An Integrated Approach for Intrusion Detection in Intelligent Grid Computing Networks Using Machine Learning
K. MeenakshiDepartment of Networking and Communications, School of Computing, SRM Institute of Science and Technology, Kattankulathur, Chengalpet District, Tamil Nadu, India. meenaksk@srmist.edu.in0000-0002-5428-6353
Dr.M. Naga RajuAssociate Professor, Department of CSE, GITAM School of Technology, GITAM (Deemed to be University), Nagadenahalli, Doddabalapur, Bengaluru, India. nmysore2@gitam.edu0000-0003-0970-0911
Dr. Channabasamma ArandiComputer Science Department, Koneru Lakshmaiah Education Foundation, Bowrampet, Hyderabad, Telangana, India. channabasamma.ar@gmail.com0000-0003-4689-0638
Dr.D.V. Lalitha ParameswariComputer Science Department, G. Narayanamma Institute of Technology and Science, Hyderabad, India. dvlalitha@gnits.ac.in0000-0002-4283-2193
Dr.R.N. Ashlin DeepaComputer Science Department, Goksraju Rangaraju Institute of Engineering and Technology, Hyderabad, India. rndeepa.pradeep@gmail.com0000-0002-1742-7516
Veena PotdarAssistant Professor, Department of CSE, Dr. Ambedkar Institute of Technology, Outer Ring Road, Mallathahalli, Bangalore, India. veenapotdar@gmail.com0000-0003-3006-688X
Intelligent Grid (IG) systems improve the usability of old energy networks, but they can still be hacked in many ways. Intruders can get into the system through these holes, risking IG networks' safety and privacy. An Intrusion Detection System (IDS) keeps services safe and secure in an IG setting. With the help of Machine Learning (ML) techniques and characteristics, this work shows an IDS for IG platforms. The categorization algorithm comprises a Convolutional Neural Network (CNN) and a Gated Recurrent Unit (GRU). The research uses Precision, Intrusion Detecting Rate (IDR), and False Alarming Ratio (FAR) to rate how well the suggested approach works. It turns out that the Random Forest (RF) and Neural Network (NN) algorithms did outperform the others. The study found that the KDD-99 records had a False Alarm Rate (FAR) of 7.29%, and the NSL-KDD records had a FAR of 7.31%. 88.68% of the time, both methods find things, and 90.87% of the time, they confirm that they are correct.