There is a huge interest worldwide related to continuously increasing the use of renewable energy sources (RES) for electricity generation. Romania, at this moment, even though it has to attain a share of 30.7% of RES from total energy consumption by 2030, does not have any major investment project of this kind in the near future. Photovoltaic (PV) is one of the most promising technologies, with decreasing prices for PV panels but with the disadvantage of large, needed surfaces. This study presents a solution to install PV panels where there is a need for electricity, in a large city, by using the surface of a reservoir. “Lacul Morii” Reservoir in Bucharest is the choice for the case study. The insolation and the possibility to install floating PV, as well as electricity generation, benefits for water quality and carbon dioxide (CO₂) emissions reduction are assessed, and even the installation of charging stations for electric bikes and cars. The results are very promising, and the main conclusion is that, after its realization, the floating photovoltaic (FPV) plant on “Lacul Morii” Reservoir will be a source of clean electricity and a demonstration project on how to benefit from solar energy to produce electricity in large cities where there are reservoirs.

An existing Romanian hydro system (two reservoirs/peak hydropower plants), where the addition of a pumped storage plant with a weekly emptying/filling cycle was planned, was selected as a case study. For the main upstream reservoir/hydropower plant, an operational policy with a monthly time step was derived using a stochastic dynamic programming model. The optimal weekly scheduling problem of the whole system was solved by a genetic algorithm-based model. The monetary income maximization, by 2014 market energy prices for produced/consumed energy, was chosen as the objective function; any gain from ancillary services was ignored. An original methodology for coupling the monthly and weekly time-step results was used to obtain the annual performance estimation within the mean hydrological year conditions. At that level, the inclusion of the pumped storage plant would lead to a gain to nearly double the annual performance of the existing hydro system.

Climate change represents one of the major challenges of our century with great potential to alter water quality, and hence, find suitable solutions becomes a must. Stanca–Costesti reservoir is one of the most important in Romania and one of the most affected by the hydrologic variability. The studies regarding the trophic state of this reservoir are few, even if there are some environmental issues in its hydrological basin that could be further investigated. According to the National Administration “Apele Romane” (ANAR) yearly reports, the Stanca–Costesti reservoir is, from the trophic state point of view, an oligotrophic lake. The current research is based on chemical and some biological data collected over 10 years (ANAR) for the trophic state of the Stanca–Costesti reservoir, using the Carlson index. The research investigates the hydrological data and spans over 10 years that were classified into three categories, namely: wet year, normal year, and dry year and the influences generated by the contrasting weather (flow and temperature changes) on the trophic state of the lake. The research findings show that the trophic state of the lake is directly influenced by the hydrological variability, namely evolving to a hypertrophic status due to concentrations of nutrients. Moreover, over the years, according to ANAR data, the water quality in the reservoir alternated. Hence, at times, the quality of the water was poor, with possible negative influences on water usage. As a consequence, we proposed that the water quality be verified monthly, and this should be done by means of a more reliable method, such as a multiparameter index or multicriteria analysis.

In the hydropower sector, accurate estimation of short-term reservoir inflows is an essential element to ensure efficient and safe management of water resources. Short-term forecasting supports the optimization of energy production, prevention of uncontrolled water discharges, planning of equipment maintenance, and adaption of operational strategies. In the absence of data on topography, vegetation, and basin characteristics (required in distributed or semi-distributed models), data-driven approaches can serve as effective alternatives for inflow prediction. This study proposes a novel hybrid approach that reverses the conventional LSTM (Long Short-Term Memory)—ARIMA (Autoregressive Integrated Moving Average) sequence: LSTM is first used to capture nonlinear hydrological patterns, followed by ARIMA to model residual linear trends.The model was calibrated using daily inflow data in the Izvorul Muntelui–Bicaz reservoir in Romania from 2012 to 2020, tested for prediction on the day ahead in a repetitive loop of 365 days corresponding to 2021 and further evaluated through multiple seven-day forecasts randomly selected to cover all 12 months of 2021. For the tested period, the proposed model significantly outperforms the standalone LSTM, increasing the R² from 0.93 to 0.96 and reducing RMSE from 9.74 m³/s to 6.94 m³/s for one-day-ahead forecasting. For multistep forecasting (84 values, randomly selected, 7 per month), the model improves R² from 0.75 to 0.89 and lowers RMSE from 18.56 m³/s to 12.74 m³/s. Thus, the hybrid model offers notable improvements in multi-step forecasting by capturing both seasonal patterns and nonlinear variations in hydrological data. The approach offers a replicable data-driven solution for inflow prediction in reservoirs with limited physical data.