• Deep Sheth
• Chetan Sheth

The power system is a perplexed interconnected network. The network is growing rapidly with the increase in the power demand with the increasing population which has made it compulsory to use modern energy management system (EMS). In such a perplexed interconnected network it is crucial to meet the load demand with the power generation, otherwise, issues like voltage instability, voltage collapse, or blackout might take place. Here comes the role of demand-side management which holds a crucial position for managing the load demand and power generation to ensure the power system stability, security, and reliability. In demand-side management, there are certain strategies like load shifting, peak clipping, strategic growth valley filling, flexible load shape, and strategic conservation which can aid the electric utility in matching the power generation and load demand. However, load shifting proves to be one of the best strategies to fulfil the above-mentioned criteria satisfactorily. It is essential to revise the structure for generation, transmission, and distribution so that the additional load demand can be fulfilled but by using the DSM strategy we can eradicate the need of erecting the revised structure. Currently, The DSM algorithm is supposed to be applied by the human operator only on the forecasted load curve to obtain the load shifted curve which is a lengthy and very time-consuming process. This paper proposes a model which is based on artificial neural networks and has the potential to automize the demand-side management process which in turn reduces human interference and hence mitigates the involved human error. The proposed model aids the electric utility in forecasting the load-shifted curve in the hourly pattern with the help of artificial neural networks and by using an autoregressive moving average model with exogenous inputs. This model will greatly help the electric utility in automizing the demand-side management process and hence minimizes the human interference which in turn removes the involved human error.

Artificial Neural Networks, Autoregressive moving average model with exogenous inputs, Demand-side Management, Load Shifting.

"An Application of Artificial Neural Networks in Power Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.j427-j433, May-2022, Available :http://www.jetir.org/papers/JETIR2205A55.pdf

"An Application of Artificial Neural Networks in Power Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppj427-j433, May-2022, Available at : http://www.jetir.org/papers/JETIR2205A55.pdf