An Efficient Stochastic Gradient Descent Algorithm to Maximize the Coverage of Cellular Networks

Network coverage and capacity optimization is an important operational task in cellular networks. The network coverage maximization by adjusting azimuths and tilts of antennas is focused and the existing approaches are mainly gradient-free methods. A standard gradient descent algorithm and its impro...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on wireless communications Ročník 18; číslo 7; s. 3424 - 3436
Hlavní autoři: Liu, Yaxi, Huangfu, Wei, Zhang, Haijun, Long, Keping
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.07.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Antennas
Azimuth
Base stations
Cellular communication
Cellular network
Cellular networks
computational complexity
coverage optimization
gradient descent
Heuristic methods
Linear programming
Machine learning algorithms
Optimization
stochastic gradient descent
ISSN:1536-1276, 1558-2248
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Network coverage and capacity optimization is an important operational task in cellular networks. The network coverage maximization by adjusting azimuths and tilts of antennas is focused and the existing approaches are mainly gradient-free methods. A standard gradient descent algorithm and its improved version, namely a Stochastic Gradient Descent (SGD) algorithm are proposed on the basis of a novel coverage indicator, named as the soft coverage indicator, to approximate the hard version of the original coverage indicator. We prove that the gradient vector is sparse, which accelerates gradient calculation, due to the number limitation of base stations within a specific distance from a given sampling point even if there are many decision variables of azimuths and tilts. Also, the SGD algorithm only requires a small amount of computation based on cheap estimates of the gradients, and thus is applicable to large-scale networks in an efficient manner. The experiments show that the proposed approaches perform well both in their near-optimal solutions and in their computation efficiency compared with the meta-heuristic algorithms. The extensibility and practicality of the proposed algorithms are also discussed.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1536-1276
1558-2248
DOI:10.1109/TWC.2019.2914040