In this paper, we investigate the robustness of Feed Forward Neural Network (FFNN) ensemble models applied to quarterly time series forecasting tasks, by comparing their prediction ability with that of Seasonal Auto-regressive Integrated Moving Average (SARIMA) models. We obtained adequate SARIMA models which required statistical knowledge and considerable effort. On the other hand, FFNN ensemble models were readily constructed from a single FFNN template, and they produced competitive forecasts, at the level of well-constructed SARIMA models. The single template approach for adapting FFNN ensembles to multiple time series datasets can be an economic and sensible alternative if fitting individual models for each time series turns out to be very time consuming. Additionally, FFNN ensembles were able to produce accurate interval estimations, in addition to good point forecasts.

This paper addresses the involvement of Electronic Engineering students in the development of an electric micro smart grid equipped with renewable energy sources and storage components through the execution of their final engineering projects as part of the regular curriculum. First, the pre-defined overall target smart grid is introduced, followed by its current state of development. Then, the context of the students' participation is presented, followed by the description of their input as modular contributions to a sequentially conceived process leading to the final target system. The conclusions stress the learning-by-doing feature of the students' involvement, that not only helps to consolidate the theoretical, methodological and practical skills previously acquired but also puts the students in contact with new technologies and engineering problems and systems, and provides abilities regarding teamwork and participation in relatively long-term project.