The available modelling data shortage issue makes it difficult to guarantee the performance of data-driven building energy prediction (BEP) models for both the newly built buildings and existing information-poor buildings. Both knowledge transfer learning (KTL) and data incremental learning (DIL) can address the data shortage issue of such buildings. For new building scenarios with continuous data accumulation, the performance of BEP models has not been fully investigated considering the data accumulation dynamics. DIL, which can learn dynamic features from accumulated data adapting to the developing trend of new building time-series data and extend BEP model’s knowledge, has been rarely studied. Previous studies have shown that the performance of KTL models trained with fixed data can be further improved in scenarios with dynamically changing data. Hence, this study proposes an improved transfer learning cross-BEP strategy continuously updated using the coarse data incremental (CDI) manner. The hybrid KTL-DIL strategy (LSTM-DANN-CDI) uses domain adversarial neural network (DANN) for KLT and long short-term memory (LSTM) as the Baseline BEP model. Performance evaluation is conducted to systematically qualify the effectiveness and applicability of KTL and improved KTL-DIL. Real-world data from six-type 36 buildings of six types are adopted to evaluate the performance of KTL and KTL-DIL in data-driven BEP tasks considering factors like the model increment time interval, the available target and source building data volumes. Compared with LSTM, results indicate that KTL (LSTM-DANN) and the proposed KTL-DIL (LSTM-DANN-CDI) can significantly improve the BEP performance for new buildings with limited data. Compared with the pure KTL strategy LSTM-DANN, the improved KTL-DIL strategy LSTM-DANN-CDI has better prediction performance with an average performance improvement ratio of 60%.

可用的建模数据短缺问题使得难以保证新建建筑和现有信息贫乏建筑的数据驱动的建筑能源预测（BEP）模型的性能。知识转移学习（KTL）和数据增量学习（DIL）都可以解决此类建筑的数据短缺问题。对于具有连续数据积累的新建筑场景，考虑到数据积累动态，BEP 模型的性能尚未得到充分研究。DIL能够从积累的数据中学习动态特征，适应新建建筑时间序列数据的发展趋势，扩展BEP模型的知识，但目前的研究很少。之前的研究表明，使用固定数据训练的KTL模型的性能在数据动态变化的场景中可以进一步提高。因此，本研究提出了一种改进的迁移学习跨BEP策略，使用粗数据增量（CDI）方式不断更新。混合 KTL-DIL 策略 (LSTM-DANN-CDI) 使用域对抗神经网络 (DANN) 进行 KLT，并使用长短期记忆 (LSTM) 作为基线 BEP 模型。进行绩效评估是为了系统地验证 KTL 和改进的 KTL-DIL 的有效性和适用性。采用来自 6 种类型 6 种 36 栋建筑的真实数据来评估 KTL 和 KTL-DIL 在数据驱动的 BEP 任务中的性能，考虑模型增量时间间隔、可用目标和源建筑数据量等因素。与 LSTM 相比，结果表明 KTL（LSTM-DANN）和提出的 KTL-DIL（LSTM-DANN-CDI）可以显着提高数据有限的新建筑的 BEP 性能。与纯KTL策略LSTM-DANN相比，改进的KTL-DIL策略LSTM-DANN-CDI具有更好的预测性能，平均性能提升率为60%。