Nikos Anerousis

Workload characterization and prediction in the cloud: A multiple time series approach

Cloud computing promises high scalability, flexibility and cost-effectiveness to satisfy emerging computing requirements. To efficiently provision computing resources in the cloud, system administrators need the capabilities of characterizing and predicting workload on the Virtual Machines (VMs). In this paper, we use data traces obtained from a real data center to develop such capabilities. First, we search for repeatable workload patterns by exploring cross-VM workload correlations resulted from the dependencies among applications running on different VMs. Treating workload data samples as time series, we develop a co-clustering technique to identify groups of VMs that frequently exhibit correlated workload patterns, and also the time periods in which these VM groups are active. Then, we introduce a method based on Hidden Markov Modeling (HMM) to characterize the temporal correlations in the discovered VM clusters and to predict variations of workload patterns. The experimental results show that our method can not only help better understand group-level workload characteristics, but also make more accurate predictions on workload changes in a cloud.

Efficient ticket routing by resolution sequence mining

IT problem management calls for quick identification of resolvers to reported problems. The efficiency of this process highly depends on ticket routing---transferring problem ticket among various expert groups in search of the right resolver to the ticket. To achieve efficient ticket routing, wise decision needs to be made at each step of ticket transfer to determine which expert group is likely to be, or to lead to the resolver. In this paper, we address the possibility of improving ticket routing efficiency by mining ticket resolution sequences alone, without accessing ticket content. To demonstrate this possibility, a Markov model is developed to statistically capture the right decisions that have been made toward problem resolution, where the order of the Markov model is carefully chosen according to the conditional entropy obtained from ticket data. We also design a search algorithm, called Variable-order Multiple active State search(VMS), that generates ticket transfer recommendations based on our model. The proposed framework is evaluated on a large set of real-world problem tickets. The results demonstrate that VMS significantly improves human decisions: Problem resolvers can often be identified with fewer ticket transfers.

Problem Determination in Enterprise Middleware Systems using Change Point Correlation of Time Series Data

Clustered enterprise middleware systems employing dynamic workload scheduling are susceptible to a variety of application malfunctions that can manifest themselves in a counterintuitive fashion and cause debilitating damage. Until now, diagnosing problems in that domain involves investigating log files and configuration settings and requires in-depth knowledge of the middleware architecture and application design. This paper presents a method for problem determination using change point detection techniques and problem signatures consisting of a combination of changes (or absence of changes) in different metrics. We implemented this approach on a clustered middleware system and applied it to the detection of the storm drain condition: a debilitating problem encountered in clustered systems with counterintuitive symptoms. Our experimental results show that the system detects 93% of storm drain faults with no false positives

Generative models for ticket resolution in expert networks

Ticket resolution is a critical, yet challenging, aspect of the delivery of IT services. A large service provider needs to handle, on a daily basis, thousands of tickets that report various types of problems. Many of those tickets bounce among multiple expert groups before being transferred to the group with the right expertise to solve the problem. Finding a methodology that reduces such bouncing and hence shortens ticket resolution time is a long-standing challenge. In this paper, we present a unified generative model, the Optimized Network Model (ONM), that characterizes the lifecycle of a ticket, using both the content and the routing sequence of the ticket. ONM uses maximum likelihood estimation, to represent how the information contained in a ticket is used by human experts to make ticket routing decisions. Based on ONM, we develop a probabilistic algorithm to generate ticket routing recommendations for new tickets in a network of expert groups. Our algorithm calculates all possible routes to potential resolvers and makes globally optimal recommendations, in contrast to existing classification methods that make static and locally optimal recommendations. Experiments show that our method significantly outperforms existing solutions.

EasyTicket: a ticket routing recommendation engine for enterprise problem resolution

Managing problem tickets is a key issue in IT service industry. A large service provider may handle thousands of problem tickets from its customers on a daily basis. The efficiency of processing these tickets highly depends on ticket routing---transferring problem tickets among expert groups in search of the right resolver to the ticket. Despite that many ticket management systems are available, ticket routing in these systems is still manually operated by support personnel. In this demo, we introduce EasyTicket, a ticket routing recommendation engine that helps automate this process. By mining ticket history data, we model an enterprise social network that represents the functional relationships among various expert groups in ticket routing. Based on this network, our system then provides routing recommendations to new tickets. Our experimental studies on 1.4 million real-world problem tickets show that on average, EasyTicket can improve the efficiency of ticket routing by 35%.

Two Heads Better Than One: Metric+Active Learning and its Applications for IT Service Classification

Large IT service providers track service requests and their execution through problem/change tickets. It is important to classify the tickets based on the problem/change description in order to understand service quality and to optimize service processes. However, two challenges exist in solving this classification problem: 1) ticket descriptions from different classes are of highly diverse characteristics, which invalidates most standard distance metrics; 2) it is very expensive to obtain high-quality labeled data. To address these challenges, we develop two seemingly independent methods 1) Discriminative Neighborhood Metric Learning (DNML) and 2) Active Learning with Median Selection (ALMS), both of which are, however, based on the same core technique: iterated representative selection. A case study on real IT service classification application is presented to demonstrate the effectiveness and efficiency of our proposed methods.

Content-aware resolution sequence mining for ticket routing

Ticket routing is key to the efficiency of IT problem management. Due to the complexity of many reported problems, problem tickets typically need to be routed among various expert groups, to search for the right resolver. In this paper, we study the problem of using historical ticket data to make smarter routing recommendations for new tickets, so as to improve the efficiency of ticket routing, in terms of the Mean number of Steps To Resolve (MSTR) a ticket. Previous studies on this problem have been focusing on mining ticket resolution sequences to generate more informed routing recommendations. In this work, we enhance the existing sequence-only approach by further mining the text content of tickets. Through extensive studies on real-world problem tickets, we find that neither resolution sequence nor ticket content alone is sufficient to deliver the most reduction in MSTR, while a hybrid approach that mines resolution sequences in a content-aware manner proves to be the most effective. We therefore propose such an approach that first analyzes the content of a new ticket and identifies a set of semantically relevant tickets, and then creates a weighted Markov model from the resolution sequences of these tickets to generate routing recommendations. Our experiments show that the proposed approach achieves significantly better results than both sequence-only and content-only solutions.

Clustered subset selection and its applications on it service metrics

Motivated by the enormous amounts of data collected in a large IT service provider organization, this paper presents a method for quickly and automatically summarizing and extracting meaningful insights from the data. Termed Clustered Subset Selection (CSS), our method enables program-guided data explorations of high-dimensional data matrices. CSS combines clustering and subset selection into a coherent and intuitive method for data analysis. In addition to a general framework, we introduce a family of CSS algorithms with different clustering components such as k-means and Close-to-Rank-One (CRO) clustering, and Subset Selection components such as best rank-one approximation and Rank-Revealing QR (RRQR) decomposition. From an empirical perspective, we illustrate that CSS is achieving significant improvements over existing Subset Selection methods in terms of approximation errors. Compared to existing Subset Selection techniques, CSS is also able to provide additional insight about clusters and cluster representatives. Finally, we present a case-study of program-guided data explorations using CSS on a large amount of IT service delivery data collection.

Improving readiness for enterprise migration to the cloud

Enterprises are increasingly moving their IT infrastructures to the Cloud, driven by the promise of low-cost access to ready-to-use, elastic resources. Given the heterogeneous and dynamic nature of enterprise IT environments, a rapid and accurate discovery of complex infrastructure dependencies at the application, middleware, and network level is key to a successful migration to the Cloud. Existing migration approaches typically replicate source resources and configurations on the target site, making it challenging to optimize the resource usage (for reduced cost with same or better performance) or cloud-fit configuration (no misconfiguration) after migration. The responsibility of reconfiguring the target environment after migration is often left to the users, who, as a result, fail to reap the benefits of reduced cost and improved performance in the Cloud. In this paper we propose a method that automatically computes optimized target resources and identifies configurations given discovered source properties and dependencies of machines, while prioritizing performance in the target environment. From our analysis, we could reduce service costs by 60.1%, and found four types of misconfigurations from real enterprise datasets, affecting up to 81.8% of a data centers servers.

Enterprise-scale cloud migration orchestrator

With the promise of low-cost access to flexible and elastic resources, enterprises are increasingly migrating their existing workloads into the Cloud. Yet, the heterogeneity of the workloads and existing configuration of legacy IT infrastructure make it challenging to enable a one-click, seamless migration process. There are multiple tools available for migrating servers based on their existing configurations and multiple ways of dealing with data synchronization (post migration). In this paper, we present a Cloud Migration Orchestrator (CMO), based on business process management (BPM) approach to provide a systematic framework to automate and coordinate migration activities. CMO coordinates the process of migration, starting from discovery, provisioning, network configuration, execution of migration, cutover and validation. CMO integrates multiple migration technologies, to support different migration scenarios. We present and discuss our results from a preliminary deployment of CMO to migrate 25 VMware instances and discuss how this approach improves the effectiveness of migration, and seamlessly coordinates activities required to be executed.