Search

With the liberalization and deregulation of the power industry, the power market presents increasingly invisible dynamics and uncertainty. Establishing an effective price forecasting model has always been an important issue for power market participants to avoid risks and maximize economic benefits. However, due to the inherent characteristics of high frequency and high volatility of electricity price data, it is still a difficult and challenging problem to achieve high-precision forecasting. To overcome these difficulties, this study constructed a novel multivariate electric price bi-forecasting system based on the proposed linear operator combination mechanism and deep learning model. Specifically, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is used for data preprocessing, while the multiobjective golden eagle optimization algorithm (MOGEO) optimized deep belief network and bidirectional long short-term memory network are used as the main prediction models for realizing two forecasting modes of point forecast and interval forecast by a multi-input multi-output structure simultaneously. To verify the model forecasting ability and effectiveness, four datasets from Australia (New South Wales) from 2020.7 to 2021.1 are selected for experiments. According to the empirical results, the mean absolute percentage error results of the designed forecasting strategy in point forecasting are within 4% for the four datasets, and the average coverage width criterion values in interval forecasting are all approximately 0.3. The results show that the system has good electricity price forecasting ability and can help policy-makers better understand market dynamics and develop more effective market regulation and intervention measures. • A novel electric price multi-bi-forecasting is constructed using MIMO scheme. • Multi-variable forecast scheme is adopted using the electric price and load data. • A new combination mechanism is introduced to combine the member models. • A superior optimizer is introduced in this system to realize two functions. [ABSTRACT FROM AUTHOR]

Background: Better population data on respiratory viruses in children in tropical and southern hemisphere countries is needed.Methods: The epidemiology of respiratory viruses among healthy children (6 months to <10 years) with influenza-like illness (ILI) was determined in a population sample derived from an influenza vaccine trial (NCT01051661) in 17 centers in eight countries (Australia, South East Asia and Latin America). Active surveillance for ILI was conducted for approximately 1 year (between February 2010 and August 2011), with PCR analysis of nasal and throat swabs.Results: 6266 children were included, of whom 2421 experienced 3717 ILI episodes. Rhinovirus/enterovirus had the highest prevalence (41.5%), followed by influenza (15.8%), adenovirus (9.8%), parainfluenza and respiratory syncytial virus (RSV) (both 9.7%), coronavirus (5.6%), human metapneumovirus (5.5%) and human bocavirus (HBov) (2.0%). Corresponding incidence per 100 person-years was 29.78, 11.34, 7.03, 6.96, 6.94, 4.00, 3.98 and 1.41. Except for influenza, respiratory virus prevalence declined with age. The incidence of medically-attended ILI associated with viral infection ranged from 1.03 (HBov) to 23.69 (rhinovirus/enterovirus). The percentage of children missing school or daycare ranged from 21.4% (HBov) to 52.1% (influenza).Conclusions: Active surveillance of healthy children provided evidence of respiratory illness burden associated with several viruses, with a substantial burden in older children. [ABSTRACT FROM AUTHOR]