Search

This paper introduces SPLANDID , a novel techno-economic methodology for the optimal sizing, placement, and management of shared Battery Energy Storage Systems (BESSs) in residential communities that minimizes both capital and operational costs, along with energy losses within the community. To address the installation of two types of shared BESSs (i.e., single centralized BESS, multiple distributed BESSs), our methodology offers two distinct approaches: one optimizes the centralized BESS, while the other focuses on optimizing distributed BESSs. We formulate each approach as a constrained optimization problem and solve it using the particle swarm optimization (PSO) algorithm. To validate our methodology, we use real consumption and production patterns collected from households in a residential community in the United Kingdom (UK). We propose and compare three scenarios (i.e., no BESS installation, single BESS installation, and multiple BESSs installation) using various numerical metrics, such as total energy losses and total costs. Simulation results underscore the effectiveness of BESS installation, demonstrating an impressive 82.24% reduction in total costs compared to the benchmark scenario without BESS. Moreover, the installation of multiple distributed BESSs outperforms a single centralized BESS, reducing total costs and energy losses by 17.4% and 49.4%, respectively. Furthermore, the distributed installation proves efficient by decreasing the required storage capacity by 11.82% in contrast to the centralized approach. Compared to the large existing body of literature, this study contributes on several fronts. First, it explores the feasibility of installing multiple distributed shared BESSs in residential communities, departing from the dominant single centralized shared BESS installation in existing studies. The results obtained with this alternative installation strategy are highly promising from several perspectives. Secondly, our methodology is uniquely designed to base planning on actual batteries available on the market, enhancing its practical applicability in real-life scenarios. This approach contrasts with studies that often propose optimal sizes without considering the constraints imposed by the capabilities of existing batteries. • The planning and management of shared battery energy storage systems are addressed. • A literature review is conducted with meticulous classification of the articles. • Different scenarios are proposed to underscore the importance of storage systems. • Real data from a residential community in the UK are used to validate our proposal. [ABSTRACT FROM AUTHOR]

The evolution towards smart grids (SGs) is mainly characterized by the integration of renewable energy sources (RESs) throughout the grid. The intermittent nature of these sources necessitated the installation of energy storage systems (ESSs) to improve the efficiency and reliability in the power system. Moreover, the ongoing high price of batteries has encouraged the installation of shared ESSs in residential communities. However, managing the shared ESS and the energy flows in the community is considered a key challenge. In order to handle this issue, we introduce a novel energy management system (EMS), namely E nergy M anagement I n residential CO mmunities with shared storage based on multi-agent systems (EMICO). It finds the optimal energy trading operations between households, as well as the operations of the shared ESS that minimize the total energy losses. We first propose a new cluster-based architecture for the residential community in which we integrate Internet of Energy (IoE) devices to manage energy flows and find the shortest path to transfer energy with minimal loss from a cluster to the other. Then, we model our energy management problem as a constrained optimization problem and we use Lagrange multiplier method to solve it in a centralized way. In order to preserve households' privacy, we propose a decentralized approach based on multi-agent systems (MASs) to solve our problem. We test our approach on real data traces obtained from a set of households located in the United Kingdom. Numerical results show that EMICO outperforms a literature approach in terms of energy losses (up to 35.66% of reduction in energy losses), electricity bill (up to 21.21% cheaper), number of exchanged messages (up to 83.81% less messages exchanged), and length of required cables (up to 95.03% less cables required). [ABSTRACT FROM AUTHOR]

The evolution towards Smart Grids (SGs) represents an important opportunity for modernization of the energy industry. It is characterized by a bidirectional flow of information and energy between consumers and suppliers. However, the rapid increase of energy demands in residential areas is becoming a challenging problem. In order to address this issue, Demand-Side Management (DSM) has proven to be an effective solution. In this paper, we propose LOSISH, a price-based Demand Response (DR) system for load scheduling in residential Smart Homes (SHs) that achieves a trade-off between electricity payments and consumer's discomfort. Our proposed system considers Renewable Energy Sources (RESs), Battery Energy Storage System (BESS) and Plug-in Electric Vehicle (PEV). We formulate our scheduling as a constrained optimization problem and we propose a new hybrid algorithm to solve it. The latter combines two well known heuristic algorithms: Particle Swarm Optimization (PSO) and Binary Particle Swarm Optimization (BPSO). Moreover, we propose a new clustering algorithm based on Machine Learning (ML) to extract consumer's preferences from a real dataset that contains the historical consumption patterns of his smart appliances. We test our approach on real data traces obtained from a SH and we set up an experiment to evaluate our algorithm on a Raspberry Pi and measure its energy consumption. To prove the effectiveness of our approach, we compare our results with another approach from the literature in terms of electricity bill, Peak-to-Average Ratio (PAR), energy consumption, and execution time. Numerical results show that LOSISH outperforms the other approach in terms of electricity bill (up to 52.92% cheaper), PAR (up to 44% decrease in peak demands), energy consumption (up to 69.44% less consumption), and execution time (up to 63.15% faster). • The load scheduling problem in residential smart homes is studied. • A constrained problem is formulated to make a trade-off between costs and comfort. • A hybrid heuristic algorithm and a Machine Learning clustering model are proposed. • Real data collected from a smart home in the UK was used to validate our approach. • Simulation and experimental results demonstrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Existing thermal comfort prediction approaches by machine learning models have been achieving great success based on large datasets in sustainable Industry 4.0 environment. However, the industrial Internet of Things (IoT) environment generates small-scale datasets where each dataset may contain lots of worker's private data. The latter is challenging the current prediction approaches as small datasets running a large number of iterations can result in overfitting. Moreover, worker's privacy has been a public concern throughout recent years. Therefore, there must be a trade-off between developing accurate thermal comfort prediction models and worker's privacy-preserving. To tackle this challenge, we present a privacy-preserving machine learning technique, federated learning (FL), where an FL-based neural network algorithm (Fed-NN) is proposed for thermal comfort prediction. Fed-NN departs from current centralized machine learning approaches where a universal learning model is updated through a secured parameter aggregation process in place of sharing raw data among different industrial IoT environments. Besides, we designed a branch selection protocol to solve the problem of communication overhead in federating learning. Experimental studies on a real dataset reveal the robustness, accuracy, and stability of our algorithm in comparison to other machine learning algorithms while taking privacy into consideration. [ABSTRACT FROM AUTHOR]

Monitoring the thermal comfort of building occupants is crucial for ensuring sustainable and efficient energy consumption in residential buildings. Existing studies have addressed the monitoring of thermal comfort through questionnaires and activities involving occupants. However, few studies have considered disabled people in the monitoring of thermal comfort, despite the potential for impairments to present thermal requirements that are significantly different from those of an occupant without a disability. Additionally, people with disabilities can experience difficulties in expressing their thermal comfort, which further complicates assessment and monitoring. To overcome this, we propose the development of a new learning model using a deep neural network. Our model can predict the indoor thermal comfort of differently abled people in real time to facilitate remote monitoring. We generated our real dataset using a new Internet of Things (IoT) architecture. Our architecture also includes a data collection scheme to ensure an efficient collection process, enabling the collection of targeted data before transferring them to cloud servers for further data analysis. Experimental results illustrate the reliability of our data collection scheme in gathering useful and targeted data, as well as the efficiency of our deep learning-based model, which achieved an accuracy of 94% and a precision and recall of 98% and 97%, respectively. • Studied thermal comfort sensations of disabled people based on Fanger's PMV model. • Focused on three types of disability: Physical, Intellectual, and Neurological. • Through IoT network, we collected a real dataset on thermal comfort in France. • Analysed thermal sensation variations between disabled and abled people. • Build a new prediction model of disabled people's thermal sensations using deep neural network. [ABSTRACT FROM AUTHOR]