Machine learning for energy consumption prediction and scheduling in smart buildings

  title={Machine learning for energy consumption prediction and scheduling in smart buildings},
  author={Safae Bourhnane and Mohamed Riduan Abid and Rachid Lghoul and Khalid Zine-dine and Najib Elkamoun and Driss Benhaddou},
  journal={SN Applied Sciences},
Predicting energy consumption in Smart Buildings (SB), and scheduling it, is crucial for deploying Energy-efficient Management Systems. Most important, this constitutes a key aspect in the promising Smart Grids technology, whereby loads need to be predicted and scheduled in real-time to cope for the strongly coupled variance between energy demand and cost. Several approaches and models have been adopted for energy consumption prediction and scheduling. In this paper, we investigated available… 

A Data-Driven Forecasting Strategy to Predict Continuous Hourly Energy Demand in Smart Buildings

The objective of this paper is to present an energy consumption forecasting strategy that allows hourly day-ahead predictions that is tested using real data from two buildings located in Valladolid, Spain.

Energy Consumption Prediction in Low Energy Buildings using Machine learning and Artificial Intelligence for Energy Efficiency

  • P. Vijayan
  • Computer Science, Engineering
    2022 8th International Youth Conference on Energy (IYCE)
  • 2022
A study of different prediction models in energy forecasting, implemented in Matlab, and results for the training and testing results are presented.

An Efficient Electric Energy Consumption Prediction System Using Machine Learning Framework An Efficient Electric Energy Consumption Prediction System Using Machine Learning Framework

This study proposes a method for forecasting the energy consumption of residential buildings by using machine learning technique and the random forest algorithm for classification is used, making it robust and hence increasing the accuracy.

Smart Energy Management System: A Comparative Study of Energy Consumption Prediction Algorithms for a Hotel Building

Different algorithms that predict the electrical energy consumption of hotels building are provided, a case study of a hotel building in Shanghai, using machine learning algorithms in RapidMiner software, such as Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT) and Random Forest (RF).

A Pragmatic Investigation of Energy Consumption and Utilization Models in the Urban Sector Using Predictive Intelligence Approaches

A review analysis of the various computational intelligence approaches currently being utilized to predict energy consumption through machine learning and deep learning-based models to lays a foundation stone for further research works to be undertaken for energy prediction.

Demand Analysis of Energy Consumption in a Residential Apartment using Machine Learning

A prediction analysis of energy consumption of a residential apartment using different machine learning models including multiple linear regression (MLR), random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNN) reveals that random Forest (RF) model can reach to the best accuracy with the highest performance parameters.

Sequential Learning-Based Energy Consumption Prediction Model for Residential and Commercial Sectors

A comparative analysis of a variety of deep features with several sequential learning models to select the optimized hybrid architecture for energy consumption prediction outperforms existing models over publicly available datasets, including Household and Korean commercial building datasets.

Generating Synthetic Data to Reduce Prediction Error of Energy Consumption

A model that takes time series energy consumption data as input, pre-processes the data, and then uses multiple augmentation techniques and generative adversarial networks to generate synthetic data which when combined with the original data, reduces energy consumption prediction error.

Smart Agriculture as a Cyber Physical System: A Real-World Deployment

The system architecture, the wireless communication infrastructure, and the processing behind the control unit of Smart Agriculture is presented, which is an intelligent system using Fuzzy logic and the use of batteries for optimal energy usage is advocated.

Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems

The artificial neural network model with the highest accuracy and the shortest calculation time among the developed prediction models was applied to the Building Automation System to enable real-time performance monitoring and to confirm the field applicability of the developed model.



An End to End Real Time Architecture for Analyzing and Clustering Time Series Data: Case of an Energy Management System

This paper is to present an end-to – end architecture for a real time test bed implemented at Al Akhawayn University in Ifrane Morocco to analyze and cluster time series sensor data using an IoT architecture composed of Kaa (a middleware), Kafka (a realtime data messaging queue), Spark (an in-memory data analytics platform) and k-means (a clustering algorithm).

Optimal Household Appliances Scheduling Under Day-Ahead Pricing and Load-Shaping Demand Response Strategies

In this paper, a detailed home energy management system structure is developed to determine the optimal day-ahead appliance scheduling of a smart household under hourly pricing and peak

Fuzzy Logic-Based Energy Management System Design for Residential Grid-Connected Microgrids

This paper presents the design of a low complexity fuzzy logic controller of only 25-rules to be embedded in an energy management system for a residential grid-connected microgrid including renewable

ICT for renewable energy integration into smart buildings: IoT and big data approach

This work presents the architecture of a real-world smart micro-grid testbed to be deployed in a university campus with an emphasis on the ICT component, advocating that SG will utilize Internet of Things (IoT) to source all types of data, and thus making the whole system fall within the realm of Big Data.

Scheduling smart home appliances using mixed integer linear programming

This paper considers the minimum electricity cost scheduling problem of smart home appliances, and the optimal power profile signal minimizes cost, while satisfying technical operation constraints and consumer preferences.

Neural Network Models for Time Series Forecasts

Across monthly and quarterly time series, the neural networks did significantly better than traditional methods in the present experiment, and were particularly effective for discontinuous time series.

Machine learning: Trends, perspectives, and prospects

The adoption of data-intensive machine-learning methods can be found throughout science, technology and commerce, leading to more evidence-based decision-making across many walks of life, including health care, manufacturing, education, financial modeling, policing, and marketing.