Modeling coordinated operation of multiple hydropower reservoirs at a continental scale using artificial neural network: the case of Brazilian hydropower system

Abstract

Reservoirs considerably affect river streamflow and need to be accurately represented in environmental impact studies. Modeling reservoir outflow represents a challenge to hydrological studies since reservoir operations vary with flood risk, economic and demand aspects. The Brazilian Interconnected Energy System (SIN) is an example of a unique and complex system of coordinated operation composed by more than 160 large reservoirs. We proposed and evaluated an integrated approach to simulate daily outflows from most of the SIN reservoirs (138) using an Artificial Neural Network (ANN) model, distinguishing run-of-the-river and storage reservoirs and testing cases whether outflow and level data were available as input. Also, we investigated the influence of the proposed input features (14) on the simulated outflow, related to reservoir water balance, seasonality, and demand. As a result, we verified that the outputs of the ANN model were mainly influenced by local water balance variables, such as the reservoir inflow of the present day and outflow of the day before. However, other features such as the water level of 4 large reservoirs that represent different regions of the country, which infers about hydropower demand through water availability, seemed to influence to some extent reservoirs outflow estimates. This result indicates advantages in using an integrated approach rather than looking at each reservoir individually. In terms of data availability, it was tested scenarios with (WITH_Qout) and without (NO_Qout and SIM_Qout) observed outflow and water level as input features to the ANN model. The NO_Qout model is trained without outflow and water level while the SIM_Qout model is trained with all input features, but it is fed with simulated outflows and water levels rather than observations. These 3 ANN models were compared with two simple benchmarks: outflow is equal to the outflow of the day before (STEADY) and the outflow is equal to the inflow of the same day (INFLOW). For run-of-the-river reservoirs, an ANN model is not necessary as outflow is virtually equal to inflow. For storage reservoirs, the ANN estimates reached median Nash-Sutcliffe efficiencies (NSE) of 0.91, 0.77 and 0.68 for WITH_, NO_ and SIM_Qout respectively, compared to a median NSE of 0.81 and 0.29 for the STEADY and INFLOW benchmarks respectively. In conclusion, the ANN models presented satisfactory performances: when outflow observations are available, WITH_Qout model outperforms STEADY; otherwise, NO_Qout and SIM_Qout models outperform INFLOW.

Machine Learning Assisted Reservoir Operation Model for Long‐Term Water Management Simulation

“…The ML-based techniques may also be used to derive operational rule curves which can then be used as inputs within RMMs (Coerver et al 2018). ML techniques such as artificial neural network (ANN; Brêda et al 2021;Zhang et al 2018), recurrent neural network (RNN; Yang et al 2019;Zhang et al 2019), long short term memory (LSTM; Zhang et al 2018), support vector machine, and classification and regression tree (Yang et al 2016) have been utilized in several reservoir operation applications, mostly focusing on the prediction of reservoir release. However, while ML-based models may yield good performance in real-time or short-term release forecasting (Yang et al 2019), given their purely data-driven nature, it remains unclear if they can also be used to simulate other reservoir functions (e.g., storage) to support long-term water resource planning.…”

“…ML techniques such as artificial neural network (ANN; Brêda et al. 2021; Zhang et al. 2018), recurrent neural network (RNN; Yang et al.…”

Impact of precipitation extremes on energy production across the São Francisco river basin

“…The ONS is the entity responsible for coordinating and controlling the operation of electricity generation and transmission facilities in the NIS, as well as planning the operation of the country's isolated systems (ONS, 2023b). The operational strategy of the NIS as a whole takes precedence over the individual strategies of HPPs, allowing for the dispatch of energy to regions with low-capacity reservoirs and avoiding the use of local thermal power plants (BRÊDA et al, 2021).…”