The energy sector is currently undergoing a significant shift, driven by the growing integration of renewable energy sources and the decentralization of electricity markets, which are now extending into local communities. This transformation highlights the pivotal role of prosumers within these markets, and as a result, the concept of Renewable Energy Communities is gaining traction, empowering their members to curtail reliance on non-renewable energy sources by facilitating local energy generation, storage, and exchange. Also in a community, management efficiency depends on being able to predict future consumption to make decisions regarding the purchase, sale and storage of electricity, which is why forecasting the consumption of community members is extremely important. This study presents an innovative approach to manage community energy balance, relying on Machine Learning (ML) techniques, namely eXtreme Gradient Boosting (XGBoost), to forecast electricity consumption. Subsequently, a decision algorithm is employed for energy trading with the public grid, based on solar production and energy consumption forecasts, storage levels and market electricity prices. The outcomes of the simulated model demonstrate the efficacy of incorporating these techniques, since the system showcases the potential to reduce both the community electricity expenses and its dependence on energy from the centralized distribution grid. ML-based techniques allowed better results specially for bi-hourly tariffs and high storage capacity scenarios with community bill reductions of 9.8%, 2.8% and 5.4% for high, low, and average photovoltaic (PV) generation levels, respectively.

The growth of the automobile industry in recent decades and the overuse of personal vehicles have amplified problems directly related to road safety, such as the increase in traffic congestion and number of accidents, as well as the degradation of the quality of roads. At the same time, and with the contribution of climate change effects, dangerous weather events have become more common on road infrastructure. In this context, Cooperative Intelligent Transport Systems (C-ITS) and Internet of Things (IoT) solutions emerge to overcome the limitations of human and local sensory systems, through the collection and distribution of relevant data to Connected and Automated Vehicles (CAVs). In this paper, an intra- and inter-vehicle sensory data collection system is presented, starting with the acquisition of relevant data present on the Controller Area Network (CAN) bus, collected through the vehicle’s On-Board-Diagnostics II (OBD-II) port, as well as on an on-board smartphone device and possibly other additional sensors. Short-range communication technologies, such as Bluetooth Low Energy (BLE), Wi-Fi, and ITS-G5, are employed in conjunction with long-range cellular networks for data dissemination and remote cloud monitoring. The results of the experimental tests allow the analysis of the road environment, as well as the notification in near real-time of adverse road conditions to drivers. The developed data collection system reveals itself as a potentially valuable tool for improving road safety and to iterate on the current Road Weather Models (RWMs).

Road infrastructure plays a critical role in the support and development of the Cooperative Intelligent Transport Systems (C-ITS) paradigm. Roadside Units (RSUs), equipped with vehicular communication capabilities, traffic radars, cameras, and other sensors, can provide a multitude of vehicular services and enhance the cooperative perception of vehicles on the road, leading to increased road safety and traffic efficiency. Moreover, the central C-ITS system responsible for overseeing the road traffic and infrastructure, such as the RSUs, needs an efficient way of collecting and disseminating important information to road users. Warnings of accidents or other dangers, and other types of vehicular services such as Electronic Toll Collection (ETC), are examples of the types of information that the central C-ITS system is responsible for disseminating. To remedy these issues, we present the design of an implemented roadside and cloud architecture for the support of C-ITS services. With the main objectives of managing Vehicle-to-Everything (V2X) communication units and network messages of a public authority or motorway operator acting as a central C-ITS system, the proposed architecture was developed for different mobility testbeds in Portugal, under the scope of the STEROID research project and the pan-European Connected Roads (C-Roads) initiative. RSUs, equipped with ETSI ITS-G5 communications, are deployed with a cellular link or fiber optics connection for remote control and configuration. These are connected to a cloud Message Queuing Telemetry Transport (MQTT) broker where communication is based on a geographical tiling scheme, which allows the selection of the appropriate coverage areas for the dissemination of C-ITS messages. The architecture is deployed in the field, on several Portuguese motorways, where road traffic and infrastructure are monitored through a C-ITS platform with visualization and event reporting capabilities. The provided architecture is independent of the underlying communication technology and can be easily adapted in the future to support Cellular-V2X (PC5 interface) or 5G RSUs. Performance results of the deployed architecture are provided.

Forecasting road flow has strong importance for both allowing authorities to guarantee safety conditions and traffic efficiency, as well as for road users to be able to plan their trips according to space and road occupation. In a summer resort, such as beaches near cities, traffic depends directly on weather conditions, variables that should be of great impact on the quality of forecasts. Will the use of a dataset with information on transit flows enhanced with meteorological information allow the construction of a precise traffic flow forecasting model, allowing predictions to be made in advance of the traffic flow in suitable time? The present work evaluates different machine learning methods, namely long short-term memory, autoregressive LSTM, and a convolutional neural network, and data attributes to predict traffic flows based on radar and meteorological sensor information. The models trained to predict the traffic flow have shown that weather conditions were essential for this forecast, and thus, these variables were employed in the evaluated deep-learning models. The results pointed out that it is possible to forecast the traffic flow at a reasonable error level for one-hour periods, and the CNN model presented the lowest prediction error values and consumed the least time to build its predictions.

Future intelligent transportation systems (ITS) hold the promise of supporting the operation of safety-critical applications, such as cooperative self-driving cars. For that purpose, the communications among vehicles and with the road-side infrastructure will need to fulfil the strict real-time guarantees and challenging dependability requirements. These safety requisites are particularly important in wireless vehicular networks, where road traffic presents several threats to human life. This paper presents a systematic survey on fault tolerance techniques in the area of vehicular communications. The work provides a literature review of publications in journals and conferences proceedings, available through a set of different search databases (IEEE Xplore, Web of Science, Scopus and ScienceDirect). A systematic method, based on the preferred reporting items for systematic reviews and meta-analyses (PRISMA) Statement was conducted in order to identify the relevant papers for this survey. After that, the selected articles were analysed and categorised according to the type of redundancy, corresponding to three main groups (temporal, spatial and information redundancy). Finally, a comparison of the core features among the different solutions is presented, together with a brief discussion regarding the main drawbacks of the existing solutions, as well as the necessary steps to provide an integrated fault-tolerant approach to the future vehicular communications systems.