Since the frequency of network security incidents is nonlinear,traditional prediction methods such as ARMA,Gray systems are difficult to deal with the problem.When the size of sample is small,methods based on artifici...Since the frequency of network security incidents is nonlinear,traditional prediction methods such as ARMA,Gray systems are difficult to deal with the problem.When the size of sample is small,methods based on artificial neural network may not reach a high degree of preciseness.Least Squares Support Vector Machines (LSSVM) is a kind of machine learning methods based on the statistics learning theory,it can be applied to solve small sample and non-linear problems very well.This paper applied LSSVM to predict the occur frequency of network security incidents.To improve the accuracy,it used an improved genetic algorithm to optimize the parameters of LSSVM.Verified by real data sets,the improved genetic algorithm (IGA) converges faster than the simple genetic algorithm (SGA),and has a higher efficiency in the optimization procedure.Specially,the optimized LSSVM model worked very well on the prediction of frequency of network security incidents.展开更多
Long Term Evolution （LTE）-based cellular networks are being deployed around the world to provide public safety with enhanced capabilities and access to broadband technology. In the United States, the First Responder...Long Term Evolution （LTE）-based cellular networks are being deployed around the world to provide public safety with enhanced capabilities and access to broadband technology. In the United States, the First Responder Network Authority （FirstNet） is on the verge of deploying a nationwide network called the National Public Safety Broadband Network （NPSBN）. Commercial networks typically aim at maximizing network capacity, i.e. the aggregate data rate, in order to increase revenue. However, in public safety networks, coverage, not capacity, is paramount, especially during an outage when sites are down. Through traffic control and preemption, the service level of low-priority users is reduced or denied, fleeing up resources to restore coverage to high-priority users, e.g. users responding to an incident. In this study, we examine the effect of outages on network coverage and throughput. As our main contribution, we propose three traffic-control schemes that exploit variable modulation and coding, a feature that LTE enhances with respect to its 3G predecessors. The schemes differ based on the proportion of low- and high-priority users preempted. We show that the network coverage can be restored significantly and we investigate the tradeoff between the three schemes. Finally, we perform sensitivity analysis to confirm the effectiveness of the schemes across a wide range of scenarios.展开更多
基金supported in part by the National High Technology Research and Development Program of China ("863" Program) (No.2007AA010502)
文摘Since the frequency of network security incidents is nonlinear,traditional prediction methods such as ARMA,Gray systems are difficult to deal with the problem.When the size of sample is small,methods based on artificial neural network may not reach a high degree of preciseness.Least Squares Support Vector Machines (LSSVM) is a kind of machine learning methods based on the statistics learning theory,it can be applied to solve small sample and non-linear problems very well.This paper applied LSSVM to predict the occur frequency of network security incidents.To improve the accuracy,it used an improved genetic algorithm to optimize the parameters of LSSVM.Verified by real data sets,the improved genetic algorithm (IGA) converges faster than the simple genetic algorithm (SGA),and has a higher efficiency in the optimization procedure.Specially,the optimized LSSVM model worked very well on the prediction of frequency of network security incidents.
文摘Long Term Evolution （LTE）-based cellular networks are being deployed around the world to provide public safety with enhanced capabilities and access to broadband technology. In the United States, the First Responder Network Authority （FirstNet） is on the verge of deploying a nationwide network called the National Public Safety Broadband Network （NPSBN）. Commercial networks typically aim at maximizing network capacity, i.e. the aggregate data rate, in order to increase revenue. However, in public safety networks, coverage, not capacity, is paramount, especially during an outage when sites are down. Through traffic control and preemption, the service level of low-priority users is reduced or denied, fleeing up resources to restore coverage to high-priority users, e.g. users responding to an incident. In this study, we examine the effect of outages on network coverage and throughput. As our main contribution, we propose three traffic-control schemes that exploit variable modulation and coding, a feature that LTE enhances with respect to its 3G predecessors. The schemes differ based on the proportion of low- and high-priority users preempted. We show that the network coverage can be restored significantly and we investigate the tradeoff between the three schemes. Finally, we perform sensitivity analysis to confirm the effectiveness of the schemes across a wide range of scenarios.
