1,721,093 research outputs found
Editorial for Special Issue: “Feature Papers of Forecasting”
Full text linkNowadays, forecasting applications are receiving unprecedent attention thanks to their capability to improve the decision-making processes by providing useful indications [...
Comparative Analysis of Wireless Protocols in Smart Home Energy Management Systems
No full textThis paper presents a comprehensive comparative analysis of various wireless protocols employed in smart home energy management systems. As the proliferation of smart home technologies continues, the efficient and reliable management of energy consumption becomes crucial. Wireless communication protocols, such as Zigbee, Thread, Z-Wave, Wi-Fi, Bluetooth, and LoRa, play a pivotal role in ensuring seamless connectivity among smart devices. This study evaluates these protocols based on key performance metrics including energy efficiency, range, data throughput, scalability, and security. This comparative analysis aims to guide system designers in selecting the most appropriate wireless protocol to optimize energy management in smart homes, thereby enhancing sustainability and user experience. Comparing the aforementioned protocols evolves into an outcome that demonstrates a solution for smart home communication systems, such as Thread, ZigBee, and Z-Wave. These 3 protocols are precisely designed for home communication and controlling local network systems
An Overview of Data-Driven Methods for the Online State of Charge Estimation
No full textIn the last years, the drift toward electric mobility and the need for renewable energy penetration placed the batteries and their control in a prominent position. A critical parameter for the battery management system (BMS) is the state of charge (SOC) of the battery pack. This paper gives an overview of the trends of the last 5 years of SOC estimation, using data-driven estimation methods. Due to the evolution of electronic materials and the abundance of available data, data-driven methods became popular and advantageous
Advanced asset management tools in photovoltaic plant monitoring: UAV-based digital mapping
No full textPhotovoltaic (PV) plant monitoring and maintenance has become an often critical activity: the high efficiency requirements of the new European policy have often been in contrast with the many low-quality plants installed in several countries over the past few years. In actual industrial practices, heterogeneous information is produced, and they are often managed in a fragmented way. Several software tools have been developed for obtaining reliable and valuable information from the PV plant’s raw data. With the aim of gathering and managing all these data in a more complex and integrated manner, an information managing system is proposed in this work—it is composed of a structured database, called the Photovoltaic Indexed Database, and a user interface, called the Digital Map, that allows for easy access and completion of the information present in the database. This information managment system and PV plant digitalization process is able to analyze and properly index the IR in the database, as well as the visual images obtained in photovoltaic plant monitoring
Bayesian Hyperparameter Optimization of Stacked Long Short-Term Memory Neural Network for the State of Charge Estimation
No full textElectrification and reduction of fossil fuel usage placed the battery industry in a prominent position. The state of charge (SOC) of the battery is a crucial parameter for the optimal operation of the battery management system (BMS). In the last years, with the development of electronic materials and the ability to store a big amount of data, data-driven methods for the SOC of the battery can to capture the dynamics of the battery. A big problem of the data-driven methods is the selection of the hyperparameters of the model. Heuristic methods have been used mostly with manual tuning or through exhaustive methods, such as random search and grid search. In this paper, a Bayesian Hyperparameter Optimization with a Gaussian process is proposed and applied to a stacked Long Short-Term Memory (LSTM) neural network. The proposed method is validated using a public dataset and compared with other state-of-the-art methods, achieving low errors
Recycling of c-Si PV Modules: An Energy Analysis and Further Improvements
No full textNowadays, the management of our planet’s resources is becoming of primary importance due to their increasing exploitation from human activities. The present study focuses, in particular, on the management of photovoltaic (PV) waste produced when they reach their end-of-life. PV modules contain precious and valuable materials, as well as toxic materials that may cause problems for human health and the environment if not disposed of properly. This study aims, at first, to review and analyze the current literature in order to deeply understand the topic of recycling PV modules, particularly crystalline-Silicon ones, which represent the largest market share. A second part analyzes the energy consumption of these recycling processes considering first-generation c-Si PV modules. Finally, improvements are suggested also considering the design of PV modules (Eco-design). The study estimates that the energy consumed to recycle c-Si PV modules could reach values as low as 130÷300 kWh/ton of PV waste treated
Performance and Thermal Analysis of Organic Photovoltaic Modules in Outdoor Conditions
No full textOrganic photovoltaic (OPV) modules are an emerging, innovative and low-cost solution to convert sunlight into electricity. Their flexibility and semi-transparency make OPV modules a suitable solution even in applications that cannot be based on traditional photovoltaic (PV) technologies. However, high ageing rate, short lifetime and low efficiency have limited their diffusion. This paper presents two outdoor test campaigns designed to assess and to compare with traditional silicon-based PV technologies the power output of OPV modules operating in real environmental conditions. OPV modules, as well as silicon-based PV modules, were operated at their maximum power point for several days: data collected demonstrated that OPV power output is slightly enhanced by the cells temperature at low irradiance, while at high irradiance the temperature coefficient of power is close to zero. Unlike silicon-based PV technologies, quite constant maximum power point voltage regardless the OPV cells temperature justifies the latter result
User Behavior Clustering Based Method for EV Charging Forecast
Full text linkThe increasing adoption of electric vehicles poses new problems for the electrical distribution network. For this reason, proper electric vehicle forecasting will be of fundamental importance for a predictive energy management system, which could greatly help the operation of the grid. This paper proposes a comprehensive novel methodology to forecast single charging sessions of electric vehicle and the resulting cumulative energy forecast of the charging infrastructure. Historical charging sessions are first clustered on the basis of similar user characteristics and their respective probability density functions are defined. From this, every charging session is predicted with a triplet of parameters, namely the arrival time, the charging duration and the average power expected during the process. The proposed method has been evaluated by considering a real case study. The results showed the ability to greatly improve the accuracy with respect to the chosen benchmark, both in terms of energy required by the station and the predicted number of charging sessions. The overall performance measured by Skill Score is 0.37 for the year 2019
An Overview of Optimization Methods for Home Energy Management Systems
No full textEnergy Management System (EMS) is a major component of a smart grid and significant for the operational qualification. Controlling the residential grid, resulting into improving cost, emission, and comfort. The study aims to investigate the optimization methods used in Home Energy Management System(HEMS) and evaluate their effectiveness. The paper dis-cusses the architecture of HEMS, which is classified into three layers: physical, communication, and software. The physical layer comprises measurement systems and sensors for data acquisition, including smart meters, IoT sensors and smart appliances. The communication layer facilitates the interconnection between the control systems, central platforms, and smart devices. The software layer comprises the algorithmic and programming parts to optimize the system. Culminate into evaluating the different optimization methods used in HEMS, including mathematical, meta-heuristic, and artificial intelligence models
- …
