Search

Micro-grid systems have been recently emerged for efficient integration and management of renewable energy sources, buildings’ equipment (e.g. ventilation; lighting; heating, ventilation, and air conditioning), and energy storage devices. The intermittent nature of the produced electricity from renewable energy sources constitutes, however, the main challenge for their seamless integration into buildings. Recent studies stated that storage devices, despite their actual high cost, could be used to tackle this issue by balancing between the variability of renewable energy sources production and the unpredictable building’s occupancy. However, managing the power flows in micro-grid systems is highly required in order to minimize the consumption from the electric grid while ensuring the quality and the reliability of electrical services. In this article, a micro-grid system platform is introduced for efficient integration and management of renewable energy sources and storage devices. The platform’s architecture is composed of three main components: (a) the power generation components that integrate the renewable energy sources together with the storage devices and the traditional electrical grid, (b) an advanced metering component for data gathering and analysis, and (c) control services for power flow management. The platform was developed and deployed in a real-setting scenario. Simulations and experimentations have been performed and results show the usefulness of the proposed platform for efficient management of the deployed micro-grid system.

Predicting electricity consumption represents one of most important information for efficient energy management in smart buildings. It is mainly used for occupancy prediction and the development of optimized control approaches of building’s appliances (e.g., lighting and heating/air conditioning systems). Recently, several approaches have been proposed for load profiling, prediction and forecasting. The work presented in this paper is towards the development of load forecasting approaches for being integrated for occupancy prediction and context-driven control of building’s appliances. We mainly investigated the accuracy of various machine learning and statistical methods for forecasting energy consumption. An IoT and Big Data based platform was deployed for gathering near-real time data about electricity/load consumption. Recorded data were used to deploy predictive models using ARIMA, SARIMA, XGBoost, Random Forest (RF), and Long Short-Term Memory. Experiments have been conducted and results are reported to shed more light on the accuracy of these methods for load forecasting.

The intermittent nature of renewable energy sources has attracted much interest for integrating storage devices towards the deployment of micro-grid systems. In fact, these devices could be deployed into the system by decoupling energy production from consumption mainly by storing the extra produced energy from RES during the day for eventual usage at night. However, for standalone systems, computing the optimum size of energy production systems and storage devices is required for continuous electricity supply. In this paper, a micro-grid system is modeled, sized, and experimented according to a given consumption profile using a deployed prototype at our EEBLab.

In the last decade, many research works have been conducted to further promote the use of electric vehicles by developing new technologies and services. However, the management of their charging planning and scheduling is still a challenging task that needs to be addressed. The main issue is to reroute vehicles to the suitable charging stations with less waiting time, fast charging process, while ensuring interesting points for their users. In this paper, a prediction model is introduced for managing and handling charging needs of electric vehicles. The aim is to predict the average charging rate and charging time of multiple requests by taking into account the inter-arrival of charging requests and the charging state of each electric vehicle. Simulations have been conducted with high number of charging requests and obtained results show the efficiency of the proposed approach by studying its impact on waiting times and the occupation of charging stations.

Context-awareness has been considered as a crucial fact for developing context-driven control approaches in which sensing, and actuation tasks are performed according to the contextual changes. This could be done by including the occupants’ presence, number, actions and behaviours in up-to-date context taking into account the complex interlinked elements, situations, processes, and their dynamics. Many recent studies have shown that occupants’ information is a major leading source of uncertainty when developing occupancy-driven control approaches for energy efficient buildings. Comprehensive and real-time fine-grained occupancy information has to be, therefore, integrated in order to improve the performance of these control approaches. The work presented in this paper is towards the development of a holistic platform that combines recent IoT and Big data technologies for real-time occupancy detection. We focus mainly on occupants’ presence by comparing static and dynamic machine learning techniques. Experiments have been conducted and results are presented to assess the usefulness of the platform and the effectiveness of real-time machine learning strategies for data streams processing.

nowadays, it is well known that a main solution for pollution reduction in cities will be the introduction of electric and hybrid vehicles on transportation roads. Many research efforts have been dedicated to develop new technologies to further promote the use of this type of vehicles. However, their penetration on transportation roads faces some obstacles that have not yet been fully tackled. For instance, the development of intelligent battery management systems needs to be further investigated taking into consideration the uncertainty linked to how vehicles will perform in different scenarios, such as traffic situation, driver behavior, and road profile. The work presented in this study is towards developing a battery management system by investigating new approaches for accurate estimation and prediction of remaining charge, the expected lifetime of the batteries and the remaining driving rang. We focus mainly on the integration of predictive analytics techniques for forecasting the state-of-charge. We first deployed statistical- and machine learning based techniques in real-sitting scenarios (LSTM, ARIMA and XGBoost). Experiments have been conducted using an electric vehicle platform and results are reported to shed more light on their accuracy for multiple-horizon forecasts of battery’s state of charge.

Micro-grid (MG) systems are increasingly deployed on buildings in order to enhance energy efficiency while maintaining occupants' comfort. A MG system includes renewable energy sources (RES) for energy production, storage devices for storing energy excess, and control strategies for orchestrating all components and for improving the efficiency of the system. However, forecasting methods are required to develop predictive control strategies in order to tackle the uncertainty and intermittency of energy production and consumption. The State-of-Charge (SoC) of batteries is one of the main parameters used in predictive control algorithms, because it indicates how much energy is stored and how long a MG system can be relying on the deployed storage devises. Several methods have been developed for SoC estimation, but little work has been dedicated for SoC forecasting in MG systems. In this paper, we introduce a predictive approach for SoC forecasting using the Long Short-Term Memory (LSTM) algorithm. Extensive experiments have been conducted and results are provided and show the accuracy of this algorithm for different forecasting horizons.

Batteries have shown great potential for being integrated in Micro-Grid (MG) systems. However, their integration is not a trivial task and, therefore, requires extensive modeling and simulations in order to efficiently estimating their State-of-Charge (SoC) within MG systems. The work presented in this article focuses mainly on battery modeling for SoC estimation. We put more emphasize on battery system's characterization, modeling, SoC estimation and its integration into MG systems in order to study its performance. In fact, an instrumentation platform, composed of recent and low cost sensing and actuating equipment, is developed in order to identify the battery's parameters and then build the battery model. The simulation results show good agreement with the experimental results, and thus the battery model is validated in both charging and discharging processes. Then, the battery's SoC estimation in both charging and discharging processes is investigated by means of sophisticated methods, such as, Artificial Neural Network, Luenberger observer and Kalman Filter combined with Coulomb counting. The results of these methods are reported and compared to the SoC estimated using the Coulomb counting method in order to end up with the precise method. The modeled battery is afterwards integrated into an MG system, which is deployed into our EEBLab (Energy Efficient Building Laboratory) test-site, for simulation and experimental investigations. Finally, the four algorithms for SoC estimation are included into the instrumentation platform, which is connected to a Lead-acid battery already integrated into the MG system, in order to show and compare their performances and accuracy for online battery's SoC estimation.

Recent advances in pervasive technologies, such as wireless, ad hoc networks, and wearable sensor devices, allow the connection of everyday things to the Internet, commonly denoted as the Internet of Things (IoT). The IoT is seen as an enabler to the development of intelligent and context-aware services and applications. However, handling dynamic and frequent context changes is a difficult task without a real-time event/data acquisition and processing platform. Big data technologies and data analytics have been recently proposed for timely analyzing information (i.e., data, events) streams. The main aim is to make users' life more comfortable according to their locations, current requirements, and ongoing activities. In this article, combining IoT techniques and Big data technologies into a holistic platform for continuous and real-time health-care data monitoring and processing is introduced. Real-testing experiments have been conducted and results are reported to show the usefulness of this platform in a real-case scenario.

The intermittent nature and overwhelming variability of the produced electricity from renewable energy sources (RES) constitutes the main challenge for their seamless integration into buildings. Recent studies stated that storage devises, despite their actual high cost, could be used to tackle this issue by balancing the intermittent nature of RES production and the unpredictable building's occupancy. In fact, these storage devises could handle this issue, which is very complex without taking into consideration actual occupancy and environmental context. This paper introduces a demand/response control approach by mainly focusing on micro-grid systems, which are composed of PVs, batteries, and buildings equipment (e.g., ventilation system, lighting, BVAC). A prototype was developed and deployed in a real-setting scenario at our EEBLAB. Experimentations have been performed and results show the usefulness of the proposed control approach for micro-grid systems.

Context-awareness is crucial for leveraging energy-efficient buildings by developing intelligent control approaches in which sensing and actuation tasks are performed according to the contextual changes. This could be done by including the users' actions and behaviours in up-to-date context taking into account the complex interlinked elements, situations, processes, and their dynamics. In this paper, we introduce a holistic platform that integrates recent sensing/actuating and Big data technologies for monitoring and data processing. The main aim is to develop context-driven control approaches whereby energy consumption, production, and storage could be controlled according to actual situations (e.g., occupancy, occupant behaviour patterns, energy production patterns, and weather data). A platform prototype was deployed in our university test site. Experiments have been conducted and preliminary results show the usefulness of this holistic platform for monitoring and data processing in energy efficient buildings.

Micro-Grid (MG) systems have been extensively studied and deployed to lower the power consumption while reducing the greenhouse gas emissions. Although, the challenge with Renewable Energy Sources (RES) is their uncertain and intermittent nature, things that led the researchers to think about integrating storage devices, especially batteries, into MG systems. The main aim is to store the excess of produced energy for further usage when not enough energy is available. Nevertheless, batteries modeling and characterization is mandatory to identify their parameters and study their performance within MG systems. Moreover, in order to continuously supply electricity to the building, it is required to figure out the optimum size of energy production systems and storage devices. This paper introduces a methodology for MG modeling and performance evaluation. Its main contribution is twofold, i) battery’s parameters identification, and ii) modeling and dimensioning method for both standalone and MG systems. An instrumentation platform, composed of recent sensing and actuating equipment, for MG energy management and battery characterization is developed. Simulation and experimental results show the effectiveness of the proposed methodology.