Distributed stream processing systems (DSPSs) have many important applications such as sensor data analysis, network security, and business intelligence. Failure management is essential for DSPSs that often require highlyavailable system operations. In this paper, we explore a new predictive failure management approach that employs online failure prediction to achieve more efficient failure management than previous reactive or proactive failure management approaches. We employ light-weight streambased classification methods to perform online failure forecast. Based on the prediction results, the system can take differentiated failure preventions on abnormal components only. Our failure prediction model is tunable, which can achieve a desired tradeoff between failure penalty reduction and prevention cost based on a user-defined reward function. To achieve low-overhead online learning, we propose adaptive data stream sampling schemes to adaptively adjust measurement sampling rates based on the states of monitored components, and maintain a limited size of historical training data using reservoir sampling. We have implemented an initial prototype of the predictive failure management framework within the IBM System S distributed stream processing system. Experiment results show that our system can achieve more efficient failure management than conventional reactive and proactive approaches, while imposing low overhead to the DSPS.
Abstract-In this paper, we present a new online failure forecast system to achieve predictive failure management for fault-tolerant data stream processing. Different from previous reactive or proactive approaches, predictive failure management employs failure forecast to perform informed and just-in-time preventive actions on abnormal components only. We employ stream-based online learning methods to continuously classify runtime operator state into normal, alert, or failure, based on collected feature streams. We have implemented the online failure forecast system as part of the IBM System S stream processing system. Our experiments show that the on-line failure forecast system can achieve good prediction accuracy for a range of stream processing software failures, while imposing low overhead to the stream system.
This work presents numerical well testing method of composite model for formation evaluation by using pressure transient data, which are provided by CNOOC field tests. Since polymer flooding reservoirs are effected by multiple factors, the well testing composite models are established by considering wellbore storage effect, convection and diffusion. Typical curves, sensitivity analysis and history match are also conducted. In the Newtonian-non-Newtonian composite model, the pressure derivative curves of the transient section and the radial flow section obviously move upward with the increase of polymer viscosity. In the non-Newtonian-Newtonian composite reservoir, the greater of the oil viscosity, the greater magnitude upturned of the transition section. The data of polymer flooding field tests provided by CNOOC indicates that our work can accurately evaluate reservoir characteristics in relatively homogeneous offshore reservoirs by polymer flooding, which emphasizes the potential for the application of this method in relatively homogeneous offshore and onshore reservoirs.
To analyze the unit performance degradation for top heater out-of-service operation condition, two calculation methods were introduced, that was the model based calculation method and the simplified variable operation condition analysis method. A 600MW sub-critical steam turbine unit with air cooled condenser was analyzed using the two introduced methods. It is shown that calculation data got can reflect the redistribution effect on steam flows of the turbine extractions and turbine internals due to the top heater out-of-service, and similar and close calculation results were got from the two methods, and both results were lower than result calculated using the commonly used equivalent enthalpy drop method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.