Communication-Aware Deep Learning Models for Real-Time Solar Energy Forecasting in Intelligent Power Networks

Precise solar power forecasting is critical for the stability and efficiency of modern intelligent power networks. However, the reliability of these forecasts is often compromised by communication network impairments, such as latency and packet loss, occurring between solar plants and control centers. This paper proposes a Communication-Aware Long Short-Term Memory (Comm-Aware LSTM) framework designed to integrate network-state information directly into the forecasting process. We model the system using a distributed communication topology consisting of solar plants, edge nodes, and cloud-based control centers. Our experimental results demonstrate that the proposed model significantly outperforms traditional Baseline LSTM architectures under varying network conditions. Specifically, the Comm-Aware LSTM exhibits superior training convergence, achieving lower Mean Squared Error (MSE) while maintaining a negligible computational overhead—adding only 1.6 more trainable parameters and approximately 0.3 of inference latency. Correlation analysis further reveals that by explicitly accounting for latency-induced errors, the model provides robust predictions even in high-latency scenarios 0.5s. This research confirms that communication-aware deep learning architectures are essential for the next generation of resilient, edge-integrated smart grids.