Qi Xinjing, Wang Huan, Ji Yubo, Li Yuan, Luo Xuguang, Nie Rongshan, Liang Xiaoyu
College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou, Zhejiang, China.
Ningbo China Resources Xingguang Gas Co Ltd, Ningbo, Zhejiang, China.
PeerJ Comput Sci. 2024 Feb 29;10:e1890. doi: 10.7717/peerj-cs.1890. eCollection 2024.
As the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of short-term natural gas demand poses a significant challenge within this context, as precise forecasts have important implications for gas dispatch and pipeline safety. The incorporation of intelligent algorithms into prediction methodologies has resulted in notable progress in recent times. Nevertheless, certain limitations persist. However, there exist certain limitations, including the tendency to easily fall into local optimization and inadequate search capability. To address the challenge of accurately predicting daily natural gas loads, we propose a novel methodology that integrates the adaptive particle swarm optimization algorithm, attention mechanism, and bidirectional long short-term memory (BiLSTM) neural networks. The initial step involves utilizing the BiLSTM network to conduct bidirectional data learning. Following this, the attention mechanism is employed to calculate the weights of the hidden layer in the BiLSTM, with a specific focus on weight distribution. Lastly, the adaptive particle swarm optimization algorithm is utilized to comprehensively optimize and design the network structure, initial learning rate, and learning rounds of the BiLSTM network model, thereby enhancing the accuracy of the model. The findings revealed that the combined model achieved a mean absolute percentage error (MAPE) of 0.90% and a coefficient of determination (R) of 0.99. These results surpassed those of the other comparative models, demonstrating superior prediction accuracy, as well as exhibiting favorable generalization and prediction stability.
随着经济持续发展和技术进步，社会对环境友好型生态系统的需求日益增加。因此，以温室气体排放量极少而闻名的天然气已被广泛用作清洁能源替代品。在这种背景下，准确预测短期天然气需求构成了一项重大挑战，因为精确的预测对天然气调度和管道安全具有重要意义。近年来，将智能算法纳入预测方法已取得显著进展。然而，仍存在某些局限性。具体而言，包括容易陷入局部优化以及搜索能力不足等问题。为应对准确预测每日天然气负荷的挑战，我们提出了一种新颖的方法，该方法整合了自适应粒子群优化算法、注意力机制和双向长短期记忆（BiLSTM）神经网络。第一步是利用BiLSTM网络进行双向数据学习。在此之后，采用注意力机制计算BiLSTM中隐藏层的权重，特别关注权重分布。最后，利用自适应粒子群优化算法对BiLSTM网络模型的网络结构、初始学习率和学习轮数进行全面优化和设计，从而提高模型的准确性。研究结果表明，该组合模型的平均绝对百分比误差（MAPE）为0.90%，决定系数（R）为0.99。这些结果超过了其他对比模型，展示出卓越的预测准确性，以及良好的泛化能力和预测稳定性。
