This study examines how strongly demand-load prediction and adaptive load control in photovoltaic heating systems rely on computationally intensive artificial neural network (ANN) models. To streamline the computational workflow and reduce runtime resource requirements, we propose an ANN load-prediction-and-validation algorithm coupled with a corresponding offline control strategy. By optimizing the algorithmic structure and shifting heavy computations away from online execution, the proposed method substantially lowers the operational computational burden while preserving predictive accuracy, enabling efficient real-time load prediction and adaptive control. Based on a modelling study of a monocrystalline PV string comprising two 330 W modules connected in series, the proposed simplified prediction method produced annual cumulative energy outputs of 139.9, 391.2, 320.2, 251.4, and 154.1 kW·h across the five irradiance intervals [200, 400), [400, 600), [600, 800), [800, 1000), and [1000, ∞), respectively. Compared with a conventional artificial neural network (ANN)-based prediction approach, the corresponding deviations were 1.1%, −0.1%, 0.0%, 0.1%, and −0.4%, the total annual cumulative energy outputs across all intervals was 1256.7 kW·h with a mean deviation of −0.07%. Moreover, the simplified load-control strategy required only 3.57% of the computational resources consumed by the conventional ANN method. In addition, the method rapidly reallocates computational resources in response to changes in real-time input data, thereby minimizing redundant computation. Overall, the results demonstrate that the proposed framework markedly reduces computational complexity without sacrificing accuracy, providing an effective alternative to traditional ANN-based solutions and facilitating the practical deployment of photovoltaic heating systems.
Xu et al. (Thu,) studied this question.