Accurate prediction of heating loads in district heating systems is essential for the implementation of demand-driven heating. This work presents a novel heating load prediction model that is particularly suitable for complex multi-user buildings. The input characteristics of the model are established through the heat transfer mechanism, considering factors such as the cumulative impact of outdoor temperature and user demand (indoor temperature). The specific form of the heating load function is determined using the MLR-PSO (Multiple Linear Regression-Particle Swarm Optimization) method. Only the indoor and outdoor temperatures need to be provided for the model to calculate future heating loads. Practical engineering tests demonstrated that the model achieved normalized mean bias errors of daily loads between 4.98 % and 5.54 % across different heating seasons, with a minimum annual relative deviation of 0.75 % for annual loads. Additionally, the model helps guide the operation of heating systems. For example, during the 2021–2022 heating season, setting the target indoor temperature at 18 °C reduced weekly energy consumption by 15.3 % compared to the previous season. This approach may be employed to construct a simple load model for existing heating systems to accurately predict both short-term and long-term loads, providing valuable insights into the management and control of heating systems.

中文翻译：

---

基于混合机制和数据驱动方法的建筑群集中供热简单负荷模型


准确预测区域供热系统的热负荷对于实施需求驱动供暖至关重要。这项工作提出了一种新颖的热负荷预测模型，特别适合复杂的多用户建筑。模型的输入特性通过传热机制建立，考虑室外温度和用户需求（室内温度）的累积影响等因素。热负荷函数的具体形式采用MLR-PSO（多重线性回归-粒子群优化）方法确定。只需为模型提供室内和室外温度即可计算未来的热负荷。实际工程测试表明，该模型在不同采暖季日负荷归一化平均偏差误差在4.98%~5.54%之间，年负荷相对偏差最小为0.75%。此外，该模型还有助于指导供暖系统的运行。例如，在2021-2022年供暖季，将室内目标温度设定为18℃，与上一季相比，每周能耗可减少15.3%。这种方法可用于为现有供暖系统构建简单的负荷模型，以准确预测短期和长期负荷，为供暖系统的管理和控制提供有价值的见解。