This paper addresses the estimation of household communities' overall energy usage and solar energy production, considering different prediction horizons. Forecasting the electricity demand and energy generation of communities can help enrich the information available to energy grid operators to better plan their short-term supply. Moreover, households will increasingly need to know more about their usage and generation patterns to make wiser decisions on their appliance usage and energy-trading programs. The main issues to address here are the volatility of load consumption induced by the consumption behaviour and variability in solar output influenced by solar cells specifications, several meteorological variables, and contextual factors such as time and calendar information. To address these issues, we propose a predicting approach that first considers the highly influential factors and, second, benefits from an ensemble learning method where one Gradient Boosted Regression Tree algorithm is combined with several Sequence-to-Sequence LSTM networks. We conducted experiments on a public dataset provided by the Ausgrid Australian electricity distributor collected over three years. The proposed model's prediction performance was compared to those by contributing learners and by conventional ensembles. The obtained results have demonstrated the potential of the proposed predictor to improve short-term multi-step forecasting by providing more stable forecasts and more accurate estimations under different day types and meteorological conditions.

The rising demand for sustainable energy requires to identify the sites for photovoltaic systems with the best performance. This paper tackles the question of feasibility of photovoltaic power plants at high altitude. A direct comparison between an alpine and an urban area site is conducted in the south of Austria. Two low-cost automatic photovoltaic power measurement devices with dual-axis sun tracking and maximum power point tracking are deployed at two test sites. The system periodically performs a scan over the southern semihemisphere and executes maximum power point adjustment in order to assess the performance for a given direction. The gathered data shows a higher photovoltaic power yield in the higher altitude test site. Furthermore, the high altitude photovoltaic power as a function of azimuth and elevation angle appears to be not only higher but also more flat than in lower altitudes. This indicates a lower power loss in case of deviation from the optimal solar angles. The results show that even on low-cost hardware a difference in photovoltaic power can be observed, even though in this experiment it amounts to less than 5% increase of peak power in higher altitudes. However, the measured peak powers on the mountain are more stable and therefore closer to a constant level than the heavily fluctuating peak power values at the low altitude site. Additionally, a slight shift in optimal elevation angles between altitudes can be observed, as the optimum angle turns out to be lower on the high altitude site. This angle shift could be caused by snow reflections on the mountainous test site.

Photovoltaic (PV) systems have received much attention in recent years due to their ability of efficiently converting solar power into electricity, which offers important benefits to the environment. PV systems in regions with high solar irradiation can produce a higher output but the temperature affects their performance. This paper presents a study on the effect of cold climate at high altitude on the PV system output. We report a comparative case study, which presents measurement results at two distinct sites, one at a height of 612 meters and another one at a mountain site at a height of 1764 meters. This case study applies the maximum power point tracking (MPPT) technique in order to determine maximum power from the PV panel at different azimuth and altitude angles. We used an Arduino system to measure and display the attributes of the PV system. The measurement results indicate an increased efficiency of 42% for PV systems at higher altitude.