Ullah Irshad, Muhammad Hasanat Syed, Aurangzeb Khursheed, Alhussein Musaed, Rizwan Muhammad, Anwar Muhammad Shahid
Electrical Engineering Kohat, University of Engineering & Technology Peshawar, Peshawar, KPK, Pakistan.
Department of Computer Engineering, King Saud University, Riyadh, Saudi Arabia.
PeerJ Comput Sci. 2023 Sep 15;9:e1487. doi: 10.7717/peerj-cs.1487. eCollection 2023.
Precise short-term load forecasting (STLF) plays a crucial role in the smooth operation of power systems, future capacity planning, unit commitment, and demand response. However, due to its non-stationary and its dependency on multiple cyclic and non-cyclic calendric features and non-linear highly correlated metrological features, an accurate load forecasting with already existing techniques is challenging. To overcome this challenge, a novel hybrid technique based on long short-term memory (LSTM) and a modified split-convolution (SC) neural network (LSTM-SC) is proposed for single-step and multi-step STLF. The concatenating order of LSTM and SC in the proposed hybrid network provides an excellent capability of extraction of sequence-dependent features and other hierarchical spatial features. The model is evaluated by the Pakistan National Grid load dataset recorded by the National Transmission and Dispatch Company (NTDC). The load data is pre-processed and multiple other correlated features are incorporated into the data for performance enhancement. For generalization capability, the performance of LSTM-SC is evaluated on publicly available datasets of American Electric Power (AEP) and Independent System Operator New England (ISO-NE). The effect of temperature, a highly correlated input feature, on load forecasting is investigated either by removing the temperature or adding a Gaussian random noise into it. The performance evaluation in terms of RMSE, MAE, and MAPE of the proposed model on the NTDC dataset are 500.98, 372.62, and 3.72% for multi-step while 322.90, 244.22, and 2.38% for single-step load forecasting. The result shows that the proposed method has less forecasting error, strong generalization capability, and satisfactory performance on multi-horizon.
精确的短期负荷预测（STLF）在电力系统的平稳运行、未来容量规划、机组组合以及需求响应中起着至关重要的作用。然而，由于其非平稳性，以及对多个周期性和非周期性日历特征以及高度相关的非线性计量特征的依赖性，使用现有技术进行准确的负荷预测具有挑战性。为了克服这一挑战，提出了一种基于长短期记忆（LSTM）和改进的分裂卷积（SC）神经网络（LSTM-SC）的新型混合技术，用于单步和多步STLF。在所提出的混合网络中，LSTM和SC的连接顺序提供了出色的提取序列相关特征和其他分层空间特征的能力。该模型通过国家输电和调度公司（NTDC）记录的巴基斯坦国家电网负荷数据集进行评估。对负荷数据进行预处理，并将多个其他相关特征纳入数据以提高性能。为了评估泛化能力，在公开可用的美国电力公司（AEP）和新英格兰独立系统运营商（ISO-NE）数据集上对LSTM-SC的性能进行了评估。通过去除温度或向其中添加高斯随机噪声，研究了高度相关的输入特征温度对负荷预测的影响。在所提出的模型在NTDC数据集上的RMSE、MAE和MAPE方面的性能评估中，多步负荷预测分别为500.98、372.62和3.72%，单步负荷预测分别为322.90、244.22和2.38%。结果表明，所提出的方法具有较小的预测误差、较强的泛化能力以及在多步预测方面令人满意的性能。
