Future smart grids will open the marketplace to novel services for grid management, such as Demand Side Management (DSM). To achieve energy saving in distribution systems, DSM aims at modifying load profile patterns of electricity demand by involving actively customers. In particular, residential customers can participate to this service by shifting their energivourous appliances (e.g. washing machine and dishwasher).In this paper, we present a novel DSM service to manage a day ahead balance. It exploits a human-in-the-loop approach to provide suggestions on shifting their appliances based on Latent Dirichlet Allocation algorithm combining both i) the probability density function of each customer's appliance usage and ii) the cost function. To assess our DSM service, we present our experimental results performed in a realistic environment where we simulated a virtual population of about 1′000 families.
A Distributed Software Solution for Demand Side Management with Consumer Habits Prediction / Barbierato L.; Bottaccioli L.; MacIi E.; Grasso E.; Acquaviva A.; Patti E.. - STAMPA. - (2019), pp. 8783512.1-8783512.6. (Intervento presentato al convegno 19th IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019 tenutosi a ita nel 2019) [10.1109/EEEIC.2019.8783512].
A Distributed Software Solution for Demand Side Management with Consumer Habits Prediction
Acquaviva A.;
2019
Abstract
Future smart grids will open the marketplace to novel services for grid management, such as Demand Side Management (DSM). To achieve energy saving in distribution systems, DSM aims at modifying load profile patterns of electricity demand by involving actively customers. In particular, residential customers can participate to this service by shifting their energivourous appliances (e.g. washing machine and dishwasher).In this paper, we present a novel DSM service to manage a day ahead balance. It exploits a human-in-the-loop approach to provide suggestions on shifting their appliances based on Latent Dirichlet Allocation algorithm combining both i) the probability density function of each customer's appliance usage and ii) the cost function. To assess our DSM service, we present our experimental results performed in a realistic environment where we simulated a virtual population of about 1′000 families.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
