Fig 1 - uploaded by Sally Ida McClean
Content may be subject to copyright.
Source publication
Network Management Systems (NMS) are used to monitor the network and along with Operations Support Systems (OSS) maintain the performance with a focus on guaranteeing sustained QoS to the applications and services. One aspect that is given less importance is the energy consumption of the network elements during the off peak periods. This paper look...
Contexts in source publication
Context 1
... proposed energy aware network management framework is shown in Fig. 1. It consists of three modules, namely, the Network Management System (NMS), the Decision Management System (DMS) and the Configuration Management System (CMS). The NMS is the central entity which interacts with the DMS and the CMS. The NMS can be based on the SNMP protocol which collects network management data using the SNMP ...
Context 2
... NMS can be based on the SNMP protocol which collects network management data using the SNMP Management Information Base (MIB) of the network elements. In our case, we concentrate on two main data sets, namely the energy consumption related data (denoted as the Energy Monitor in Fig.1) and the data related to the QoS metrics (denoted as the QoS Monitor in Fig.1). ...
Context 3
... NMS can be based on the SNMP protocol which collects network management data using the SNMP Management Information Base (MIB) of the network elements. In our case, we concentrate on two main data sets, namely the energy consumption related data (denoted as the Energy Monitor in Fig.1) and the data related to the QoS metrics (denoted as the QoS Monitor in Fig.1). The collected data is then fed from the NMS to DMS, where the latter builds a model of the network behaviour using the BBN framework and provides the decision with regard to which network elements (or their ports) to put to sleep and for how long. ...
Similar publications
In this paper a multi-band/Ultra-Wideband (UWB) Multiple Input Multiple Output (MIMO) antenna, which is composed of two identical microstrip fed triple notch band UWB antennas and a Radial Stub Loaded Resonator (RSLR), is proposed and verified numerically and experimentally. The antenna is designed to meet the requirement of multi-band/UWB communic...
In the traditional paradigm, large power plants provide active and reactive power required for the transmission system and the distribution network purchases grid power from it. However, with more and more distributed energy resources (DERs) connected at distribution levels, it is necessary to schedule DERs to meet their demand and participate in t...
Over the southeastern Pacific (SEP), droplet concentration (Nd) in the typically unpolluted marine stratocumulus west of 80° W (> 1000 km offshore) is periodically strongly enhanced in zonally elongated "hook"-shaped features that increase albedo. Here, we examine three hook events using the chemistry version of the Weather Research and Forecasting...
Airborne aerosol measurements in the central equatorial Pacific during PASE (Pacific Atmospheric Sulfur Experiment) revealed that cloud condensation nuclei (CCN) activated in marine boundary layer (MBL) clouds were strongly influenced by entrainment from the free troposphere (FT). About 65% entered at sizes effective as CCN in MBL clouds, while ~25...
El objetivo de este estudio fue identificar la mejor fecha de siembra de nuevas variedades experimentales de maíz y seleccionar los mejores genotipos. El trabajo se realizó en el campo experimental del Instituto Tecnológico de Roque, Celaya, Gto. El material genético de maíz fue un ensayo de variedades procedentes del Centro Internacional de Mejora...
Citations
... Reinforcement Learning has been used to provide efficient bandwidth allocation in differentiated services (Diffserv) networks for per hop behaviour aggregates (Hui and Chen-Khong, 2003). Router performance modelling has been achieved using the learning features of BNs (Bashar et al., 2009(Bashar et al., , 2010b(Bashar et al., , 2011(Bashar et al., , 2012Bashar, 2013). An interesting survey on applications of AI techniques to the telecommunications domain that summarises over a decade of research work is provided in Qi et al. (2007). ...
... Hence, the choice of a particular approach is dependent on the domain, the problem to be solved and the specific requirement from the system modeller. Source: Khan et al. (2006) In order to choose a particular ML approach for the research work in this paper, a further suitability analysis was performed on five prominent ML approaches, namely, neural networks (Bashar et al., 2010a), support vector machines (SVM) (Guo et al., 2007), BNs (Bashar et al., 2010b), genetic algorithm (Karabudak et al., 2004) and ...
... To reiterate, this paper presents the related survey and provides reasoning for arriving to the conclusion that the BN approach is a viable solution for implementing ML-based NM solutions. However, the proposed solutions have already been published by the authors of this paper in [7] (BNAC), [8] (BNDAC), and [6] (BNITE). ...
The ever evolving telecommunication networks in terms of their technology, infrastructure, and supported services have always posed challenges to the network managers to come up with an efficient Network Management System (NMS) for effective network management. The need for automated and efficient management of the current networks, more specifically the Next Generation Network (NGN), is the subject addressed in this research. A detailed description of the management challenges in the context of current networks is presented and then this work enlists the desired features and characteristics of an efficient NMS. It then proposes that there is a need to apply Artificial Intelligence (AI) and Machine Learning (ML) approaches for enhancing and automating the functions of NMS. The first contribution of this work is a comprehensive survey of the AI and ML approaches applied to the domain of NM. The second contribution of this work is that it presents the reasoning and evidence to support the choice of Bayesian Networks (BN) as a viable solution for ML-based NMS. The final contribution of this work is that it proposes and implements three novel NM solutions based on the BN approach, namely BN-based Admission Control (BNAC), BN-based Distributed Admission Control (BNDAC) and BN-based Intelligent Traffic Engineering (BNITE), along with the description of algorithms underpinning the proposed framework.
... Bayesian reasoning based software agents have been used to achieve intelligent network fault management [12]. Reinforcement Learning has been used to provide efficient bandwidth allocation in Differentiated Services (Diff- [15]. An interesting survey on applications of AI techniques to the telecommunications domain that summarizes over a decade of research work, is provided in [16]. ...
The recent emphasis on monitoring and managing telecommunication networks in more intelligent and autonomic manner has led to the emergence and popularity of Machine Learning based Network Management Systems. In order to study the behavior and assess the performance of such NMS, it is essential that a suitable modeling and evaluation framework exists. The work presented here addresses this need and proposes an autonomic NMS which employs the prediction capabilities of the Bayesian Networks (BN) models. To achieve this, it formulates and models the BN-based Decision Support System for providing real-time decisions with regard to the Call Admission Control (CAC) problem in the Next Generation Network (NGN) environment. Simulated experiments are performed to verify the suitability and practicality of the proposed models. The novelty and relevance of this research is demonstrated through offline modeling and online performance evaluation of BNAC (Bayesian Networks-based Admission Control) by considering the metrics of Packet Delay, Packet Loss, Queue Size and Blocking Probability. The paper concludes that BNAC approach performs better than the Peak Rate CAC in terms of online CAC functionality.
... This section describes the assumptions made for implementing BNITE and the policy level algorithm which forms the core of the solution. It is to be noted that the work presented here is an extension of our earlier preliminary work presented in [12]. ...
Network Management Systems (NMS) are used to monitor the network and maintain its performance with a prime focus on guaranteeing sustained QoS to the services. However, another aspect that must be given due importance is the energy consumption of the network elements, specially during the off-peak periods. This paper proposes and implements a novel idea of energy-aware network management that looks at a scenario where the NMS plays an important role in making the network energy efficient by predictively turning the network elements to sleep mode when they are underutilized. To this end, it designs and evaluates a Bayesian Networks (BN) based Intelligent Traffic Engineering (BNITE) solution, which provides intelligent decisions to the NMS for it to adaptively alter the operational modes of the network elements, with minimum compromise in the network performance and QoS guarantees. Energy-aware Traffic Engineering algorithms are developed for both stand-alone (single router) and centralised (multiple routers) scenarios to prove the concept. Simulated network experiments using NCTUns and Hugin Researcher have been used to demonstrate the feasibility and practicality of the proposed solution. Significant energy savings with minimal degradation in QoS metrics demonstrate the benefits of BNITE solution for real-world networks such as the NGN.
... Among the existing uncertainty reasoning methods, the Bayesian network is the only one that directly grounded in probability theory. The Bayesian network approach is mainly used as a prediction tool for representing and reasoning about the uncertain domain [7]. It has been used successfully in many fields such as speech recognition, industrial control, economic forecasting, etc. ...
... The decision domain specifies the relation between the input traffic and a set of bursty indicators including the buffer behaviours and characteristics, Fig. 2. The Conditional Probability Tables (CPTs) are needed to specify a probability distribution based on the network at each node. These tables can be specified in any forms: implicitly by some parametric probability distribution, or explicitly as tables [7]. In our implementation, the decision model (burst detection model) is implemented manually by considering all the parameters which can indicate the bursty traffic from normal traffic pattern. ...
Power management strategies (PMS) are applied to keep a balance, between different energy sources (i.e. solar, wind, geothermal, hydro), storage units (i.e. fuel cell, batteries, fly wheel) and loads. Up to date, there has been reported several advance techniques to solve this task, for instance: Fuzzy Logic, Deep Learning, Droop Control, Bayesian Networks, among others. Nevertheless, some of those PMS are over simplified and others are too complex to be programmed in devices with limited resources. To solve these issues, this paper proposes a PMS based on Fuzzy Logic, which keeps a balance between those two goals. Characteristics of the proposed PMS are a small number of rules; fulfillment of the demanded power at every time; reducing use of the storage unit; and keeping a balance between the different sources, storage unit and loads. The proposed PMS is numerically evaluated by using SIMULINK-MATLAB®, in a 10kW residential DC Microgrid (MG), and validated by using a Hardware in the Loop platform (NI myRio-1900 and Typhoon HIL402). A comparison with three popular advance techniques demonstrates the feasibility of the proposed PMS.
This paper is devoted to the management of Autonomous Hybrid Renewable Energy Systems. The structure of such applications depends to a great extent on a large number of random factors and needs an intelligent approach to cope with them. The way of implementation of Bayesian Belief Networks, which help to solve the given problem, is described in the article.
For the last years, the research and development in the field of Renewable Energy has been growing due to the need of Renewable Energy as an extended and reliable source of energy. However, the implementation of renewable energy has many complex problems not easily solved with conventional methods. Recently, Artificial Intelligence techniques such as Artificial Neural Networks, Fuzzy Logic and Genetic Algorithms, have been widely used to deal with these problems in the field of Renewable Energy. Nevertheless, issues with a degree of uncertainty need Bayesian Networks since this is one of the most effective theories to face them. This technique can contribute to the Renewable Energy harnessing and other open issues on this field. In this work we show the state of the art of the applications of Bayesian Networks in Renewable Energy, such as solar thermal, photovoltaic, wind, geothermal, hydroelectric energies and biomass. Additionally, we include related topics such as energy storage, smart grids and energy assessment. We classify the literature by areas considering three main subjects: resource evaluation, operation, and applications, and in each section we describe the possible directions to be taken in the research of the field. We find that the main applications are done for forecasting, fault diagnosis, maintenance, operation, planning, sizing and risk management. We conclude that Bayesian Networks are a promising tool for the field of Renewable Energy with potential applications due to their versatility.
Recent surveys show that the number of road accidents has increased predominantly. One of the major causes to which increased accidents are attributed to is physical ailment of drivers. Continuous monitoring of driver's health condition is essential in order to reduce car accidents that occur due to health abnormality. A non-intrusive method is demanded so as to prevent hindering of driving activity. This paper presents a mobile health monitoring system which is an application running in Android based smart phone. The mobile phone acquires vital parameters such as Heart Rate (HR) and Respiration Rate (RR) from a wearable body sensor through Bluetooth. As faster heart beat and shortness of breath are the most common symptoms of heart problem, the proposed system considers heart rate and respiration rate for deciding abnormal health status. A Bayesian Belief network (BBN) is designed to analyze the vital parameters along with the driver's health history and decide whether the health status of the driver is normal or abnormal in real time. Bayesian Network is a powerful representation for uncertain domains like human health status. Also, it improves classification accuracy as it allows seamless integration of additional information such as the driver's health records with sensed vital information for deciding abnormality and thus avoids false alarms. When abnormality is detected, immediately the driver gets a beep alert call in his mobile and call alert is generated to the caregiver in the case of emergency. The proposed system is tested in real time and it gives reasonable accuracy.
