Hydropower generation is influenced by various factors such as precipitation, temperature, and installed capacity, with hydrometeorological factors exhibiting significant temporal variability. This study proposes a hydropower generation forecasting method based on Transformer and SE-Attention for different provinces. In the model, the outputs of the Transformer and SE-Attention modules are fed into an LSTM layer to capture long-term data dependencies. The SE-Attention module is reintroduced to enhance the model’s focus on important temporal features, and a linear layer maps the hidden state of the last time step to the final output. The proposed Transformer-LSTM-SE model was tested using provincial hydropower generation data from Yunnan, Sichuan, and Chongqing. The experimental results demonstrate that this model achieves high accuracy and stability in medium- and long-term hydropower forecasting at the provincial level, with an average accuracy improvement of 33.79% over the LSTM model and 24.30% over the Transformer-LSTM model.

The complementary operation of hydropower and photovoltaic power, aimed at meeting real-time demand, has led to frequent adjustments in power generation, causing significant fluctuations in hydrological systems and adversely affecting fish reproduction. The traditional hydrological regime alteration assessment index is based on index of hydrologic alternation (IHA) and mostly focuses on annual and daily runoff alterations. This study proposes a new set of indicators considering the characteristics of subdaily hydrological regime alterations, including magnitude, rate of change, duration, frequency, and timing. Using the hourly outflow from Longyangxia, an analysis of indicator redundancy was conducted. The alteration of the indicators before and after hydropower and photovoltaic operation was then analyzed using the cumulative probability distribution curve. Additionally, a concentration index was introduced to analyze the variations in hydrological impacts during different months. The results show that the hydro–photovoltaic complementary operation changed the subdaily natural flow regime, significantly increasing the rate of flow increase or decrease and the duration, with most indexes increasing by more than 100% compared with the natural flow regime. Furthermore, the concentration values of the indexes for the hydro–photovoltaic complementary operation were less than 10, indicating a more significant impact on the subdaily flow regime throughout the year. This research provides crucial data for mitigating ecological impacts under multi-source complementary scheduling.