Lucia Happe

Supporting swift reaction: automatically uncovering performance problems by systematic experiments

Performance problems pose a significant risk to software vendors. If left undetected, they can lead to lost customers, increased operational costs, and damaged reputation. Despite all efforts, software engineers cannot fully prevent performance problems being introduced into an application. Detecting and resolving such problems as early as possible with minimal effort is still an open challenge in software performance engineering. In this paper, we present a novel approach for Performance Problem Diagnostics (PPD) that systematically searches for well-known performance problems (also called performance antipatterns) within an application. PPD automatically isolates the problems root cause, hence facilitating problem solving. We applied PPD to a well established transactional web e-Commerce benchmark (TPC-W) in two deployment scenarios. PPD automatically identified four performance problems in the benchmark implementation and its deployment environment. By fixing the problems, we increased the maximum throughput of the benchmark from 1800 requests per second to more than 3500.

Survivability models for the assessment of smart grid distribution automation network designs

Smart grids are fostering a paradigm shift in the realm of power distribution systems. Whereas traditionally different components of the power distribution system have been provided and analyzed by different teams through different lenses, smart grids require a unified and holistic approach that takes into consideration the interplay of communication reliability, energy backup, distribution automation topology, energy storage and intelligent features such as automated failure detection, isolation and restoration (FDIR) and demand response. In this paper, we present an analytical model and metrics for the survivability assessment of the distribution power grid network. The proposed metrics extend the system average interruption duration index (SAIDI), accounting for the fact that after a failure the energy demand and supply will vary over time during a multi-step recovery process. The analytical model used to compute the proposed metrics is built on top of three design principles: state space factorization, state aggregation and initial state conditioning. Using these principles, we reduce a Markov chain model with large state space cardinality to a set of much simpler models that are amenable to analytical treatment and efficient numerical solution. In the special case where demand response is not integrated with FDIR, we provide closed form solutions to the metrics of interest, such as the mean time to repair a given set of sections. We have evaluated the presented model using data from a real power distribution grid and we have found that survivability of distribution power grids can be improved by the integration of the demand response feature with automated FDIR approaches. Our empirical results indicate the importance of quantifying survivability to support investment decisions at different parts of the power grid distribution network.

Survivability analysis of power distribution in smart grids with active and reactive power modeling

A paradigm shift is taking place in the realm of power distribution networks. Power distribution networks that have been traditionally built to meet peak demand are now being automated to offer reliability on demand, i.e., smart distribution power grids can be automatically reconfigured after events such as power failures. In future distribution automation networks an important design decision will consist of which approach to use to avoid voltage drops. A standard approach is to add static capacitors to the distribution circuit. Novel techniques include the automatic reduction of active or reactive load through demand response, or the addition of distributed generators that can tradeoff active load for reactive load. In this paper, we introduce a new modeling approach to assist in such design decisions. The survivability of a system is its ability to function during and after a failure. In survivability analysis, the initial state of the system is set to a failure state, so survivability is “conditional performability” [9, 11]. The main contribution of this paper is the development of a model to study the power distribution in smart grids during the (transient) period that starts after a failure till the system fully recovers. The proposed model bridges power flow modeling of reactive power compensation [8, 14] with performability/survivability modeling of automation distribution networks [1]. We use a Markov chain to characterize the phased recovery of the system after a failure [5]. Then, we associate to each state of the Markov chain a set of corresponding rewards to characterize the active and reactive power supplied and demanded in that state.

View-based model-driven software development with ModelJoin

Fragmentation of information across instances of different metamodels poses a significant problem for software developers and leads to a major increase in effort of transformation development. Moreover, compositions of metamodels tend to be incomplete, imprecise, and erroneous, making it impossible to present it to users or use it directly as input for applications. Customized views satisfy information needs by focusing on a particular concern, and filtering out information that is not relevant to this concern. For a broad establishment of view-based approaches, an automated solution to deal with separate metamodels and the high complexity of model transformations is necessary. In this paper, we present the ModelJoin approach for the rapid creation of views. Using a human-readable textual DSL, developers can define custom views declaratively without having to write model transformations or define a bridging metamodel. Instead, a metamodel generator and higher-order transformations create annotated target metamodels and the appropriate transformations on-the-fly. The resulting views, which are based on these metamodels, contain joined instances and can effectively express concerns unforseen during metamodel design. We have applied the ModelJoin approach and validated the textual DSL in a case study using the Palladio Component Model.

Survivability Evaluation of Gas, Water and Electricity Infrastructures

The infrastructures used in cities to supply power, water and gas are consistently becoming more automated. As society depends critically on these cyber-physical infrastructures, their survivability assessment deserves more attention. In this overview, we first touch upon a taxonomy on survivability of cyber-physical infrastructures, before we focus on three classes of infrastructures (gas, water and electricity) and discuss recent modelling and evaluation approaches and challenges.

Interactive Visual Analytics for Efficient Maintenance of Model Transformations

Maintaining model transformations remains a demanding task due to the sheer amount of metamodel elements and transformation rules that need to be understood. Several established techniques for software maintenance have been ported to model transformation development. Most available techniques proactively help to design and implement maintainable transformations, yet however, a growing number of legacy transformations needs to be maintained. Interactive visualization techniques to support model transformation maintenance still do not exist. We propose an interactive visual analytics process for understanding model transformations for maintenance. Data and control dependencies are statically analyzed and displayed in an interactive graph-based view with cross-view navigation and task-oriented filter criteria. We present results of an empirical study, where we asked programmers to carry out typical maintenance tasks on a real-world transformation in QVT-O. Subjects using our view located relevant code spots significantly more efficiently.

A common analysis framework for smart distribution networks applied to survivability analysis of distribution automation

Smart distribution networks shall improve the efficiency and reliability of power distribution by intelligently managing the available power and requested load. Such intelligent power networks pose challenges for information and communication technology (ICT). Their design requires a holistic assessment of traditional power system topology and ICT architecture. Existing analysis approaches focus on analyzing the power networks components separately. For example, communication simulation provides failure data for communication links, while power analysis makes predictions about the stability of the traditional power grid. However, these insights are not combined to provide a basis for design decisions for future smart distribution networks. In this paper, we describe a common model-driven analysis framework for smart distribution networks based on the Common Information Model (CIM). This framework provides scalable analysis of large smart distribution networks by supporting analyses on different levels of abstraction. Furthermore, we apply our framework to holistic survivability analysis. We map the CIM on a survivability model to enable assessing design options with respect to the achieved survivability improvement. We demonstrate our approach by applying the mapping transformation in a case study based on a real distribution circuit. We conclude by evaluating the survivability impact of three investment options.

Designing information hiding modularity for model transformation languages

Development and maintenance of model transformations make up a substantial share of the lifecycle costs of software products that rely on model-driven techniques. In particular large and heterogeneous models lead to poorly understandable transformation code due to missing language concepts to master complexity. At the present time, there exists no module concept for model transformation languages that allows programmers to control information hiding and strictly declare model and code dependencies at module interfaces. Yet only then can we break down transformation logic into smaller parts, so that each part owns a clear interface for separating concerns. In this paper, we propose a module concept suitable for model transformation engineering. We formalize our concept based on cQVTom, a compact subset of the transformation language QVT-Operational. To meet the special demands of transformations, module interfaces give control over both model and code accessibility. We also implemented the approach for validation. In a case study, we examined the effort required to carry out two typical maintenance tasks on a real-world transformation. We are able to attest a significant reduction of effort, thereby demonstrating the practical effects of a thorough interface concept on the maintainability of model transformations.

A Scalable Approach to the Assessment of Storm Impact in Distributed Automation Power Grids

We present models and metrics for the survivability assessment of distribution power grid networks accounting for the impact of multiple failures due to large storms. The analytical models used to compute the proposed metrics are built on top of three design principles: state space factorization, state aggregation, and initial state conditioning. Using these principles, we build scalable models that are amenable to analytical treatment and efficient numerical solution. Our models capture the impact of using reclosers and tie switches to enable faster service restoration after large storms.We have evaluated the presented models using data from a real power distribution grid impacted by a large storm: Hurricane Sandy. Our empirical results demonstrate that our models are able to efficiently evaluate the impact of storm hardening investment alternatives on customer affecting metrics such as the expected energy not supplied until complete system recovery.

An empirical study on the perception of metamodel quality

Despite the crucial importance of metamodeling for Model-Driven Engineering (MDE), there is still little discussion about the quality of metamodel design and its consequences in model-driven development processes. Presumably, the quality of metamodel design strongly affects the models and transformations that conform to these metamodels. However, so far surprisingly few work has been done to validate the characterization of metamodel quality. A proper characterization is essential to automate quality improvements for metamodels such as metamodel refactorings. In this paper, we present an empirical study to sharpen the understanding of the perception of metamodel quality. In the study, 24 participants created metamodels of two different domains and evaluated the metamodels in a peer review process according to an evaluation sheet. The results show that the perceived quality was mainly driven by the metamodels completeness, correctness and modularity while other quality attributes could be neglected.