• Deep Sheth
• Chetan Sheth

The power system is a highly complex network due to the fact that it is a large interconnected system. The power demand is increasing exponentially with the increase in population and therefore it becomes necessary to control the power generation and load demand. If the voltage instability violates the predefined limits, then it can result in the total collapse of the power system that is a blackout. Demand-side management plays a very vital role in balancing the energy generation and power consumption to maintain the stability of the complex network which ensures a secured and healthy operation of the power system so that the operator does not have to face the condition of the black start of the generating stations due to blackout. There are various strategies for demand-side management and those are peak clipping, load shifting, valley filling, strategic growth, flexible load shape, and strategic conservation but load shifting is heavily performed by the electric utilities as it is a very reliable technique to fulfill the mentioned criteria. DSM proves to be extremely helpful as it mitigates the need of the electric utility to erect the structure for generation, transmission, and distribution in order to meet the additional power demand. In current practice, the human operator itself has to perform the DSM algorithm on the forecasted load curve which is very time-consuming. This paper proposes a model which is based on artificial intelligence which will automize the demand side management process in order to eliminate human error and to decrease the human involvement factor. This recommended model which uses artificial neural networks has the potential to forecast the load shifted curve in the hourly pattern with the help of an autoregression moving average model. The proposed model has the capacity to benefit the electric utility in automizing the demand side management process and thus will eradicate human error and decrease the human involvement factor.

Artificial Neural Networks, Autoregression moving average model, Demand-side Management, Load Shifting.

"Artificial Intelligence for Demand Side Management", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 1, page no.b647-b653, January-2022, Available :http://www.jetir.org/papers/JETIR2201186.pdf

"Artificial Intelligence for Demand Side Management", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 1, page no. ppb647-b653, January-2022, Available at : http://www.jetir.org/papers/JETIR2201186.pdf