Prediction of Electric Power Production and Consumption for the CETATEA Building Using Neural Networks.

Economic and social development is hardly influenced by electric power production and consumption. In this context of the energy supply pressure, energy production and consumption must be monitored and controlled in an intelligent way. Due to the availability of large data measurements, prediction algorithms based on neural networks are widely used in accurate power prediction. Firstly, the particularity of our work is represented by the size of the dataset consisting of 4 years of continuous real-time data measurements collected from the CETATEA photovoltaic power plant, a research site for renewable energies located in Cluj-Napoca, Romania. Secondly, the high granularity of the dataset with more than 4.2 million unified production and consumption power values recorded every 30 s guarantees the overall prediction accuracy of the system. Performance metrics used to evaluate the prediction accuracy are the mean bias error, the mean square error, the convergence time of the prediction system, the test performance, and the train mean performance. Test results indicate that the predicted unified electric power production and consumption closely resembles the unified electric power measured values.

Unmanned Vehicles' Placement Optimisation for Internet of Things and Internet of Unmanned Vehicles.

Currently, the use of unmanned vehicles, such as drones, boats and ships, in monitoring tasks where human presence is difficult or even impossible raises several issues. Continuous efforts to improve the autonomy of such vehicles have not solved all aspects of this issue. In an Internet of Unmanned Vehicles (IoUV) environment, the idea of replacing the static wireless infrastructure and reusing the mobile monitoring nodes in different conditions would converge to a dynamic solution to assure data collection in areas where there is no infrastructure that ensures Internet access. The current paper fills a significant gap, proposing an algorithm that optimises the positions of unmanned vehicles such that an ad hoc network is deployed to serve specific wireless sensor networks that have no other Internet connectivity (hilly/mountainous areas, Danube Delta) and must be connected to an Internet of Things (IoT) ecosystem. The algorithm determines the optimum positions of UV nodes that decrease the path losses below the link budget threshold with minimum UV node displacement compared to their initial coordinates. The algorithm was tested in a rural scenario and 3rd Generation Partnership Project (3GPP), free space and two-ray propagation models. The paper proposes another type of network, a Flying and Surface Ad Hoc Network (FSANET), a concept which implies collaboration and coexistence between unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) and several use cases that motivate the need for such a network.