A Lightweight Tool for Anomaly Detection in Cloud Data Centres

Cloud data centres are critical business infrastructures and the fastest growing service providers. Detecting anomalies in Cloud data centre operation is vital. Given the vast complexity of the data centre system software stack, applications and workloads, anomaly detection is a challenging endeavour. Current tools for detecting anomalies often use machine learning techniques, application instance behaviours or system metrics distribu- tion, which are complex to implement in Cloud computing environments as they require training, access to application-level data and complex processing. This paper presents LADT, a lightweight anomaly detection tool for Cloud data centres that uses rigorous correlation of system metrics, implemented by an efficient corre- lation algorithm without need for training or complex infrastructure set up. LADT is based on the hypothesis that, in an anomaly-free system, metrics from data centre host nodes and virtual machines (VMs) are strongly correlated. An anomaly is detected whenever correlation drops below a threshold value. We demonstrate and evaluate LADT using a Cloud environment, where it shows that the hosting node I/O operations per second (IOPS) are strongly correlated with the aggregated virtual machine IOPS, but this correlation vanishes when an application stresses the disk, indicating a node-level anomaly.

The VINEYARD Approach: Versatile, Integrated, Accelerator-Based, Heterogeneous Data Centres.

Emerging web applications like cloud computing, Big Data and social networks have created the need for powerful centres hosting hundreds of thousands of servers. Currently, the data centres are based on general purpose processors that provide high flexibility buts lack the energy efficiency of customized accelerators. VINEYARD aims to develop an integrated platform for energy-efficient data centres based on new servers with novel, coarse-grain and fine-grain, programmable hardware accelerators. It will, also, build a high-level programming framework for allowing end-users to seamlessly utilize these accelerators in heterogeneous computing systems by employing typical data-centre programming frameworks (e.g. MapReduce, Storm, Spark, etc.). This programming framework will, further, allow the hardware accelerators to be swapped in and out of the heterogeneous infrastructure so as to offer high flexibility and energy efficiency. VINEYARD will foster the expansion of the soft-IP core industry, currently limited in the embedded systems, to the data-centre market. VINEYARD plans to demonstrate the advantages of its approach in three real use-cases (a) a bio-informatics application for high-accuracy brain modeling, (b) two critical financial applications, and (c) a big-data analysis application.

LS-ADT: Lightweight and Scalable Anomaly Detection for Cloud Datacentres

Cloud data centres are implemented as large-scale clusters with demanding requirements for service performance, availability and cost of operation. As a result of scale and complexity, data centres typically exhibit large numbers of system anomalies resulting from operator error, resource over/under provisioning, hardware or software failures and security issus anomalies are inherently difficult to identify and resolve promptly via human inspection. Therefore, it is vital in a cloud system to have automatic system monitoring that detects potential anomalies and identifies their source. In this paper we present a lightweight anomaly detection tool for Cloud data centres which combines extended log analysis and rigorous correlation of system metrics, implemented by an efficient correlation algorithm which does not require training or complex infrastructure set up. The LADT algorithm is based on the premise that there is a strong correlation between node level and VM level metrics in a cloud system. This correlation will drop significantly in the event of any performance anomaly at the node-level and a continuous drop in the correlation can indicate the presence of a true anomaly in the node. The log analysis of LADT assists in determining whether the correlation drop could be caused by naturally occurring cloud management activity such as VM migration, creation, suspension, termination or resizing. In this way, any potential anomaly alerts are reasoned about to prevent false positives that could be caused by the cloud operator’s activity. We demonstrate LADT with log analysis in a Cloud environment to show how the log analysis is combined with the correlation of systems metrics to achieve accurate anomaly detection.

Prevalence and Management of Anaemia in Renal Transplant Recipients: Data from Ten European Centres.

Background: Although it is a known predictor of mortality, there is a relative lack of recent information about anaemia in kidney transplant recipients. Thus, we now report data about the prevalence and management of post-transplant anaemia (PTA) in Europe 5 years after the TRansplant European Survey on Anemia Management (TRESAM) study. Methods: In a cross-sectional study enrolling the largest number of patients to date, data were obtained from 5,834 patients followed at 10 outpatient transplant clinics in four European countries using the American Society of Transplantation anaemia guideline. Results: More than one third (42%) of the patients were anaemic. The haemoglobin (Hb) concentration was significantly correlated with the estimated glomerular filtration rate (eGFR) (r = 0.4, p < 0.001). In multivariate analysis, eGFR, serum ferritin, age, gender, time since transplantation and centres were independently and significantly associated with Hb. Only 24% of the patients who had a Hb concentration <110 g/l were treated with an erythropoiesis-stimulating agent. The prevalence of anaemia and also the use of erythropoiesis-stimulating agents were significantly different across the different centres, suggesting substantial practice variations. Conclusions: PTA is still common and under-treated. The prevalence and management of PTA have not changed substantially since the TRESAM survey.

Improved Nonlinear PCA for Process Monitoring Using Support Vector Data Description

Nonlinear principal component analysis (PCA) based on neural networks has drawn significant attention as a monitoring tool for complex nonlinear processes, but there remains a difficulty with determining the optimal network topology. This paper exploits the advantages of the Fast Recursive Algorithm, where the number of nodes, the location of centres, and the weights between the hidden layer and the output layer can be identified simultaneously for the radial basis function (RBF) networks. The topology problem for the nonlinear PCA based on neural networks can thus be solved. Another problem with nonlinear PCA is that the derived nonlinear scores may not be statistically independent or follow a simple parametric distribution. This hinders its applications in process monitoring since the simplicity of applying predetermined probability distribution functions is lost. This paper proposes the use of a support vector data description and shows that transforming the nonlinear principal components into a feature space allows a simple statistical inference. Results from both simulated and industrial data confirm the efficacy of the proposed method for solving nonlinear principal component problems, compared with linear PCA and kernel PCA.

Catalysing open innovation through publicly funded R&D: A Comparison of University and Company-based research centres

Public funding of university and company-based R&D centres of excellence is widespread both in core and more peripheral regions. What is less well-known is whether these R&D centres can catalyse multi-directional, multi-actor and iterative innovation. Based on data from a real-time monitoring study, this article explores the development of 18 R&D centres’ external connections. University-based R&D centres establish more new connections than company-based centres and are more likely to be interacting with small or micro-firms. However, there is a general bias towards links with larger firms; micro, small and medium-sized enterprises also are less likely to be involved in collaborative R&D with research centres than other types of relationships. The results suggest the potential for R&D centres to act as a catalyst for open innovation but emphasise the need to ensure that the focus of the R&D being conducted is relevant to the needs of smaller firms.

Seasonal variation in month of diagnosis in children with type 1 diabetes registered in 23 EURODIAB centres during 1989-2008

Objectives: To investigate seasonal variation in month of diagnosis in children with type 1 diabetes registered in EURODIAB centres during 1989-2008.
Methods: 23 population-based registers recorded date of diagnosis in new cases of clinically diagnosed type 1 diabetes in children aged under 15 years. Completeness of ascertainment was assessed through capture-recapture methodology and was high in most centres. A general test for seasonal variation (11df) and Edward's test for sinusoidal (sine wave) variation (2df) were employed. Time series methods were also used to investigate if meteorological data were predictive of monthly counts after taking account of seasonality and long term trends.
Results: Significant seasonal variation was apparent in all but two small centres, with an excess of cases apparent in the winter quarter. Significant sinusoidal pattern was also evident in all but two small centres with peaks in December (14 centres), January (5 centres) or February (2 centres). Relative amplitude varied from ±11% to ±39% (median ±18%). There was no relationship across the centres between relative amplitude and incidence level. However there was evidence of significant deviation from the sinusoidal pattern in the majority of centres. Pooling results over centres, there was significant seasonal variation in each age-group at diagnosis, but with significantly less variation in those aged under 5 years. Boys showed marginally greater seasonal variation than girls. There were no differences in seasonal pattern between four sub-periods of the 20 year period. In most centres monthly counts of cases were not associated with deviations from normal monthly average temperature or sunshine hours; short term meteorological variations do not explain numbers of cases diagnosed.
Conclusions: Seasonality with a winter excess is apparent in all age-groups and both sexes, but girls and the under 5s show less marked variation. The seasonal pattern changed little in the 20 year period.

External beam radiotherapy in exudative age-related macular degeneration: a pooled analysis of phase I data

In recent years external beam radiotherapy (EBRT) has been proposed as a treatment for the wet form of age-related macular degeneration (AMD) where choroidal neovascularization (CNV) is the hallmark. While the majority of pilot (Phase I) studies have reported encouraging results, a few have found no benefit, i.e. EBRT was not found to result in either improvement or stabilization of visual acuity of the treated eye. The natural history of visual loss in untreated CNV of AMD is highly variable. Loss of vision is influenced mainly by the presenting acuity, and size and composition of the lesion, and to a lesser extent by a variety of other factors. Thus the variable outcome reported by the small Phase I studies of EBRT published to date may simply reflect the variation in baseline factors. We therefore obtained information on 409 patients treated with EBRT from eight independent centres, which included details of visual acuity at baseline and at subsequent follow-up visits. Analysis of the data showed that 22.5% and 14.9% of EBRT-treated eyes developed moderate and severe loss of vision, respectively, during an average follow-up of 13 months. Initial visual acuity, which explained 20.5% of the variation in visual loss, was the most important baseline factor studied. Statistically significant differences in loss of vision were observed between centres, after considering the effects of case mix factors. Comparisons with historical data suggested that while moderate visual loss was similar to that of the natural history of the disease, the likelihood of suffering severe visual loss was halved. However, the benefit in terms of maintained/improved vision in the treated eye was modest.

Voices from higher up the ladder:Exploring the team leader role in call centres

This paper focuses on an under-researched employee category in the call centre literature-the team leader. The paper, drawing on data from nine Australian call centres, finds that the team leader role is integral to the effectiveness of call centres, yet it is a role that consists of considerable complexity and contradictions. The research demonstrates the critical role performed by team leaders: coach, mentor, trainer, performance evaluator, communicator and supervisor. It also shows team leaders as being far more positive about many of the features of the call centre work environment compared with those on the front line. However, there does appear to be a need for greater acknowledgement of their challenging role, the contradictions that are inherent in the job and the need, in many cases, for increased support being made available to assist. © 2013 John Wiley & Sons Ltd.