Climate Aware Deep Neural Networks (CADNN) for wind power simulation

Wind power forecasting plays a vital role in modern energy systems by facilitating the integration of renewable energy sources into the power grid. Accurate prediction of wind energy output is essential for managing the inherent intermittency of wind power, optimizing energy dispatch, and maintaining grid stability. This paper proposes the use of Deep Neural Network (DNN)-based predictive models that leverage climate datasets—including wind speed, atmospheric pressure, temperature, and other meteorological variables—to enhance the accuracy of wind power simulations.In particular, we focus on the Coupled Model Intercomparison Project (CMIP) datasets, which provide long-term climate projections, as inputs for training the DNN models. These models are designed to capture the complex nonlinear relationships between CMIP-based climate data and actual wind power generation at wind farms located in Germany. We evaluate several DNN architectures, including the Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM) networks, and Transformer-enhanced LSTM m̃odels, to identify the most effective configuration for climate-aware wind power simulation.To support this implementation, we develop a modular Python package (CADNN) that facilitates multiple tasks, including statistical analysis of climate variables, data visualization, preprocessing, DNN training, and performance evaluation. We demonstrate that DNN models, when integrated with climate data, significantly improve forecasting accuracy. This climate-aware modeling framework provides a deeper understanding of the time-dependent climatic patterns influencing wind power generation and is adaptable to other geographical regions.