Shuo Chen

Short-term load forecasting (STLF) is an essential component of smart grids, enabling power departments to anticipate grid operations in advance, thereby controlling electricity usage in a timely manner, allocating power resources reasonably, and ensuring the quality and reliability of grid services. In the field of electric load forecasting, existing prediction models perform poorly on load data with frequent fluctuations and have issues with prediction lag. To address these issues, this paper proposes an improved TimesNet model based on wavelet decomposition, called WaveTimes. Firstly, the model uses wavelet decomposition to decompose load data, obtaining sequences with smaller mutation amplitudes and weaker autocorrelation. Secondly, a feature extraction module is introduced, which uses Fourier transformation and computer vision models for periodic analysis, effectively capturing periodic changes in load data across different frequency domains. Finally, a residual connection and prediction module are used to complete the forecasting task. This paper evaluates the proposed method on public datasets and load data from a certain province in China, showing significant improvements compared to the baseline. The model can more effectively support relevant departments in load control and demand response, contributing to the construction of smart grids.

Understanding electrical load profiles and detecting anomaly behaviors are important to the smart grid system. However, current load identification and anomaly analysis are based on static analysis, and less consideration is given to anomaly findings under load change conditions. This paper proposes a deep variational autoencoder network (DVAE) for load profiles, along with anomaly analysis services, and introduces auto-time series data updating strategies based on sliding window adjustment. DVAE can help reconstruct the load curve and measure the difference between the original and the newer curve, whose measurement indicators include reconstruction probability and Pearson similarity. Meanwhile, the design of the sliding window strategy updates the data and DVAE model in a time-series manner. Experiments were carried out based on datasets from the U.S. Department of Energy and from Southeast China. The results showed that the proposed services could result in a 5% improvement in the AUC value, which helps to identify the anomaly behavior.

In this paper, a neural network model called Long Short-Term Temporal Convolutional Network (LST-TCN) model is proposed for short-term load forecasting. This model refers to the 1-D fully convolution network, causal convolution, and void convolution structure. In the convolution layer, a residual connection layer is added. Additionally, the model makes use of two networks to extract features from long-term data and periodic short-term data, respectively, and fuses the two features to calculate the final predicted value. Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN) are used as comparison algorithms to train and forecast 3 h, 6 h, 12 h, 24 h, and 48 h ahead of daily electricity load together with LST-TCN. Three different performance metrics, including pinball loss, root mean squared error (RMSE), and mean absolute error (RASE), were used to evaluate the performance of the proposed algorithms. The results of the test set proved that LST-TCN has better generalization effects and smaller prediction errors. The algorithm has a pinball loss of 1.2453 for 3 h ahead forecast and a pinball loss of 1.4885 for 48 h ahead forecast. Generally speaking, LST-TCN has better performance than LSTM, TCN, and other algorithms.