In this paper, we present a conceptual study on a Virtual Power Plant (VPP) architecture for the optimal management of Distributed Energy Resources (DERs) owned by prosumers participating in Demand-Side Management (DSM) programs. Compared to classical VPP architectures, which aim to aggregate several DERs dispersed throughout the electrical grid, in the proposed VPP architecture the supervised physical domain is limited to single users, i.e., to single Points of Delivery (PODs) of the distribution network. The VPP architecture is based on a service-oriented approach, where multiple agents cooperate to implement the optimal management of the prosumer’s assets, by also considering different forms of Demand Response (DR) requests. The considered DR schemes range from Price-Based DRs to Event-Based DRs, covering both the normal operating functions and the emergency control requests applied in modern distribution networks. With respect to centralized approaches, in this study the control perspective is moved from the system level to the single prosumer’s level, who is allowed to independently provide flexible power profiles through the aggregation of multiple DERs. A generalized optimization model, formulated as a Mixed-Integer Linear Programming (MILP) problem, is also introduced. Such a model is able to compute the optimal scheduling of a prosumer’s assets by considering both DR requests and end-users’ requirements in terms of comfort levels while minimizing the costs.

The recent advances in computing technologies and the increasing availability of large amounts of data in smart grids and smart cities are generating new research opportunities in the application of Machine Learning (ML) for improving the observability and efficiency of modern power grids. However, as the number and diversity of ML techniques increase, questions arise about their performance and applicability, and on the most suitable ML method depending on the specific application. Trying to answer these questions, this manuscript presents a systematic review of the state-of-the-art studies implementing ML techniques in the context of power systems, with a specific focus on the analysis of power flows, power quality, photovoltaic systems, intelligent transportation, and load forecasting. The survey investigates, for each of the selected topics, the most recent and promising ML techniques proposed by the literature, by highlighting their main characteristics and relevant results. The review revealed that, when compared to traditional approaches, ML algorithms can handle massive quantities of data with high dimensionality, by allowing the identification of hidden characteristics of (even) complex systems. In particular, even though very different techniques can be used for each application, hybrid models generally show better performances when compared to single ML-based models.

The LoRaWAN technology, an example of Low Power Wide Area Network, is considered a possible IoT-derived solution for realizing private cellular (single-hop) communications in the industrial domain. However, despite LoRaWAN promises long range and dense environments with many obstacles (as the industrial ones), it may suffer from coverage issue. Additionally, the inverse relationship between data rates and range may be unacceptable for many industrial applications. In this paper, an innovative LoRaWAN range extender (based on an enhanced LoRaWAN node) is described, and its integration in the infrastructure of IIoT-enabled industrial wireless networks is presented. A frame relay strategy is suggested, thus avoiding to trade-off the highest data rates against an increased sensitivity. The feasibility of the solution is formally verified and the features of the realized proof-of-concept prototype, based on commercially available hardware, are discussed. The experimental results, obtained with a purposely designed test bench, show the effectiveness of the proposed approach. In particular, the range extender is transparent for legacy LoRaWAN networks as confirmed by correct relaying of uplink and downlink for different types of LoRaWAN message.

The rising concerns about global warming and environmental pollution are increasingly pushing towards the replacement of road vehicles powered by Internal Combustion Engines (ICEs). Electric Vehicles (EVs) are generally considered the best candidates for this transition, however, existing power grids and EV management systems are not yet ready for a large penetration of EVs, and the current opinion of the scientific community is that further research must be done in this field. The so-called Vehicle-to-Grid (V2G) concept plays a relevant role in this scenario by providing the communication capabilities required by advanced control and Demand-Side Management (DSM) strategies. Following this research trend, in this paper the communication requirements for the DSM of EVs in urban environments are discussed, by focusing on the mobile communication among EVs and smart grids. A specific system architecture for the DSM of EVs moving inside urban areas is proposed and discussed in terms of the required data throughput. In addition, the use of a Low-Power Wide-Area Network (LPWAN) solution—the Long-Range Wide Area Network (LoRaWAN) technology—is proposed as a possible alternative to cellular-like solutions, by testing an experimental communication infrastructure in a real environment. The results show that the proposed LPWAN technology is capable to handle an adequate amount of information for the considered application, and that one LoRa base station is able to serve up to 438 EVs per cell, and 1408 EV charging points.

The application of the most recent advances of the Internet-of-Things (IoT) technology to the automation of buildings is emerging as a promising solution to achieve greater efficiencies in energy consumption, and to allow the realization of sustainable models. The application of IoT has been demonstrated as effective in many fields, such as confirmed, for instance, by the Industry 4.0 concepts, which are revolutionizing modern production chains. By following this approach, the use of distributed control architectures and of IoT technologies (both wired and wireless) would result in effective solutions for the management of smart environments composed of groups of buildings, such as campuses. In this case, heterogeneous IoT solutions are typically adopted to satisfy the requirements of the very diverse possible scenarios (e.g., indoor versus outdoor coverage, mobile versus fixed nodes, just to mention a few), making their large-scale integration cumbersome. To cope with this issue, this paper presents an IoT architecture able to transparently manage different communication protocols in smart environments, and investigates its possible application for the monitoring and control of distributed energy resources in a smart campus. In particular, a use–case focused on the integration of the Long Range Wide Area Network (LoRaWAN) technology is considered to cope with heterogeneous indoor and outdoor communication scenarios. The feasibility analysis of the proposed solution is carried out by computing the scalability limits of the approach, based on the proposed smart campus data model. The results of the study showed that the proposed solution would be able to manage more than 10,000 nodes. An experimental validation of the LoRaWAN technology confirms its suitability in terms of coverage and latency, with a minimum LoRaWAN cell coverage range of 250 m, and a communication latency of about 400 ms. Finally, the advantages of the proposed solution in the supervision and management of a PV system are highlighted in a real-world scenario.