Ajay Chhokra

INDICES: Exploiting Edge Resources for Performance-Aware Cloud-Hosted Services

Despite the known benefits of hosting cloud-based services, the longer and often unpredictable end-to-end network latencies between the end user and the cloud can be detrimental to the response time requirements of the interactive cloud-hosted applications. Existing efforts that exploit edge/fog technology to migrate services closer to clients in order to improve response times do not fully resolve this problem as they do not focus on performance and interference issues at the migrated locations. This paper proposes INDICES framework that addresses these limitations by providing a novel solution that determines when and to which MDC a service should be migrated to and thus provides the desired performance. Empirical results validating our claims are presented using a setup comprising a centralized cloud and MDCs composed of heterogeneous hardware.

A simulation testbed for cascade analysis

Electrical power systems are heavily instrumented with protection assemblies (relays and breakers) that detect anomalies and arrest failure propagation. However, failures in these discrete protection devices could have inadvertent consequences, including cascading failures resulting in blackouts. This paper aims to model the behavior of these discrete protection devices in nominal and faulty conditions and apply it towards simulation and contingency analysis of cascading failures in power transmission systems. The behavior under fault conditions are used to identify and explain conditions for blackout evolution which are not otherwise obvious. The results are demonstrated using a standard IEEE-14 Bus System.

A component-based approach for modeling failure propagations in power systems

Resiliency and reliability is of paramount impor- tance for energy cyber physical systems. Electrical protection systems including detection elements such as Distance Relays and actuation elements such as Breakers are designed to protect the system from abnormal operations and arrest failure propagation by rapidly isolating the faulty components. However, failure in the protection devices themselves can and do lead to major system events and fault cascades, often leading to blackouts. This paper augments our past work on Temporal Causal Diagrams (TCD), a modeling formalism designed to help reason about the failure progressions by (a) describing a way to generate the TCD model from the system specification, and (b) understand the system failure dynamics for TCD reasoners by configuring simulation models.

Diagnosis in Cyber-Physical Systems with Fault Protection Assemblies

Fault Protection Assemblies are used in cyber-physical systems for automated fault-isolation. These devices alter the mode of the system using locally available information in order to stop fault propagation. For example, in electrical networks relays and breakers isolate faults in order to arrest failure propagation and protect the healthy parts of the system. However, these assemblies themselves can have faults, which may inadvertently induce secondary failures. Often these secondary failures lead to cascade effects, which then lead to total system collapse. This behavior is often seen in electrical transmission systems where failures of relays and breakers may cause overloading and the disconnection of parts of an otherwise healthy system. In the past, we had developed a consistency based diagnosis approach for physical systems based on the temporal failure propagation graph. We now describe an extension that uses the concept of timed discrete event observers in combination with the timed failure propagation graphs to extend the hypothesis to include the possibility of failures in the fault protection units. Using a simulated power system case study, we show that the combined approach is able to diagnose faults in both the plant and the protection devices.

Diagnostics and prognostics using temporal causal models for cyber physical energy systems

Reliable operation of cyber-physical systems such as power transmission and distribution systems is crtiical for the seamless functioning of a vibrant economy. These systems consist of tightly coupled physical (energy sources, transmission and distribution lines, and loads) and computational components (protection devices, energy management systems, etc.). The protection devices such as distance relays help in preventing failure propagation by isolating faulty physical components. However, these devices rely on hard thresholds and local information, often ignoring system-level effects introduced by the distributed control algorithms. This leads to scenarios wherein a local mitigation in a subsytem could trigger a larger fault cascade, possibly resulting in a blackout.Efficient models and tools that curtail such systematic failures by performing fault diagnosis and prognosis are therefore necessary.

A Systematic Approach of Identifying Optimal Load Control Actions for Arresting Cascading Failures in Power Systems

Cascading outages in power networks cause blackouts which lead to huge economic and social consequences. The traditional form of load shedding is avoidable in many cases by identifying optimal load control actions. However, if there is a change in the system topology (adding or removing loads, lines etc), the calculations have to be performed again. This paper addresses this problem by providing a workflow that 1) generates system models from IEEE CDF specifications, 2) identifies a collection of blackout causing contingencies, 3) dynamically sets up an optimization problem, and 4) generates a table of mitigation strategies in terms of minimal load curtailment. We demonstrate the applicability of our proposed methodology by finding load curtailment actions for N-k contingencies (k = 1, 2, 3) in IEEE 14 Bus system.

A modeling framework to integrate exogenous tools for identifying critical components in power systems

Cascading failures in electrical power systems are one of the major causes of concern for the modem society as it results in huge socio-economic loss. Tools for analyzing these failures while considering different aspects of the system are typically very expensive. Thus, researchers tend to use multiple tools to perform various types of analysis on the same system model in order to understand the reasons for these failures in detail. Modeling a simple system in multiple platforms is a tedious, error prone and time consuming process. This paper describes a domain specific modeling language (DSML) for power systems. It identifies and captures the right abstractions for modeling components in different analysis tools. A framework is proposed that deals with system modeling using the developed DSML, identifying the type of analysis to be performed, choosing the appropriate tool(s) needed for the analysis from the tool-chain, transforming the model based on the required specifications of a particular tool and performing the analysis. A case study is done on WSCC-9 Bus System, IEEE-14 Bus System and IEEE-39 Bus System to demonstrate the entire workflow of the framework in identifying critical components for power systems.

Poster Abstract: Distributed Reasoning for Diagnosing Cascading Outages in Cyber Physical Energy Systems

The power grid incorporates a number of protection elements such as distance relays that detect faults and prevent the propagation of failure effects from influencing the rest of system. However, the decision of these protection elements is only influenced by local information in the form of bus voltage/current (V-I) samples. Due to lack of system wide perspective, erroneous settings, and latent failure modes, protection devices often mis-operate and cause cascading effects that ultimately lead to blackouts. Blackouts around the world have been triggered or worsened by circuit breakers tripping, including the blackout of 2003 in North America, where the secondary/ remote protection relays incorrectly opened the breaker. Tools that aid the operators in finding the root cause of the problem on-line are required. However, high system complexity and the interdependencies between the cyber and physical elements of the system and the mis-operation of protection devices make the failure diagnosis a challenging problem.

Using temporal causal models to isolate failures in power system protection devices

We introduced the modeling paradigm of Temporal Causal Diagrams (TCD) in this paper. TCDs capture fault propagation and behavior (nominal and faulty) of system components. An example model for the power transmission systems was also described. This TCD model was then used to develop an executable simulation model in Simulink/ Stateflow. Though this translation of TCD to an executable model is currently done manually, we are developing model templates and tools to automate this process. Simulations results (i.e., event traces) for a couple of single and multi-fault scenarios were also presented. As part of our future work, we wish to test and study the scalability of this approach towards a larger power transmission system taking into account a far richer set of protection elements. Further, we wish to consider more realistic event traces from the fault scenarios including missing, inconsistent and out-of-sequence alarms and events.