Data science for building energy management: a review
read more
Citations
Model Predictive Control (MPC) for Enhancing Building and HVAC System Energy Efficiency: Problem Formulation, Applications and Opportunities
A review of strategies for building energy management system: Model predictive control, demand side management, optimization, and fault detect & diagnosis
A review of machine learning in building load prediction
Renewable energy: Present research and future scope of Artificial Intelligence
A review of operating performance in green buildings: Energy use, indoor environmental quality and occupant satisfaction
References
Data clustering: a review
Anomaly detection: A survey
FCM: The fuzzy c-means clustering algorithm
Top 10 algorithms in data mining
Related Papers (5)
A review of data-driven building energy consumption prediction studies
Frequently Asked Questions (21)
Q2. What future works have the authors mentioned in the paper "Data science for building energy management: a review" ?
In the near future, Big Data techniques will expand these possibilities and democratize them. This will enhance energy awareness, since users will have access to more data and be able to understand their own energy consumption habits.
Q3. What are the common techniques used for descriptive reports of energy loads?
fuzzy rules (which have been widely used for HVAC control) can also be used for descriptive reports of energy loads since they offer a robust representation in the context of high imprecision and uncertainty.
Q4. What are the techniques traditionally used for this task?
The techniques traditionally used for this task are classification, clustering, and pattern analysis (mostly by means of association rules).
Q5. What are the main technologies that are expected to have a significant impact on Energy Efficiency and Management?
Apart from Big Data, other technologies that are expected to have a significant impact on Energy Efficiency and Management include Smart metering, the Internet of Things and Cloud computing.
Q6. What was the first study to use the ISPC algorithm?
The ISPC algorithm (Incremental Summarization and Pattern Characterization) was used by De Silva et al. [52] to structure stream data into a data warehouse based on key dimensions for enabling a rapid interim summarization.
Q7. What other techniques have been used to extract predicted operation rules?
Xaio and Fan [35] used cluster analysis to identify daily power consumption patterns, whereas Morbitzer et al. [36] applied clustering to analyze simulation results for performance predictions in order to extract predicted operation rules.
Q8. How much energy is used in buildings?
According to the International Energy Agency (IEA), residential and commercial buildings are responsible for up to 32% of the total final energy consumption.
Q9. What is the main advantage of cloud computing?
Cloud computing enables continuous and transparent updates and improvements, which are readily available to customers.
Q10. What are the common problems in sequence analysis?
Frequent problems in sequence analysis include the following: (i) the extraction of sequence information using techniques such as Motif Mining (MM); (ii) the detection of frequently occurring patterns; (iii) the search for similar sequences with a time lag by means of autocorrelation methods such as the ACF (Autocorrelation Function) and PACF (Partial Autocorrelation Function); (iv) the recovery of missing sequence members.
Q11. What are some examples of methods that could be applied to Building Energy Management?
Examples include methods with more accurate results, methods capable of handling temporal data or data streams, etc., which could feasibly be applied to Building Energy Management.
Q12. What are the main advantages of using classification models?
In addition, classification models are effective tools that can be used to predict building user comfort under different environmental conditions [28].
Q13. What is the objective of detecting anomalies?
The objective of detecting anomalies is to identify items, events, or observations that deviate from expected patterns or from the usual behavior of other data items [19].
Q14. Why are some industries reluctant to embrace cloud computing?
Because of security constraints and privacy concerns, some industries are still reluctant to embrace cloud computing and cloud technologies in general.
Q15. What are the common techniques used for predicting energy loads?
Techniques such as association rules in all its variants are certainly underrepresented when modelling and predicting energy loads.
Q16. What were the main techniques used by Jiang et al.?
Classification techniques were also used by Jiang et al. [64], who created a new automatic feature analysis method using wavelet techniques and combining multiple classifiers to identify fraud in electricity distribution networks.
Q17. What is the main reason why companies are reluctant to embrace cloud computing?
For most companies, cloud computing seems a plausible choice since they can avoid scalability problems, and reduce deployment costs and time.
Q18. What is the popular method of detecting fraud in electricity companies?
Filho et al. [63] described a method to fight against fraud in electricity companies, which involves a classifying algorithm, based on decision trees, to pre-select potentially fraudulent customers, who will then undergo in-site inspection for fraud or faulty measurement equipment identification.
Q19. How can the authors detect faults in buildings?
By continuously monitoring the building, it is possible to detect when a fault has happened (typically an anomalous event) and how it affects to other equipment (by means of correlation analysis).
Q20. What other techniques were used to assist decision-making and optimize building design?
The same authors also applied classification and regression techniques couple with building indoor daylight methods to assist decision-making and optimize building design [38].
Q21. What are some of the common techniques used in energy efficiency and management?
Although these techniques have been the most frequently applied in Energy Efficiency and Management, others, which are not so well known (e.g. sequence analysis and anomaly detection), are also useful in providing solutions for building energy problems.