• Energy Research

Electricity demand forecasting is crucial for practical power system management. However, during the COVID-19 pandemic, the electricity demand system deviated from normal system, which has detrimental bias effect in future forecasts. To overcome this problem, we propose a deep learning framework with a COVID-19 adjustment for electricity demand forecasting. More specifically, we first designed COVID-19 related variables and applied a multiple linear regression model. After eliminating the impact of COVID-19, we employed an efficient deep learning algorithm, long short-term memory multiseasonal net deseasonalized approach, to model residuals from the linear model aforementioned. Finally, we demonstrated the merits of the proposed framework using the electricity demand in Taixing, Jiangsu, China, from May 13, 2018 to August 2, 2021.

Electric load forecasting plays an important role in electricity markets and power systems. Because electric load time series are complicated and nonlinear, it is very difficult to achieve a satisfactory forecasting accuracy. In this paper, a hybrid model, Wavelet Denoising-Extreme Learning Machine optimized by k-Nearest Neighbor Regression (EWKM), which combines k-Nearest Neighbor (KNN) and Extreme Learning Machine (ELM) based on a wavelet denoising technique is proposed for short-term load forecasting. The proposed hybrid model decomposes the time series into a low frequency-associated main signal and some detailed signals associated with high frequencies at first, then uses KNN to determine the independent and dependent variables from the low-frequency signal. Finally, the ELM is used to get the non-linear relationship between these variables to get the final prediction result for the electric load. Compared with three other models, Extreme Learning Machine optimized by k-Nearest Neighbor Regression (EKM), Wavelet Denoising-Extreme Learning Machine (WKM) and Wavelet Denoising-Back Propagation Neural Network optimized by k-Nearest Neighbor Regression (WNNM), the model proposed in this paper can improve the accuracy efficiently. New South Wales is the economic powerhouse of Australia, so we use the proposed model to predict electric demand for that region. The accurate prediction has a significant meaning.

AbstractWind power forecasting techniques have been well developed over the last half-century. There has been a large number of research literature as well as review analyses. Over the past 5 decades, considerable advancements have been achieved in wind power forecasting. A large body of research literature has been produced, including review articles that have addressed various aspects of the subject. However, these reviews have predominantly utilized horizontal comparisons and have not conducted a comprehensive analysis of the research that has been undertaken. This survey aims to provide a systematic and analytical review of the technical progress made in wind power forecasting. To accomplish this goal, we conducted a knowledge map analysis of the wind power forecasting literature published in the Web of Science database over the last 2 decades. We examined the collaboration network and development context, analyzed publication volume, citation frequency, journal of publication, author, and institutional influence, and studied co-occurring and bursting keywords to reveal changing research hotspots. These hotspots aim to indicate the progress and challenges of current forecasting technologies, which is of great significance for promoting the development of forecasting technology. Based on our findings, we analyzed commonly used traditional machine learning and advanced deep learning methods in this field, such as classical neural networks, and recent Transformers, and discussed emerging technologies like large language models. We also provide quantitative analysis of the advantages, disadvantages, forecasting accuracy, and computational costs of these methods. Finally, some open research questions and trends related to this topic were discussed, which can help improve the understanding of various power forecasting methods. This survey paper provides valuable insights for wind power engineers.

Electricity demand forecasting is of great significance to the electricity system and residents’ life, but it is difficult to forecast the electricity demand series because of the influence of cyclical factors. Electricity demand forecasting also faces the problem of small data amounts. Therefore, we need to design a model that is less affected by data volume and can cope with complex electricity demand series. Based on the Autoformer model, this paper establishes a novel forecasting framework with excellent performance. In the part of data preprocessing, multiple linear regression with 10 variables and Bootstrap processing are added. In the part of the model, the Auto-Correlation mechanism is modified to better extract the historical and nonlinear characteristics of electricity demand series from different time spans. Using this framework, we further analyze the impact of working days and seasonal changes on the electricity demand in Taixing City and New South Wales. In addition, we propose a new electricity demand forecasting method, which can adjust the original sequence according to the actual situation. The experimental results show that this method can achieve good precision in demand forecasting. Taking Taixing of China and New South Wales of Australia as examples, the forecasting performance with the proposed framework is better than that of Autoformer, Reformer, Informer, and other mainstream models. The forecasting indexes with our proposed framework of the test set are MAE: 35.05, RMSE: 47.28, MAPE: 1.63 in Taixing and MAE: 193.17, RMSE: 239.96, MAPE: 2.43 in NSW.

Abstract In energy demand forecasting, the objective function is often symmetric, implying that over-prediction errors and under-prediction errors have the same consequences. In practice, these two types of errors generally incur very different costs. To accommodate this, we propose a machine learning algorithm with a cost-oriented asymmetric loss function in the training procedure. Specifically, we develop a new support vector regression incorporating a linear-linear cost function and the insensitivity parameter for sufficient fitting. The electric load data from the state of New South Wales in Australia is used to show the superiority of our proposed framework. Compared with the basic support vector regression, our new asymmetric support vector regression framework for multi-step load forecasting results in a daily economic cost reduction ranging from 42.19 % to 57.39 % , depending on the actual cost ratio of the two types of errors.

Air pollution in China is becoming more serious especially for the particular matter (PM) because of rapid economic growth and fast expansion of urbanization. To solve the growing environment problems, daily PM2.5 and PM10 concentration data form January 1, 2015, to August 23, 2016, in Kunming and Yuxi (two important cities in Yunnan Province, China) are used to present a new hybrid model CI-FPA-SVM to forecast air PM2.5 and PM10 concentration in this paper. The proposed model involves two parts. Firstly, due to its deficiency to assess the possible correlation between different variables, the cointegration theory is introduced to get the input-output relationship and then obtain the nonlinear dynamical system with support vector machine (SVM), in which the parameters c and g are optimized by flower pollination algorithm (FPA). Six benchmark models, including FPA-SVM, CI-SVM, CI-GA-SVM, CI-PSO-SVM, CI-FPA-NN, and multiple linear regression model, are considered to verify the superiority of the proposed hybrid model. The empirical study results demonstrate that the proposed model CI-FPA-SVM is remarkably superior to all considered benchmark models for its high prediction accuracy, and the application of the model for forecasting can give effective monitoring and management of further air quality.

The COVID-19 pandemic has given rise to significant changes in electricity demand around the world. Although these changes differ from region to region, countries that have implemented stringent lockdown measures to curtail the spread of the virus have experienced the greatest alterations in demand. Within Australia, the state of Victoria has been subject to the largest number of days in hard lockdown during the COVID-19 pandemic. We conduct an exploratory data analysis to identify predictors of demand, and have built a time series forecasting model to predict the half-hourly electricity demand in Victoria. Our model distinguishes between lockdown periods and non-restrictive periods, and aims to identify a variety of patterns that we show to be influential on electricity demand. The model thereby provides a nuanced prediction of electricity demand that captures the shifting demand profile of intermittent lockdowns.