Search

In recent years, attacks such as the Stuxnet malware have demonstrated that cyberattacks against control systems cause extensive damage. These attacks can result in physical damage to the networked systems under their control. In this paper, we discuss our approach for detecting such attacks by distinguishing between programs running on a programmable logic controller (PLC) without having to monitor communications. Using power signatures generated by an attached, high-frequency power measurement device, we can identify what a PLC is doing and when an attack may have altered what the PLC should be doing. To accomplish this, we generated labeled data for testing our methods and applied feature engineering techniques and machine learning models. The results demonstrate that Random Forests and Convolutional Neural Networks classify programs with up to 98% accuracy for major program differences and 84% accuracy for minor differences. Our results can be used for both online and offline applications.

Power optimization and power control are challenging issues for server computer systems. To obtain power optimization in an enterprise server, one needs to observe temporal behavior of workloads, and how they contribute to relative variations in power drawn by different server components. This depth of analysis helps to validate and quantify various energy/performance trends important for power modeling. In this paper we discuss an adaptive infrastructure to synthesize models that dynamically estimate the throughput and latency characteristics based on component level power distribution in a server. In this infrastructure, we capture telemetry data from a distributed set of physical and logical sensors in the system and use it to train models for various phases of the workload. Once trained, system power, throughput and latency models participate in an optimization heuristics that re-distribute the power to maximize the overall performance/watt of an enterprise server. We demonstrate modeling accuracy and improvement in energy efficiency due to coordinated power allocation among server components.

In an energy aware environment, designers frequently turn to advanced power reduction techniques such as power shutoff and multi-supply-voltage architectures. In order to implement these techniques, it is important that power estimates be made. Power prediction is a critical necessity as chip sizes continually decrease and the desire for low power consumption is a foremost design objective. For such predictions, it is crucial to avoid underestimating power since reliability issues and possible chip damage might occur. It becomes necessary to eliminate or strictly limit underestimations by relaxing accuracy constraints while decreasing the likelihood that the estimation undershoots the actual value. Our novel approach, Asymmetrical and Lower Bounded Support Vector Regression modifies the Support Vector Regression technique by Vapnik and provides accurate prediction while maintaining a low number of underestimates. We tested our approach on two different power data sets and achieved accuracy rates of 5.72% and 5.06% relative percentage error while keeping the number of underestimates below 2.81% and 1.74%.