Data caps and service degradation are techniques used to control subscribers' data consumption. These techniques have emerged mainly due to the growing demands placed on the networking stack created by the continuous increase in the number of connected users and their feature-rich, bandwidth-heavy Over-the-Top (OTT) applications. In the mobile network's scope, where traditional operators offer user data plans with limited resources, service degradation is a standard mechanism used to throttle consumption. Limiting user data usage helps to utilize resources better and to ensure the network's reliable performance. Nevertheless, this degradation is applied in a generalized way, affecting all user applications without considering behavior. In this paper, we propose a reference model aiming to address this constraint. Specifically, we attempt to personalize service degradation policies by providing a guideline for users' OTT consumption behavior classification based on Incremental Learning (IL). We evaluated our model's viability in a case study by investigating the efficacy of several IL algorithms on a dataset containing realworld users' OTT application consumption behavior. The algorithms include Naive Bayes (NB), K-Nearest Neighbor (KNN), Adaptive Random Forest (ARF), Leverage Bagging (LB), Oza Bagging (OB), Learn++, and Multilayer Perceptron (MLP). The obtained results show that ARF and a composition between LB and ARF achieve the best performance yielding a classification precision and recall of over 90%. Based on the obtained results, we propose service degradation policies to support decision making in missioncritical systems. We argue the strong applicability of our model in real-world scenarios, especially in user consumption profiling. Our reference model offers a conceptual basis for the tasks that need to be performed when defining personalized service degradation policies in current and future networks like 5G. To the best of our knowledge, this work is the first effort in this matter.
Nowadays exists a trend that combines the features of Web 2.0 services and telecommunications services known as Telco 2.0. These converged services have been successfully implemented in early warning systems providing improved agility and flexibility in service delivery. However the deployment of converged services in rural zones of developing countries presents several constraints which do not allow to provide this kind of services, as the unavailability of a Next Generation Network (ngn), absence of advanced technology and lack of investment resources. This paper proposes a jain slee and OpenBTS integration architecture for early warning systems in rural zones. The implemented prototype is evaluated with a specific case study involving the deployment of Telco 2.0 warnings in Colombian coffee plantations which may be affected by coffee rust, one of the most threatening diseases in coffee production.Key words: jain slee, OpenBTS, integration, early warning system, converged services * The current proposal was supported by the program Fortalecimiento de la Red Interinstitucional de Cambio Climático y Seguridad Alimentaria -RICCLISA; specificaly by the project Servicios de generación de alertas Agroclimáticas como soporte a la toma de decisiones del sector Cafetero Colombiano -AgroCloud (WP2). This project is funded by Universidad del Cauca, CINARA, CENICAFE, CIAT, CREPIC and the program Redes de Conocimiento from COLCIENCIAS during 2013-2017.
Mejorando los sistemas rurales de alertas tempranas a través de la integración de OpenBTS y jain slee
ResumenActualmente existe una tendencia que combina las características de los servicios Web 2.0 y los servicios de telecomunicaciones, conocida como Telco 2.0. Estos servicios convergentes se han aplicado exitosamente en sistemas de alertas tempranas, proporcionando mayor agilidad y flexibilidad en la prestación de servicios. Sin embargo, existen varias limitantes que no permiten el despliegue de servicios convergentes en las zonas rurales de países en vía de desarrollo, como la falta de disponibilidad de una ngn (Next Generation Network), la ausencia de tecnología avanzada y la falta de recursos para inversión. Este artículo propone una arquitectura de integración entre jain slee y OpenBTS para sistemas rurales de alertas tempranas. Se evalúa el prototipo implementado con un caso de estudio específico al enviar advertencias Telco 2.0 a los cafeteros colombianos cuyas plantaciones puedan verse afectadas por la roya, una de las enfermedades más peligrosas para la producción de café.Palabras clave: jain slee, OpenBTS, integración, sistema de alertas tempranas, servicios convergentes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.