• M. Praveena
• G. Ragul

Smart grid that has Attack Recognition issues are acted like statistical learning issues for various attack situations in which the estimations are seen in group or online settings. In this approach, machine learning calculations are utilized to order estimations as being either secure or attacked. The framework for detecting attacks is given to misuse any accessible earlier information about the framework and overcome requirements emerging from the infrequent structure of the issue in the proposed approach. The best known batch and web based learning calculations (administered and semi supervised) are utilized with choice and highlight level combination to display the attack identification issue. The connections amongst factual and geometric properties of attack vectors utilized in the attack situations and learning calculations are investigated to recognize imperceptible attacks utilizing measurable learning strategies. Different tests are carried and analyzed with the proposed system. Test investigations demonstrate that machine learning algorithm can identify attacks with exhibitions higher than attack discovery calculations that utilize state vector estimation techniques in the proposed attack identification structure.

Machine Learning, smart grid, support vector machines

"ATTACK DETECTION USING MACHINE LEARNING METHODS AND SUPPORT VECTOR MACHINES IN SMART GRID", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 9, page no.870-875, September-2018, Available :http://www.jetir.org/papers/JETIR1809637.pdf

"ATTACK DETECTION USING MACHINE LEARNING METHODS AND SUPPORT VECTOR MACHINES IN SMART GRID", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 9, page no. pp870-875, September-2018, Available at : http://www.jetir.org/papers/JETIR1809637.pdf