Deep Reinforcement Learning Based Spectrum Prediction for Bursty Bands

Spectrum prediction plays an important role for the secondary user(SU)to utilize the shared spectrum resources.However,currently utilized prediction methods are not well applied to spectrum with high burstiness,as parameters of prediction models cannot be adjusted properly.This paper studies the prediction problem of bursty bands.Specifically,we first collect real Wi Fi transmission data in 2.4GHz Industrial,Scientific,Medical(ISM)band which is considered to have bursty characteristics.Feature analysis of the data indicates that the spectrum occupancy law of the data is time-variant,which suggests that the performance of commonly used single prediction model could be restricted.Considering that the match between diverse spectrum states and multiple prediction models may essentially improve the prediction performance,we then propose a deep-reinforcement learning based multilayer perceptron(DRL-MLP)method to address this matching problem.The state space of the method is composed of feature vectors,and each of the vectors contains multi-dimensional feature values.Meanwhile,the action space consists of several multilayer perceptrons(MLPs)that are trained on the basis of multiple classified data sets.We finally conduct experiments with the collected real data and simulations with generated data to verify the performance of the proposed method.The results demonstrate that the proposed method significantly outperforms the stateof-the-art methods in terms of the prediction accuracy.

PERFORMANCE ANALYSIS FOR ATM SWITCHING OF MIXED CONTINUOUS-BIT-RATE AND BURSTY TRAFFIC WITH SMOOTHING FUNCTION

Traditional packet switching networks have typically employed window-based congestion control schemes in order to regulate traffic flow. In ATM networks, the high speed of the communication links and the varied nature of the carried traffic make such schemes inappropriate. Therefore, simpler and more efficient schemes have to be proposed to improve the congestion control for ATM switching. This paper presents an exact performance analysis of ATM switching whose inputs consist of Continuous-Bit-Rate(CBR) and bursty traffic. The CBR traffic and bursty traffic are described by Bernoulli process and the Interrupted Bernoulli Process(IBP), respectively. Bursty traffic smoothing mechanism is analyzed. With the use of a recursive algorithm, the cell loss probability and the average delay for ATM switching of mixed CBR and bursty traffic are exactly calculated. Traffic smoothing could be implemented at a slower peak rate keeping the average rate constant or decreasing the average bursty length. Both numerical

突发数据传输模式下片上网络的QoS保证

针对在突发数据(Bursty)传输模式下,片上网络如何提高其传输服务质量(QoS)的问题,提出在虚拟通道(Virtual Chan-nel,VC)中划出专门的空间用来传输突发数据流.在对网络拓扑结构中的平均延时,理想平均吞吐量和能量消耗进行了理论评估的基础上,运用NIRGAM软件仿真平台,在对虚拟通道(Virtual Channel,VC)中的75%或50%用来传输突发数据流(Bursty)的两种不同的情况下,对其各项参数进行仿真和比较.实验结果显示,此方法可有效的提高片上网络的传输服务质量(QoS).

Preservation and variation of ion-to-electron temperature ratio in the plasma sheet in geo-magnetotail

The ion-to-electron temperature ratio is a good indicator of the processes involved in solar wind plasma entering and being transported inside Earth’s plasma sheet.In this study,we have demonstrated that patchy magnetic reconnection has the potential to preserve the ion-to-electron temperature ratio under certain conditions.If the charged particles are non-adiabatically accelerated no more than once in a single reconnection,the temperature ratio would be preserved;on the other hand,this ratio would not be preserved if they are accelerated multiple times.Consequently,under a northward interplanetary magnetic field(IMF)condition,the reconnection in the nonlinear phase of the Kelvin-Helmholtz instability is the dominant process for solar-originated plasma entering the Earth’s magnetosphere,and the ion-to-electron temperature ratio is preserved inside the plasma sheet.When the direction of the IMF is southward,the reflection of electrons from the magnetic mirror point,and subsequent multiple non-adiabatic accelerations at the reconnection site,are the primary reasons for the observed low ion-to-electron temperature ratio close to the Earth at midnight.While reconnections that occur in the night-side far tail might preserve the ratio,turbulence on the boundaries of the bursty bulk flows(BBFs)could change the ratio in the far tail through the violation of the frozen-in condition of the ions.The plateau in the contour of the calculated ion-to-electron temperature ratio in the down tail distance between 40 and 60 Earth radii may explain the strong correlation between the ion and electron temperatures in the outer central plasma sheet,which has not been clearly understood till date.

Bursty Behaviour of Turbulent Particle and Energy Fluxes in Edge Plasma of HT-7 Tokamak

High time resolution measurements of the electrostatic fluctuations and the turbulent particle and energy fluxes have been performed with a Langmuir probe array in the edge plasma in HT-7 tokamak. Bursty behaviour was observed in the time resolved turbulent fluxes with positive skewness and large kurtosis. The contribution of the large sporadic bursts to the transport losses were estimated. The analysis shows that the turbulent fluxes have different behaviour in different frequency domains and the probability distribution functions （PDFs） of the particle and energy fluxes present two distinct scaling ranges. All these are essentially consistent with the predictions of the self-organized criticality （SOC） model, though further studies are needed.

DELAY JITTER OF A PERIODIC CELL STREAM THROUGH AN ATM MULTIPLEXER IN A BURSTY TRAFFIC ENVIRONMENT

The periodic cell stream is a very important member among the input traffic sources in ATM networks. In this paper, a finite-buffered ATM multiplexer with traffic sources composed of a periodic cell stream, multiple i.i.d Bernoulli cell streams and bursty two-state Markov Modulated Bernoulli Process (MMBP) cell streams is exactly analyzed. The probability mass function of queuing delay, the autocorrelation and power spectrum of delay jitter for this periodic cell stream are derived. The analysis is used to expose the behavior of delay jitter for a periodic cell stream through an ATM multiplexer in a bursty traffic environment. The simulation results indicate that the analytical results are accurate.

ANALYSIS OF THE LEAKY BUCKET OUTPUT PROCESSES FOR BURSTY SOURCES IN ATM NETWORKS

In ATM networks, bursty sources can be described as the Interrupted Bernoulli Process(IBP). With the use of the thin process theory, the Probability Generating Function(PGF) of the IBP is obtained. An iterative algorithm, which can be used to calculate the IBP probability distribution, is presented. The bursty source’s equivalent description is discussed. It is proposed that the leaky bucket output process can be approximately described as the IBP. The accuracy of the analytical results has been largely validated by means of the simulation approach. Moreover, how to improve its accuracy is discussed. The smoothing function of the leaky bucket algorithm is quantitatively analyzed.

PERFORMANCE ANALYSIS OF LEAKY BUCKET ALGORITHM WITH BURSTY TRAFFIC INPUT IN ATM NETWORKS

A bursty traffic model is introduced in this paper to describe the statistical characteristics of packet video. The performance of leady bucket algorithm with bursty traffic input is analyzed. The influences of various parameters on QOS (Quality of Service) are investigated. The analysis shows that although the loss probability decreases through expanding the buffer capacity, the delay and delay jitter increase, whose effect on QOS will not be negligible.

Design and Analysis of a Multiscale Active Queue Management Scheme

Since Internet is dominated by TCP-based applications, active queue management （AQM） is considered as an effective way for congestion control. However, most AQM schemes suffer obvious performance degradation with dynamic traffic. Extensive measurements found that Internet traffic is extremely bursty and possibly self-similar. We propose in this paper a new AQM scheme called multiscale controller （MSC） based on the understanding of traffic burstiness in multiple time scale. Different from most of other AQM schemes, MSC combines rate-based and queue-based control in two time scales. While the rate-based dropping on burst level （large time scales） determines the packet drop aggressiveness and is responsible for low and stable queuing delay, good robustness and responsiveness, the queue-based modulation of the packet drop probability on packet level （small time scales） will bring low loss and high throughput. Stability analysis is performed based on a fluid-flow model of the TCP/MSC congestion control system and simulation results show that MSC outperforms many of the current AQM schemes.

Dynamic resource allocation for service in mobile cloud computing with Markov modulated arrivals

Mobile Cloud Computing (MCC) is a modern architecture that brings together cloudcomputing, mobile computing and wireless networks to assist mobile devices in storage,computing and communication. A cloud environment is developed to support a widerange of users that request the cloud resources in a dynamic environment with possible constraints. Burstiness in users service requests causes drastic and unpredictableincreases in the resource requests that have a crucial impact on policies of resourceallocation. How can the cloud system efficiently handle such burstiness when the cloudresources are limited? This problem becomes a hot issue in the MCC research area. Inthis paper, we develop a system model for the resource allocation based on the SemiMarkovian Decision Process (SMDP), able of dynamically assigning the mobile servicerequests to a set of cloud resources, to optimize the usage of cloud resources and maximize the total long-term expected system reward when the arrival process is a finitestate Markov-Modulated Poisson Process (MMPP). Numerical results show that ourproposed model performs much better than the Greedy algorithm in terms of achievinghigher system rewards and lower service requests blocking probabilities, especially whenthe burstiness degree is high, and the cloud resources are limited.

Ranking and tagging bursty features in text streams with context language models

Detecting and using bursty pattems to analyze text streams has been one of the fundamental approaches in many temporal text mining applications. So far, most existing studies have focused on developing methods to detect bursty features based purely on term frequency changes. Few have taken the semantic contexts of bursty features into consideration, and as a result the detected bursty features may not always be interesting and can be hard to interpret. In this article, we propose to model the contexts of bursty features using a language modeling approach. We propose two methods to estimate the context language models based on sentence-level context and document-level context. We then propose a novel topic diversity-based metric using the context models to find newsworthy bursty features. We also propose to use the context models to automatically assign meaningful tags to bursty features. Using a large corpus of news articles, we quantitatively show that the proposed context language models for bursty features can effectively help rank bursty features based on their newsworthiness and to assign meaningful tags to annotate bursty features. We also use two example text mining applications to qualitatively demonstrate the usefulness of bursty feature ranking and tagging.

Performance analysis of optical burst switching under bursty traffic

The performance of the algorithm of the data channel scheduling algorithm of latest available unscheduled channel with void filling (LAUC-VF) under bursty traffic is presented firstly. A bursty traffic model for optical burst switch performance simulation is also introduced.