Prakash Ranganathan

Agent-Oriented Designs for a Self Healing Smart Grid

Electrical grids are highly complex and dynamic systems that can be unreliable, insecure, and inefficient in serving end consumers. The promise of Smart Grids lies in the architecting and developing of intelligent distributed and networked systems for automated monitoring and controlling of the grid to improve performance. We have designed an agent-oriented architecture for a simulation which can help in understanding Smart Grid issues and in identifying ways to improve the electrical grid. We focus primarily on the self-healing problem, which concerns methodologies for activating control solutions to take preventative actions or to handle problems after they occur. We present software design issues that must be considered in producing a system that is flexible, adaptable and scalable. Agent-based systems provide a paradigm for conceptualizing, designing, and implementing software systems. Agents are sophisticated computer programs that can act autonomously and communicate with each other across open and distributed environments. We present design issues that are appropriate in developing a Multi-agent System (MAS) for the grid. Our MAS is implemented in the Java Agent Development Framework (JADE). Our Smart Grid Simulation uses many types of agents to acquire and monitor data, support decision making, and represent devices, controls, alternative power sources, the environment, management functions, and user interfaces.

Optimization models for energy reallocation in a smart grid

When a malfunction occurs in a Smart Grid electricity provisioning system, it is vitally important to quickly diagnose the problem and take corrective action. The self-healing problem refers to the need to take action in near real time to reallocate power to minimize the disruption. To address this need, we present a collection of integer linear programming (ILP) models designed to identify optimal combinations of supply sources, demand sites for them to serve, and the pathways along which the reallocated power should flow. The models explicitly support the uncertainty associated with alternative sources such as wind power. A simulator configured with multiple intelligent distributed software agents has been developed to support the evaluation of the model solutions.

A survey on smart grid metering infrastructures: Threats and solutions

Without a reliable metering and communication infrastructure, the smart grid could become a catastrophe to national security and economy. A true smart grid infrastructure should detect all existing and predict future threats through intrusion detection methods. Smart grids are susceptible to various physical and cyber-attack as a result of communication, control and computation vulnerabilities employed in the grid. The paper provides a comprehensive study on types of threats and solutions on smart grid communication and metering infrastructures. As a part of this survey, the smart grid metering infrastructures susceptibilities and recommended remedial actions are identified. In addition, the paper details types of known attacks on existing metering infrastructure and defensive methodologies.

Smart grid data analytics for decision support

As electric grid sensor data originating from several sensors such as the phasor measurement units (PMUs), intelligent relays, and new installation of smart meters, Plug-in Hybrid Electric Vehicles (PHEV) or Gridable Vehicles (GV), are exponentially growing, the data analytic platform for Smart Grid has huge potential (generation, transmission or distribution) and can play a significant role in the decision making process for meaningful data interpretation to act promptly or automate the grid process to avoid any failures or instability in the grid. This paper focuses on identifying the variables of interest that are important in the electric grid embedded in distributed real time data engines which will help decision support process for system operators. More specifically, the applicability and performance of M5 model and J 48 decision tree machine learning technique is investigated using the real electric grid data. We have presented how decision tree model such as M5P can support system operators in making effective decision in the Smart Grid. Two sets of test data are used in this paper; the first data set is taken from a 10 unit commitment with 50000 Gridable Vehicle and the latter analyzes a weekly New York City (NYC) demand data from NYISO.

A multiagent system using associate rule mining (ARM), a Collaborative filtering approach

Agent Oriented Programming (AOP) is a recent promising software paradigm that brings concepts from the theories of artificial intelligence into the mainstream realm of distributed systems, and yet it is rather difficult to find a successful application of agent oriented system (specifically) when large-scale systems are considered. When adopting an agent-oriented approach to solve a problem, there are a number of domain independent issues that must always be solved, such as how to model agent behavior to predict future action and how to allow agents to communicate rather than expecting developers to develop this core infrastructure themselves. In our paper, we address several problems that exist in a socialized e-learning environment and provide solutions to these problems through smart and collaborative agent behavior modeling which learn and adapt themselves through prior experiences, thereby assisting in successful implementation of this large scale e-learning system. In this paper, the author (s) proposes an implementation of a complete distributed e-learning system based on Collaborative filtering (CF) method. The system has intelligent collaborative filtering based tutoring system (ICFTS) capabilities that allow contents, presentation and navigation to be adapted according to the learners requirements. In order to achieve that development, two concepts were put together: multi-agent systems and data mining techniques (specifically, the ARM algorithm). All the implementation code is developed using MATLAB GUI environment. To our best knowledge, very few literatures discusses a portion of e-learning environment using adaptive software agents, but none of the current literatures addresses a complete implementation of their learning system in detail. The goal of the paper is to implement one such multi-agent based e-learning system which learns from its prior user experiences on top of an agent-oriented middleware that provides the domain-independent infrastructure, allowing the developers to focus on building the key logic behind it. In this system, the agents follow an adaptive cognitive learning approach, where the agent learns through user behaviors via a collaborative filtering technique, or experiencing and then processing and remembering the information in an e-learning environment. The paper will utilize agent (a piece of code) based environment in our e-learning system using ARM [1][2]. The paper follows a learning approach based cognitive domain of Blooms Taxonomy such as Analyze, Evaluate, Create, Apply, understand and remember.

User interface for situational awareness of openPDC

This paper uses complex phasor data (voltage, current and phase angle) from openPDC for situational awareness of the SmartGrid. Alarm notification features through E-mail and Short message service (SMS) on various parameters of Phasor Measurement Units (PMU) data has been developed in C# programming as an extension to the existing openPDC software functionalities. In addition, realtime display of PMU data based on the geographical locations of PMU is developed for openPDC software and is presented within a Google Maps-based Windows Forms application. The paper also discusses how to process the PMU data using a k-means clustering algorithm.

Uncertainty quantification of wind penetration and integration into smart grid: A survey

Quantification of uncertainty due to wind-energy production becomes more and more crucial as the penetration of wind into smart grid increases. System operators (TSOs) and planners would be interested to see how wind production varies over different look-ahead hours and estimate the probability of those variations under several uncertain conditions. As wind is a stochastic source of generation, this paper provides a state-of-the-art literature review on the uncertainties related to wind-energy dispatch.

A constrained topological decomposition method for the next-generation smart grid

The inherent heterogeneity in the uncertainty of variable generations (e.g., wind, solar, tidal and wave-power) in electric grid coupled with the dynamic nature of distributed architecture of sub-systems, and the need for information synchronization has made the problem of resource allocation and monitoring a tremendous challenge for the next-generation smart grid. Unfortunately, the deployment of distributed algorithms across micro grids have been overlooked in the electric grid sector. In particular, centralized methods for managing resources and data may not be sufficient to monitor a complex electric grid. This paper discusses a decentralized constrained decomposition using Linear Programming (LP) that optimizes the inter-area transfer across micro grids that reduces total generation cost for the grid. A test grid of IEEE 14-bus system is sectioned into two and three areas, and its effect on inter-transfer is analyzed.

Investigation of forecasting methods for the hourly spot price of the day-ahead electric power markets

Forecasting hourly spot prices for real-time electricity usage is a challenging task. This paper investigates a series of forecasting methods to 90 and 180 days of load data collection acquired from the Iberian Electricity Market (MIBEL). This dataset was used to train and test multiple forecast models. The Mean Absolute Percentage Error (MAPE) for the proposed Hybrid combination of Auto Regressive Integrated Moving Average (ARIMA) and Generalized Linear Model (GLM) was compared against ARIMA, GLM, Random forest (RF) and Support Vector Machines (SVM) methods. The results indicate significant improvement in MAPE and correlation co-efficient values for the proposed hybrid ARIMA-GLM method.

Using phasor data for visualization and data mining in smart-grid applications

This paper presents a density based clustering (DBSCAN) technique to visualize and analyze the smart-grid data. The technique will aid in detecting bad-data, various fault types, deviation on frequency, voltage or current values for better situational awareness. Synchrophasors (or a PMU) is a sensor placed on a transmission line that tracks voltage, current, phase and frequency of the line. To improve situational awareness of the smart grid monitoring in real-time, the utility must monitor the phasor data measurement delivered by the sensors. Time-stamped synchronized measurements offer tremendous benefit for pre and post-event analysis. The paper uses data from openPDC framework to aid system operators in carrying various predictive analytics, decisions.