51
Internet of Things and Artificial Intelligence
automatically over a network without any personal or human-to-computer interaction. It
uses a combination of wireless technologies, micro-electro-mechanical systems (MEMS),
and the Internet.
The IoT will play a significant role in smart grid (Al-Ali and Aburukba, 2015). It is
intended to perform network safety management, network operations, and maintenance,
and further can be used to monitor end-user interactions and finally more importantly to
make the smart grid secure. The IoT is not only a big world of connected devices but also
a tool that we can use to implement a smart grid.
In order to meet the growing demand for electricity, we cannot be afraid of these new
techniques and systems. The technologies and applications needed for smart grid are a
50–50 combination of modern information and communication technologies (ICT) and traditional grid technologies. We have these technologies. We just need to integrate existing
systems.
While smart grid technologies are available, people from both ICT and utility engineering communities do need to work together to make the smart grid dream come true.
3.6.5 Metrics Used
Smart grid data and analytics will revolutionize the way power is managed, delivered,
and sold. While collecting accurate, timely, and relevant data is of prime importance
for any data analytic program, the data need to be put into an appropriate context to
obtain useful information. The following are some of the fundamental analytical data
transformations which have immediate relevance to smart grid applications: aggregations, correlations, trending, exception analysis, and forecasting. Many high-value analytical processes combine several of these techniques as part of an overall analytical process
(Ranganatham, 2011). We use forecast method for our implementation in this chapter.
3.6.5.1 Forecasts
Forecasts are predictions of future events or values using historical data (Aung et al., 2012).
For instance, a forecast of power consumption for a new residential subdivision can be created using history from similar homes. Forecasts can also be built using correlation data.
For example, a forecast could be a simple prediction to understand the effect of one incremental megawatt of power consumption for each one-degree rise in summer temperature
above 40°C, or it could be a more finer and sophisticated set of algorithms that forecast
maintenance expenses based on the age of equipment, utilization trends, and past service
trends for similar equipment.
3.6.6 Datasets Used
This section discusses the datasets used in our experiments.
3.6.6.1 UMass Smart* Microgrid Data Set
A microgrid data (Barker et al., 2012) is a new paradigm developed by the inclusion of
distributed generation of smart grids. This dataset includes electrical data from over
400 homes. In the course of the Smart* project, investigation is made based on design,
deployment, and efficient use of smart homes for sustainability.
Internet of Things and Artificial Intelligence
automatically over a network without any personal or human-to-computer interaction. It
uses a combination of wireless technologies, micro-electro-mechanical systems (MEMS),
and the Internet.
The IoT will play a significant role in smart grid (Al-Ali and Aburukba, 2015). It is
intended to perform network safety management, network operations, and maintenance,
and further can be used to monitor end-user interactions and finally more importantly to
make the smart grid secure. The IoT is not only a big world of connected devices but also
a tool that we can use to implement a smart grid.
In order to meet the growing demand for electricity, we cannot be afraid of these new
techniques and systems. The technologies and applications needed for smart grid are a
50–50 combination of modern information and communication technologies (ICT) and traditional grid technologies. We have these technologies. We just need to integrate existing
systems.
While smart grid technologies are available, people from both ICT and utility engineering communities do need to work together to make the smart grid dream come true.
3.6.5 Metrics Used
Smart grid data and analytics will revolutionize the way power is managed, delivered,
and sold. While collecting accurate, timely, and relevant data is of prime importance
for any data analytic program, the data need to be put into an appropriate context to
obtain useful information. The following are some of the fundamental analytical data
transformations which have immediate relevance to smart grid applications: aggregations, correlations, trending, exception analysis, and forecasting. Many high-value analytical processes combine several of these techniques as part of an overall analytical process
(Ranganatham, 2011). We use forecast method for our implementation in this chapter.
3.6.5.1 Forecasts
Forecasts are predictions of future events or values using historical data (Aung et al., 2012).
For instance, a forecast of power consumption for a new residential subdivision can be created using history from similar homes. Forecasts can also be built using correlation data.
For example, a forecast could be a simple prediction to understand the effect of one incremental megawatt of power consumption for each one-degree rise in summer temperature
above 40°C, or it could be a more finer and sophisticated set of algorithms that forecast
maintenance expenses based on the age of equipment, utilization trends, and past service
trends for similar equipment.
3.6.6 Datasets Used
This section discusses the datasets used in our experiments.
3.6.6.1 UMass Smart* Microgrid Data Set
A microgrid data (Barker et al., 2012) is a new paradigm developed by the inclusion of
distributed generation of smart grids. This dataset includes electrical data from over
400 homes. In the course of the Smart* project, investigation is made based on design,
deployment, and efficient use of smart homes for sustainability.