Radice: (Italian noun) root Root cause analysis is one of the most crucial operations in software reliability regarding system performance diagnostic. It aims to identify the root causes of system performance anomalies, allowing the resolution or the future prevention of issues that can cause millions of dollars in losses. Common existing approaches relying on data correlation or full domain expert knowledge are inaccurate or infeasible in most industrial cases, since correlation does not imply causation, and domain experts may not have full knowledge of complex and real-time systems. In this work, we define a novel causal domain knowledge model representing causal relations about the underlying system components to allow domain experts to contribute partial domain knowledge for root cause analysis. We then introduce RADICE, an algorithm that through the causal graph discovery, enhancement, refinement, and subtraction processes is able to output a root cause causal sub-graph showing the causal relations between the system components affected by the anomaly. We evaluated RADICE with simulated data and reported a real data use case, sharing the lessons we learned. The experiments show that RADICE provides better results than other baseline methods, including causal discovery algorithms and correlation based approaches for root cause analysis.

In IT system operations, shell commands are common command line tools used by site reliability engineers (SREs) for daily tasks, such as system configuration, package deployment, and performance optimization. The efficiency in their execution has a crucial business impact since shell commands very often aim to execute critical operations, such as the resolution of system faults. However, many shell commands involve long parameters that make them hard to remember and type. Additionally, the experience and knowledge of SREs using these commands are almost always not preserved. In this work, we propose SHREC, a SRE behaviour knowledge graph model for shell command recommendations. We model the SRE shell behaviour knowledge as a knowledge graph and propose a strategy to directly extract such a knowledge from SRE historical shell operations. The knowledge graph is then used to provide shell command recommendations in real-time to improve the SRE operation efficiency. Our empirical study based on real shell commands executed in our company demonstrates that Shrec can improve the SRE operation efficiency, allowing to share and re-utilize the SRE knowledge.

Aspect Based Sentiment Analysis is a dominant research area with potential applications in social media analytics, business, finance, and health.Prior works in this area are primarily based on supervised methods, with a few techniques using weak supervision limited to predicting a single aspect category per review sentence.In this paper, we present an extremely weakly supervised multi-label Aspect Category Sentiment Analysis framework which does not use any labelled data.We only rely on a single word per class as an initial indicative information.We further propose an automatic word selection technique to choose these seed categories and sentiment words.We explore unsupervised language model post-training to improve the overall performance, and propose a multi-label generator model to generate multiple aspect category-sentiment pairs per review sentence.Experiments conducted on four benchmark datasets showcase our method to outperform other weakly supervised baselines by a significant margin. 1

The move towards more complex and dynamic telecommunication networks renders the need for more automation in the management system stringent. This is especially true in the context of 5G networks, where understanding context for providing the right management recommendations is crucial. Our work focuses on gathering context from the current status of the network and correlating it with useful information from existing documents in the network provider and operator's domain. We propose an architecture that, based on collected and interlinked information, can provide automatic recommendations for addressing existing problems in the network. More specifically, our approach is based on creating a knowledge-graph to direct workflow recommendations for network incidents. We implemented this system using the actual OSS product documentation and real network events and we show that our approach adds new value for automated network management, including improved efficiency and customer experience.

Much work has been done in the area of telecommunications transmission parameters and, in particular, Channel Quality Indicators, to analyse the best ways to improve the performance and quality of communications. However, there is a gap in published papers when it comes to real-world experiences with CQI reports and network-side analysis of transmission parameters that can provide information about user equipment and network elements behaviour. In this paper, we present our experiences with a real-world analysis of dense LTE networks, focusing on two main aspects - what information can CQI reports give us about the behaviour of user equipment in the network, and what information do they provide in relation to the individual network elements. We show what insights can be derived from a network wide statistical analysis of CQI reports and how these insights can be further used by operators to understand potential problems in their network.

Network operators are increasingly using analytic applications to improve the performance of their networks. Telecommunications analytical applications typically use SQL and Complex Event Processing (CEP) for data processing, network analysis and troubleshooting. Such approaches are hindered as they require an in-depth knowledge of both the telecommunications domain and telecommunications data structures in order to create the required queries. Valuable information contained in free form text data fields such as “additional_info”, “user_text” or “problem_text” can also be ignored. This work proposes An Anomaly Detection Algorithm for MAintenance and Network Troubleshooting (ADAMANT), a text analytic based network anomaly detection approach. Once telecommunications data records have been indexed, ADAMANT uses distance based outlier detection within sliding windows to detect abnormal terms at configurable time intervals. Traditional approaches focus on a specific type of record and create specific cause and effect rules. With the ADAMANT approach all free form text fields of alarms, logs, etc. are treated as text documents similar to Twitter feeds. All documents within a window represent a snapshot of the network state that is processed by ADAMANT. The ADAMANT approach focuses on text analytics to provide automated analysis without the requirement for SQL/CEP queries. Such an approach provides distinct network insights in comparison to traditional approaches.

In telecommunications network troubleshooting, analytical applications are widely used. Such applications typically use CEP (Complex Event Processing) and SQL queries for data processing and network analysis. Performance engineers need in-depth knowledge of both the telecommunications domain and telecommunications data structures in order to create the required queries. Moreover valuable information contained in free form text data fields such as “additional_info”, “user_text” or “problem_text” can also be ignored. This work proposes CADMANT: Context Anomaly Detection for MAintenance and Network Troubleshooting. Traditional approaches focus on a specific record type and create specific cause and effect rules. With the CADMANT approach all free form text fields of alarms, logs, etc. are treated as text documents similar to Twitter feeds. CADMANT uses distance based outlier detection within sliding windows to detect abnormal terms at configurable time intervals. The CADMANT approach provides automated analysis without the requirement for SQL/CEP queries and provides distinct network insights in comparison to traditional approaches.

In many domains such as Telecom various scenarios necessitate the processing of large amounts of data using statistical and machine learning algorithms. A noticeable effort has been made to move the data management systems into MapReduce parallel processing environments such as Hadoop and Pig. Nevertheless these systems lack the features of advanced machine learning and statistical analysis. Frame-works such as Mahout on top of Hadoop support machine learning but their implementations are at the preliminary stage. For example Mahout does not provide Support Vector Machine (SVM) algorithms and it is difficult to use. On the other hand traditional statistical software tools such as R containing comprehensive statistical algorithms for advanced analysis are widely used. But such software can only run on a single computer and therefore it is not scalable. In this paper we propose an integrated solution RPig which takes the advantages of R (for machine learning and statistical analysis capabilities) and parallel data processing capabilities of Pig. The RPig framework offers a scalable advanced data analysis solution for machine learning and statistical analysis. Analysis jobs can be easily developed with RPig script in high level languages. We describe the design implementation and an eclipse-based RPigEditor for the RPig framework. Using application scenarios from the Telecom domain we show the usage of RPig and how the framework can significantly reduce the development effort. The results demonstrate the scalability of our framework and the simplicity of deployment for analysis jobs.

Autonomic, i.e. dynamic and fault-tolerant Web service composition is a requirement resulting from recent developments such as on-demand services. In the context of planning-based service composition, multiagent planning and dynamic error handling are still unresolved problems. Recently, business rule and constraint management has been looked at for enterprise SOA to add business flexibility. This paper proposes a constraint integration and violation handling technique for dynamic service composition. Higher degrees of reliability and fault-tolerance, but also performance for autonomously composed WS-BPEL processes are the objectives.