1887

Abstract

Nowadays, many electrical utilities are moving towards self-healing distribution grid. This is realized by adding to distribution system various sensors, intelligent electronic devices (IEDs), phasor measurement units (PMU), sequence of event recorders (SERs), reclosers, detectors, measurement units, automated controllers, and other automation equipment. Those elements provide a continuous stream of data to support grid performance and improve its reliability. Huge amount of data obtained from different smart grid sources satisfy all the Big Data (BD) characteristics. The success of future electric grid depends mainly on the effective utilization of the huge amount of the data flow. This mass of information is essential to make next generation electric grid more efficient, reliable, secure, independent, and supportive during normal conditions and contingencies. The self-healing grid requires a robust real-time computation system that monitors, processes, provides predictive analytics, performs data mining and statistics, and makes faster decisions of the diverse and complex data collected within the traditional and nextgeneration electric grid. This helps to detect, locate, and isolate various faults, reconfigure and reroute power of the distribution network to minimize service disruptions and outages.Implementation of self-healing control system is associated with big data utilization which is a persisting challenge. Computational complexity challenges is associated with processing huge amounts of data during operation of the electric power system. Therefore, this paper presents acomprehensive studies of the impact of implementing a smart real-time dynamic self-healing control strategy using BD process platform with deep learning technique on the distribution system for current grid and future smart grid. The deep learning technique is a subfield of machine learning. The deep learning is shown to be highly efficient solution for the analysis of massive amounts of data which is performed by discovering and utilizing available regularities in the inputs to help self-healing control system to network reconfiguration, and coordination of various distributed energy resourcesin the smart grid. The deep learning system complexity does notdepend on the number of grid buses, this is because the power flow solving time is approximately linear with respect to the number of system buses. However, the complexity of the system depends on the number of the system inputs. The Long Short Term Memory (LSTM) recurrent neural network will be used in modeling sequential data such as time series data. Such network has the ability to learn contextual information over the history of the input sequence. The BD analyticswill be used as a key to deal with the uncertainties and different sizes of structured and unstructured data. The advanced analytics techniques such as predictive analytics, in addition to data mining, statistics, and faster decisions making will be utilized for data coming from sensors within the traditional and next-generation electric grid. The studies performed are based on real-time monitoring and control of the network topology and operating conditions taking into account different power sources and hybrid renewable energy sources which usually have different characteristics on the electric power grid. Finally, the real-time implementations of the proposed system will achieve dynamic resources optimization, network reconfiguration, and optimum operation of power grid using LSTM with big data platform.

Loading

Article metrics loading...

/content/papers/10.5339/qfarc.2018.EEPD549
2018-03-12
2019-10-14
Loading full text...

Full text loading...

http://instance.metastore.ingenta.com/content/papers/10.5339/qfarc.2018.EEPD549
Loading
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error