In United States the residential and
commercial buildings consume 73% of
the electricity. The Smart Grid implementations
have grown boosting concepts
such as: Demand Side Management
(DSM), Advanced Metering
(AM), Demand Response (DR) and
Scheduling and Forecasting (SF). The
renewable energy sources as wind turbines
and photovoltaics (PV) behave
uncertainly, therefore there is a gap between
the supply and demand energy.
To tackle the imbalances, many studies
have proposed solutions based on DR
strategies to reschedule the load energy.
From this perspective to accomplish
energy efficiency at household
level, it is necessary to use the flexibility
concept to adjust the supply demand
gap. This project proposes to get
the possible energy loads that can be
rescheduled as flexible consumption
descriptions (flex-offers). This work
focuses on wet devices (washing machine,
dishwasher) because they can
change the behaviour to fit in the RES
production energy and they represent
30% of household consumption.
In Demand Side Management, the
pricing mechanisms are designed to
encourage the consumers to change
their behaviour, for example the timeof-
use pricing sets different prices
during the day, hence the consumer
change the demand to off-peak hours.
In this context, to schedule the consumer
loads, we have to apply the best
machine learning models to get the
best results.