There has been excessive stress on the present resources owing to the ever-increasing demand of electricity. The population needs to be satisfied with their electricity demands, and the grid is being overused and therefore has become more fragile owing to the increasing electricity demand with the increasing population. Thus, the reliability as well as the efficiency of the grid has being affected. Therefore, the research to explore more ways in improving the efficiency and stability of the grid in a sustainable manner has occupied the center stage and therefore the coinage of new term, i.e., smart grid. One can define smart grid as an automation of electric grid with the current ICT that aims toward efficient management of electricity generation networks. One of the main features of smart grid is that of demand response (DR) which may be defined as the changes in the electricity usage pattern from their normal usage in response to the changing electricity pricing over time or to incentivize the payments which are designed to encourage users to decrease their usage at times of higher wholesale market price. The DSM activities are supported by the communication infrastructure, intelligent devices, sensors, and processors. This capability results in modification of load profiles and thereby helps the consumers in achieving financial gains and at the same time proper electricity usage. Energy savings and therefore reduced greenhouse gas emissions are also achieved through such process capabilities. DSM provides management of energy balance within the network and also helps in realizing the importance of intermittent renewable energy sources.

A Review on Demand Side Management Forecasting Models for Smart Grid

Choosing input variable and networks architecture are key processes for modeling short term incidence rate forecast by artificial neural networks, in this paper a method based on rough set theory is proposed to deal with them. In the proposed approach, the key factors that affect the incidence rate forecasting are firstly identified by rough set theory and then the input variables of forecast model can be determined. On the basis of the process mentioned above a set of influence rules can been obtained through reductive mining process of attributes and attribute values, then a neural networks of incidence rate forecast model is established on the rule set and BP-algorithm is adopt to optimize the networks. The method indicates that incidence rate forecast model can be established according some theoretical principles and avoiding blindness. A practical application is given at last to demonstrate the usefulness of the novel method.

Liang Liang Ma

Papers

Applying Rough Set Theory to Establish Artificial Neural Networks Model for Short Term Incidence Rate Forecasting