Congestion Control for Wireless Cellular Systems with Applications to UMTS

Rodrigues, Emanuel B.; Cavalcanti, Francisco R. P.; Wänstedt, Stefan

doi:10.1007/978-1-4419-0155-2_4

Cited by 2 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several reasons can lead to congestion: power overloads, excessive user connections, excessive cell data traffic, and cell phone processor overload [1]. When a cell identifies that it is close to congestion, it can take some actions to mitigate the problem, such as: reducing the quality of voice calls, transferring connections to other cells, and blocking new connections [2]. However, these actions have drawbacks.…”

Section: Introductionmentioning

confidence: 99%

Comparison Between Different Architectures of Multilayer Perceptron Networks for Blocking Rate Prediction in Mobile Phone Networks

Melo¹,

Santos²,

Gomes³

2022

Learn. Nonlin. Mod.

View full text Add to dashboard Cite

Blocking in mobile phone networks is a problem that consists of the refusal of the connection between a telephone device and a cell responsible for emitting the signal. The occurrence of blocking can indicate that a cell is close to congestion, leading to financial losses for telephone companies. This work developed three prediction systems using Multilayer Perceptron neural networks. Each system was modeled following different strategies: Direct, Recursive, and Direct Recursive, respectively. The training and test of the networks were carried out by using real data containing the history of blocking rates from a network of cells. The development stages consisted of analyzing the performance of each prediction system, varying the number of neurons in the hidden layers and the number of predicted steps from 1 (corresponding to 15 minutes ahead) to 20 (corresponding to 5 hours ahead). The system based on the Recursive strategy presented the lowest performance making predictions of short (15 minutes) and long (5 hours) terms with RMSE (Root Mean Squared Error) of approximately 13% and 40%, respectively, with a confidence interval between 27% and 29% considering all predictions. The systems based on the Direct and Direct Recursive strategies presented similar results, making predictions of short and long terms with RMSE of approximately 12% and 31%, respectively, with confidence intervals between 21% and 23% considering all predictions. Although the Direct and Direct Recursive systems obtained the lowest RMSE, the Direct Recursive is more advantageous as it requires fewer MLP networks. Consequently, it has simpler training and a lower computational cost.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison Between Different Architectures of Multilayer Perceptron Networks for Blocking Rate Prediction in Mobile Phone Networks

Melo¹,

Santos²,

Gomes³

2022

Learn. Nonlin. Mod.

View full text Add to dashboard Cite

show abstract

“…Diversos motivos podem levar ao congestionamento, tais como: sobrecargas de potência, excesso de conexões de usuários, excesso de tráfego de dados nas células e a sobrecarga do processador da célula telefônica [2]. Quando uma célula identifica que está próxima de sofrer um congestionamento, ela pode realizar algumas ac ¸ões para amenizar a situac ¸ão, tais como: reduc ¸ão da qualidade das chamadas de voz, transferência de uma conexão de uma célula para outra ou bloqueio de novas conexões [3]. O problema é que essas ac ¸ões podem ser desvantajosas para as empresas pois reduzem o lucro que seria obtido com clientes que deveriam estar usando a rede.…”

Section: Introduc ¸ãOunclassified

Predição de Bloqueio em Redes de Telefonia Móvel

Melo¹,

Santos²,

Gomes³

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Bloqueios em redes de telefonia é um problema que consiste na recusa da conexão entre um aparelho telefônico e uma célula responsável pela emissão do sinal. A ocorrência de bloqueios é um indicador de que a célula está próxima de sofrer um congestionamento, o que pode gerar perdas financeiras para as empresas de telefonia. Neste trabalho, foram desenvolvidos dois sistemas de previsão usando redes neurais MLPs (Multi Layer Perceptron) e seguindo as estratégias conhecidas como Direta e DirRec. Para realizar o treinamento e teste das redes MLPs, foram utilizados dados reais contendo históricos de taxa de bloqueios em células de tecnologia 3G. As etapas do desenvolvimento consistiram na análise do desempenho das redes variando o número de neurônios nas camadas ocultas e o número de passos previstos. Os dois sistemas, Direto e DirRec, apresentaram desempenhos semelhantes, fazendo previsões de curto (15 minutos) e longo (5 horas) prazos com RMSE (Root Mean Squared Error) de aproximadamente 12% e 31%, respectivamente. Porém, o sistema que utilizou a estratégia DirRec se mostrou mais viável por demandar uma quantidade menor de redes MLPs e, desta maneira, ter um treinamento mais simples.

show abstract

Congestion Control for Wireless Cellular Systems with Applications to UMTS

Cited by 2 publications

References 39 publications

Comparison Between Different Architectures of Multilayer Perceptron Networks for Blocking Rate Prediction in Mobile Phone Networks

Comparison Between Different Architectures of Multilayer Perceptron Networks for Blocking Rate Prediction in Mobile Phone Networks

Predição de Bloqueio em Redes de Telefonia Móvel

Contact Info

Product

Resources

About