Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Energy disaggregation using multi-objective genetic algorithm designed neural networksPublication . Habou Laouali, Inoussa; Gomes, Isaías; Ruano, Maria; Bennani, Saad Dosse; Fadili, Hakim El; Ruano, AntonioEnergy-saving schemes are nowadays a major worldwide concern. As the building sector is a major energy consumer, and hence greenhouse gas emitter, research in home energy management systems (HEMS) has increased substantially during the last years. One of the primary purposes of HEMS is monitoring electric consumption and disaggregating this consumption across different electric appliances. Non-intrusive load monitoring (NILM) enables this disaggregation without having to resort in the profusion of specific meters associated with each device. This paper proposes a low-complexity and low-cost NILM framework based on radial basis function neural networks designed by a multi-objective genetic algorithm (MOGA), with design data selected by an approximate convex hull algorithm. Results of the proposed framework on residential house data demonstrate the designed models’ ability to disaggregate the house devices with excellent performance, which was consistently better than using other machine learning algorithms, obtaining F1 values between 68% and 100% and estimation accuracy values ranging from 75% to 99%. The proposed NILM approach enabled us to identify the operation of electric appliances accounting for 66% of the total consumption and to recognize that 60% of the total consumption could be schedulable, allowing additional flexibility for the HEMS operation. Despite reducing the data sampling from one second to one minute, to allow for low-cost meters and the employment of low complexity models and to enable its real-time implementation without having to resort to specific hardware, the proposed technique presented an excellent ability to disaggregate the usage of devices.
- Design of ensemble forecasting models for home energy management systemsPublication . Bot, Karol; Santos, Samira; Habou Laouali, Inoussa; Ruano, Antonio; Ruano, Maria da GraçaThe increasing levels of energy consumption worldwide is raising issues with respect to surpassing supply limits, causing severe effects on the environment, and the exhaustion of energy resources. Buildings are one of the most relevant sectors in terms of energy consumption; as such, efficient Home or Building Management Systems are an important topic of research. This study discusses the use of ensemble techniques in order to improve the performance of artificial neural networks models used for energy forecasting in residential houses. The case study is a residential house, located in Portugal, that is equipped with PV generation and battery storage and controlled by a Home Energy Management System (HEMS). It has been shown that the ensemble forecasting results are superior to single selected models, which were already excellent. A simple procedure was proposed for selecting the models to be used in the ensemble, together with a heuristic to determine the number of models.
- Non-intrusive load monitoring of household devices using a hybrid deep learning model through convex hull-based data selectionPublication . Habou Laouali, Inoussa; Ruano, Antonio; Ruano, Maria da Graça; Bennani, Saad Dosse; Fadili, Hakim ElThe availability of smart meters and IoT technology has opened new opportunities, ranging from monitoring electrical energy to extracting various types of information related to household occupancy, and with the frequency of usage of different appliances. Non-intrusive load monitoring (NILM) allows users to disaggregate the usage of each device in the house using the total aggregated power signals collected from a smart meter that is typically installed in the household. It enables the monitoring of domestic appliance use without the need to install individual sensors for each device, thus minimizing electrical system complexities and associated costs. This paper proposes an NILM framework based on low frequency power data using a convex hull data selection approach and hybrid deep learning architecture. It employs a sliding window of aggregated active and reactive powers sampled at 1 Hz. A randomized approximation convex hull data selection approach performs the selection of the most informative vertices of the real convex hull. The hybrid deep learning architecture is composed of two models: a classification model based on a convolutional neural network trained with a regression model based on a bidirectional long-term memory neural network. The results obtained on the test dataset demonstrate the effectiveness of the proposed approach, achieving F1 values ranging from 0.95 to 0.99 for the four devices considered and estimation accuracy values between 0.88 and 0.98. These results compare favorably with the performance of existing approaches.
- Home energy management systems with branch-and-bound model-based predictive control techniquesPublication . Bot, Karol; Habou Laouali, Inoussa; Ruano, Antonio; Ruano, MariaAt a global level, buildings constitute one of the most significant energy-consuming sectors. Current energy policies in the EU and the U.S. emphasize that buildings, particularly those in the residential sector, should employ renewable energy and storage and efficiently control the total energy system. In this work, we propose a Home Energy Management System (HEMS) by employing a Model-Based Predictive Control (MBPC) framework, implemented using a Branch-and-Bound (BAB) algorithm. We discuss the selection of different parameters, such as time-step, to employ prediction and control horizons and the effect of the weather in the system performance. We compare the economic performance of the proposed approach against a real PV-battery system existing in a household equipped with several IoT devices, concluding that savings larger than 30% can be obtained, whether on sunny or cloudy days. To the best of our knowledge, these are excellent values compared with existing solutions available in the literature.