Rule Based Novel Method for Self Healing Attack Revelation for Smart Grids
Arvind P. Kadam1, S. G. Ankaliki2
1Arvind P. Kadam*, Research Scholar, Department of Electrical and Electronics Engineering, SDM College of Engineering, Dharwad, Affiliated to Visvesvaraya Technological University, Belgavi-Karnataka-India.
2Dr. S. G. Ankaliki, Head & Professor, Department of Electrical and Electronics Engineering, SDM College of Engineering, Dharwad, Affiliated to Visvesvaraya Technological University, Belgavi-Karnataka-India.
Manuscript received on March 30, 2020. | Revised Manuscript received on April 05, 2020. | Manuscript published on April 30, 2020. | PP: 1353-1358 | Volume-9 Issue-4, April 2020. | Retrieval Number: D7829049420/2020©BEIESP | DOI: 10.35940/ijeat.D7829.049420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, we introduce a new idea for the rebuilding of measuring sensor data collected from the power grid, eliminating the impact of the attack on the integrity of confidential data. The introduced system is based on the reconstruction of Monte Carlo analysis of experimental data and the measurement of actual training data of the transfer function of the information gathered by sensor of the strong nonlinear representation data through the root is added to the sensor measurements based on quality parameters by a clever attacker. For strong, multivariate reconstruction measures against multiple attacks sensors based regulation attack detection is used. The introduced scheme is check out using a standard IEEE 34-bus and real samples were collected from a grid system. The simulation results confirm that the introduced scheme can handle the label and non-label and attacks based on the proposed rules historical measurement data decided on the basis of the received value RAE become. 5.5. Self- healing recovery is possible within 10 msec of time limit if multiple attacks are detected by local system agent then feed gain of agent scheduler is adjusted to 1/4 to 1/3. Finally, if the value of RAE deviates according to the complexity of the time constant increases to 20 msec to recover the original response was very close to that of the nominal case.
Keywords: Cyber Security, Cyber Assaults, Deep Learning, Self-healing smart grids, State Estimation