由曹菁菁副教授、陈雨佳硕士研究生、曹小华教授,王强副教授、华中科技大学王博老师、杜杰鹏和温志鹏硕士研究生合作的学术论文《SP2LSTM: a patch learning-based electrical load forecasting for container terminal》,于2023年8月被SCI期刊《Neural Computing and Applications》(IF=6)收录发表。
《Neural Computing and Applications》是国际上神经计算与应用领域知名SCI期刊,主要发表神经计算及遗传算法、模糊逻辑和神经模糊系统等相关技术的实际应用领域的原创研究和其他信息。
研究背景:
随着港口和海洋贸易的兴起,周边环境不可避免地被航运活动影响,负荷预测是减少港口污染、优化港口能耗结构的基础。以往的负荷预测虽然与港口能源预测有关,但它们要么预测船舶能源,要么预测碳排放,并没有考虑通过历史电力数据直接预测未来短期港口用电量。
论文简介:
针对短期电力负荷预测设计了一种在补丁学习框架下针对港口负荷的短期预测方法。首先,应用奇异谱分析分别获得去噪特征和噪声特征;然后,采用基于长短期记忆网络的补丁学习模型来解决这种时间序列预测问题。将LSTM网络和BiLSTM网络分别作为去噪和带噪数据处理的全局模型,选择卷积神经网络作为patch模型。此外,设计了一种端点检测策略,用于自适应识别补丁的位置。在一个真实的中国集装箱码头装载数据集上对该模型的性能进行了测试和验证。实验结果表明,与现有的负荷预测模型相比,该方法在7个评价指标上都具有最好的性能。
Designing a short-term forecasting approach aimed at port load under the framework of patch learning for short-term electricity load forecasting. Firstly, singular spectrum analysis is applied to obtain denoised and noise features, respectively; then, a patch learning model based on the long short-term memory network is employed to address such a time-series forecasting problem. LSTM network and BiLSTM are considered as the global models to process denoised and noisy data, respectively, and convolutional neural network is selected as the patch model. Furthermore, an endpoint detection strategy is designed for adaptively identifying the positions of patches. The performance of the proposed model is tested and verified on a real Chinese container terminal load dataset.Experimental results show that the proposed approach, compared with state-of-the-art load forecasting models, has the greatest performance with respect to seven evaluation criteria.
主要完成研究生简介:陈雨佳,男,武汉理工大学交通与物流工程学院硕士研究生,主要研究领域为港口能源预测,研究成果发表在《Neural Computing and Applications》。