Search

Future smart grids with more distributed generation and flexible demand require well-verified control and management services. This article presents a distributed multimodel cosimulation platform based on smart grid architecture model to foster general purpose services in smart grids. It aims at providing developers with support to easily set-up a test-bed environment, where they can simulate realistic scenarios to assess their algorithms and services. The proposed platform takes advantages of internet-of-things communication paradigms and protocols to enable the interoperability among different models and virtual or physical devices that compose a use case. Moreover, the integration of digital real-time simulators unlocks hardware-in-the-loop features. To test the functionality of our platform, a novel scheme of fault detection, isolation, and restoration is developed, in which communication and interoperability of different functions and devices are crucial. This service is applied on a realistic portion of a power grid in Turin, Italy, where devices communicate over the Internet. Finally, the laboratory experimental results achieved during a real-time cosimulation are discussed. [ABSTRACT FROM AUTHOR]

Artificial Neural Networks (ANNs) can successfully be integrated into smart models for energy prediction, but require large datasets for training. This investigation presents an innovative methodology for photovoltaic power generation forecasting with ANNs, when only a limited amount of real data is available, and has been tested and validated on a real-life photovoltaic installation. Feature selection identifies which meteorological features most impact photovoltaic power generation. A simulator, which accurately models a real photovoltaic installation, is used to create an artificial, but accurate and realistic, dataset of power generation large enough to effectively train and test different ANNs. These are then exploited on a portion of real, but limited, dataset of power generated by the real photovoltaic installation on which the simulator is modeled. Finally, different transfer learning techniques are used to tune the ANN models with the remaining portion of the real, but limited, dataset of photovoltaic power generation. • Innovative PV power generation forecasting with ANNs, for limited real data. • IoT sensors to collect limited real data, simulator to generate artificial data. • ANNs trained on artificial data and tested on real data. • Transfer learning used to tune the ANN models. • Methodology tested on a real-life PV installation in Turin, Italy. [ABSTRACT FROM AUTHOR]

For planning and development and in real-time operation of smart grids, it is important to evaluate the impacts of photovoltaic (PV) distributed generation. This paper presents an integrated platform, constituted of two main components: a PV simulator and a real-time distribution network simulator. The first, designed and developed following the microservice approach and providing Representational State Transfer web services, simulates real-sky solar radiation on rooftops and estimates the PV energy production. The second, based on a digital real-time power systems simulator, simulates the behaviour of the electricity network under the simulated generation scenarios. The platform is tested on a case study based on real data for a district of the city of Turin, Italy. In the results, the authors show possible applications of the platform for power flow forecasting during real-time operation and for detecting possible voltage and transformers' capacity problems during planning due to high penetration of renewable energy sources. In particular, the results show that the case study distribution network, in the actual configuration, is not ready to accommodate all the generation capacity that can be installed, as, in certain hours of the day and on certain days of the year, the capacity of some transformers is exceeded. [ABSTRACT FROM AUTHOR]

The prediction of solar radiation allows estimating photovoltaic systems' power production in advance, guaranteeing a more reliable and stable energy supply. In this work, we present a novel approach for short-term solar radiation forecasting that leverages multi-channel images from the geostationary satellites of the Meteosat series, coupled with GHI values in clear-sky conditions. We propose two distinct deep learning models, a 3D-CNN and a ConvLSTM, to forecast solar radiation in terms of GHI values, up to 6-h ahead with a temporal granularity of 15 min, over a test study area, the city of Turin, Piedmont, Italy. The models have been validated with ground GHI measurements, and the results show that the ConvLSTM consistently outperforms the 3D-CNN for longer forecasting horizons, achieving a MAD of 27.18% and an nRMSE of 0.57 for 6-h ahead predictions. To motivate the use of satellite images, we compared the performance of our approach with a baseline Smart Persistence model and another benchmark model, which previously achieved state-of-the-art performance on the same data set by exploiting various kinds of meteorological inputs. The proposed models outperform the Smart Persistence for predictions farther than 15-min ahead, achieving a Forecast Skill of 0.56 for predictions 6-h ahead. Furthermore, the comparison shows that using raw satellite images overcomes the performance achievable by solely using meteorological variables, reducing the RMSD by more than 3% and the MAD by 1.37% for prediction horizons greater than 4-h ahead. [ABSTRACT FROM AUTHOR]

District Heating (DH) technology is considered to be a sustainable and quasi-renewable way of producing and distributing hot water along the city to heat buildings. However, the main obstacle to wider adoption of DH technology is represented by the thermal request peak in the morning hours of winter days, especially in Mediterranean countries. In this paper, this peak-shaving problem is tackled by combining three different approaches. A thermodynamic model is used to monitor the buildings' thermal response to energy profile modifications. An agent-based model is adopted in order to represent the end-users and their adaptability to variations of temperatures in buildings. Finally, a Reinforcement Learning algorithm is used to optimally mediate between two needs: on the one hand, a set of anticipations and delays is applied to the energy profiles in order to reduce the thermal request peak. On the other hand, the algorithm learns by trial and error the individual agents' sensitivity to thermal comfort, avoiding drastic modifications for the most sensitive users. The experiments carried out in the DH network in Torino (north-west of Italy) demonstrate that the proposed approach, compared with a literature solution chosen as a baseline, allows to achieve better results in terms of overall performances and speed of convergence. [ABSTRACT FROM AUTHOR]