict graph are induced from the Cloud-RAN.
Figure 1. An H-UDN consists of a femtocell, a picocell, a macrocell, a Cloud-RAN, and a Fog-
RAN, where the Fog-RAN incorporates the macrocell and part of the Cloud-RAN. A coverage
graph and a conflict graph are induced from the Cloud-RAN.
下载: 全尺寸图片 幻灯片
2) Cloud-RAN: A Cloud-RAN consists of three key components: ① the distributed remote
radio heads (RRHs), ② a pool of baseband processing units (BBUs) in a data center cloud and
③ a high-bandwidth and low-latency optical transport network connecting BBUs and RRHs.
Compared with traditional BSs, the RRHs are lightweight, allowing them to be deployed in a high
density with low cost. Meanwhile, the centralized BBU pool enables seamless coordination of
RRHs for collaborative signal processing, radio resource allocation, network virtualization, etc.
Thus, a natural challenge is to design scalable RRH coordination algorithms to avoid high
overhead and computational cost caused by the high density of RRHs.
3) Fog-RAN: The key idea of Fog-RAN is to take full advantages of local computing,
communication, and storage capabilities at edge devices (such as RRHs, smartphones, and
laptops.), so as to avoid heavy communication overhead and large latency caused by
backhaul/fronthaul transmission and centralized processing. To fully utilize the capabilities at
edge devices, tasks should be efficiently decomposed and assigned to different devices. As such,
decentralized control is critical in Fog-RAN. As a task offloading scheme, Fog-RAN is usually
overlaid on other network architectures. For example, the Fog-RAN in Fig. 1 partially merges
with a macrocell and a Cloud-RAN.
The above-mentioned network architectures may coexist in a single H-UDN. For example,
coordination among devices may rely on centralized processing in the BBU pool of a Cloud-RAN.
Meanwhile, the computational tasks may be offloaded to network edges of a Fog-RAN for delay-
sensitive applications. In a nutshell, a H-UDN is an inseparable continuum of different types of
networks. Signal processing and resource management in such a complicated system become
challenging due to the close interaction between different network entities. As a result,
interference across different networks must be carefully managed. Likewise, different types of
剩余15页未读,继续阅读
资源评论
- youyou06082024-01-10超级好的资源,很值得参考学习,对我启发很大,支持!
罗伯特之技术屋
- 粉丝: 3691
- 资源: 1万+
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功