Climate change has become a major problem for humanity in the last two decades. One of the reasons that caused it, is our daily energy waste. People consume electricity in order to use home/work appliances and devices and also reach certain levels of comfort while working or being at home. However, even though the environmental impact of this behavior is not immediately observed, it leads to increased CO2 emissions coming from energy generation from power plants. It has been shown that about 40% of these emissions come from the electricity consumption and also that about 20% of this percentage could have been saved if we started using energy more efficiently. Confronting such a problem efficiently will affect both the environment and our society. Monitoring energy consumption in real-time, changing energy wastage behavior of occupants and using automations with incorporated energy savings scenarios, are ways to decrease global energy footprint. In this review, we study intelligent systems for energy management in residential, commercial and educational buildings, classifying them in two major categories depending on whether they provide direct or indirect control. The article also discusses what the strengths and weaknesses are, which optimization techniques do they use and finally, provide insights about how these systems can be improved in the future.

The electricity consumption of a residence depends on many factors such as the habits and economical status of the occupants, the properties of the household and many more. To shed more light on the subject a data set for households was created. The data were collected in Greece through an anonymous survey that comprises 26 questions, resulting in 188 data points from 104 households from different time periods. Each data point contains attributes that are divided into four categories. In the first category, the information is about the household data such as the type and properties of the residence. Next, occupants' socio-economic features are gathered. In this category information for the number and type of the occupants, the employment status and the total income of the residents is included. The third category of attributes is about the energy-related occupants' behavior. Finally, the location of the household was provided from the users to estimate the weather conditions for the provided time. Data augmentation was performed to discover non-trivial relationships between the data points. Thus, a secondary set of features was computed based on the raw attributes and is also included. The provided data set can be used to extract insights that could be valuable during the imminent energy crisis.

Climate change has become a major problem for humanity in the last two decades. One of the reasons that caused it, is our daily energy waste. People consume electricity in order to use home/work appliances and devices and also reach certain levels of comfort while working or being at home. However, even though the environmental impact of this behavior is not immediately observed, it leads to increased CO2 emissions coming from energy generation from power plants. Confronting such a problem efficiently will affect both the environment and our society. Monitoring energy consumption in real-time, changing energy wastage behavior of occupants and using automations with incorporated energy savings scenarios, are ways to decrease global energy footprint. In this review, we study intelligent systems for energy management in residential, commercial and educational buildings, classifying them in two major categories depending on whether they provide direct or indirect control. The article also discusses what the strengths and weaknesses are, which optimization techniques do they use and finally, provide insights about how these systems can be improved in the future.