Biblio

Cyber threats have increased extensively during the last decade, especially in smart grids. Cybercriminals have become more sophisticated. Current security controls are not enough to defend networks from the number of highly skilled cybercriminals. Cybercriminals have learned how to evade the most sophisticated tools, such as Intrusion Detection and Prevention Systems (IDPS), and Advanced Persistent Threat (APT) is almost invisible to current tools. Fortunately, the application of Artificial Intelligence (AI) may increase the detection rate of IDPS systems, and Machine Learning (ML) techniques can mine data to detect different attack stages of APT. However, the implementation of AI may bring other risks, and cybersecurity experts need to find a balance between risk and benefits.

Harmonic distortions come into existence in the power system not only due to nonlinear loads of consumers but also due to custom power devices used by power utilities. These distortions are harmful to the power networks as these produce over heating of appliances, reduction in their life expectancy, increment in electricity bill, false tripping, etc. This paper presents an effective, simple and direct approach to identify the problematic cause either consumer load or utility source or both responsible for harmonics injection in the power system. This technique does not require mathematical model, historical data and expert knowledge. The online methodology is developed in the laboratory and tested for different polluted loads and source conditions. Experimental results are found satisfactory. This proposed technique has substantial potential to determine the problematic cause without any power interruption by plug and play operation just like CCTV.

Coming days are becoming a much challenging task for the power system researchers due to the anomalous increase in the load demand with the existing system. As a result there exists a discordant between the transmission and generation framework which is severely pressurizing the power utilities. In this paper a quick and efficient methodology has been proposed to identify the most sensitive or susceptible regions in any power system network. The technique used in this paper comprises of correlation of a multi-bus power system network to an equivalent two-bus network along with the application of Artificial neural network(ANN) Architecture with training algorithm for online monitoring of voltage security of the system under all multiple exigencies which makes it more flexible. A fast voltage stability indicator has been proposed known as Unified Voltage Stability Indicator (UVSI) which is used as a substratal apparatus for the assessment of the voltage collapse point in a IEEE 30-bus power system in combination with the Feed Forward Neural Network (FFNN) to establish the accuracy of the status of the system for different contingency configurations.