Nowadays electricity load forecasting is important to further minimize the cost of day-ahead energy market. Load forecasting can help utility operators for the efficient management of a demand response program. Forecasting of electricity load demand with higher accuracy and efficiency can help utility operators to design reasonable operational planning of generation units. But solving the problem of load forecasting is a challenging task since electricity load is affected by previous history load, several exogenous external factors (i.e., weather variables, social variables, working day or holiday), time of day, and season of the year. To solve the problem of short-term load forecasting (STLF) and further improve the forecasting accuracy, in this paper we have proposed a novel hybrid STLF model with a new signal decomposition and correlation analysis technique. To this end, load demand time series is decomposed into some regular low frequency components using improved empirical mode decomposition (IEMD). To compensate for the information loss during signal decomposition, we have incorporated the effect of exogenous variables by performing correlation analysis using T-Copula. From the T-Copula analysis, peak load indicative binary variable is derived from value at risk (VaR) to improve the load forecasting accuracy during peak time. The data obtained from IEMD and T-Copula is applied to deep belief network for predicting the future load demand of specific time. The proposed data driven method is validated on real time data from the Australia and the United States of America. The performance of proposed load forecasting model is evaluated in terms of mean absolute percentage error (MAPE) & root mean square error (RMSE). Simulation results verify that, the proposed model provides a significant decrease in MAPE and RMSE values compared to traditional empirical mode decomposition based electricity load forecasting.

短期电力负荷预测在电网安全运行和制定合理调度计划方面发挥着重要作用。为了提高电力负荷时间序列预测的准确度,提出了一种由完整自适应噪声集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)和基于注意力机制的长短期记忆神经网络(long short-term memory network based on attention mechanism, LSTM-Attention)相结合的短期电力负荷预测模型。完整自适应噪声集成经验模态分解有效地将负荷时间序列分解成多个层次规律平稳的本征模态分量,并通过神经网络模型预测极大值,结合镜像延拓方法抑制边界效应,提高分解精度,同时基于注意力机制的长短期记忆神经网络自适应地提取电力负荷数据输入特征并分配权重进行预测,最后各预测模态分量叠加重构后获得最终预测结果。通过不同实际电力负荷季节数据分别进行实验,并与其他电力负荷预测模型结果分析进行比较,验证了该预测方法在电力负荷预测精度方面具有更好的性能。

Short-term power load forecasting plays an important role in the safe operation of power grid and the formulation of reasonable dispatching plan. In order to improve the accuracy of power load time-series forecasting, a short-term power load forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and short-term memory neural network based on attention mechanism (LSTM-Attention) is proposed in this paper. The complete ensemble empirical mode decomposition with adaptive noise effectively decomposes the load time series into multiple levels of regular and stable eigenmode components, and suppresses the boundary effect through the neural network model prediction maximum combined with the image continuation method to improve the decomposition accuracy. At the same time, the long short-term memory neural network based on attention mechanism adaptively extracts the input characteristics of power load data and assigns weights for prediction. Finally, the final prediction results are obtained after superposition and reconstruction of each prediction modal component. Experiments are carried out on different seasonal data of actual power load, and the results of other power load forecasting models are analyzed and compared to verify that the forecasting method has better performance in power load forecasting accuracy.

Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a high prediction capacity of the model, which is the ability to capture precise long-range dependency coupling between output and input efficiently. Recent studies have shown the potential of Transformer to increase the prediction capacity. However, there are several severe issues with Transformer that prevent it from being directly applicable to LSTF, including quadratic time complexity, high memory usage, and inherent limitation of the encoder-decoder architecture. To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a ProbSparse self-attention mechanism, which achieves O(L log L) in time complexity and memory usage, and has comparable performance on sequences' dependency alignment. (ii) the self-attention distilling highlights dominating attention by halving cascading layer input, and efficiently handles extreme long input sequences. (iii) the generative style decoder, while conceptually simple, predicts the long time-series sequences at one forward operation rather than a step-by-step way, which drastically improves the inference speed of long-sequence predictions. Extensive experiments on four large-scale datasets demonstrate that Informer significantly outperforms existing methods and provides a new solution to the LSTF problem.