Short-term forecasting of CO2 emission intensity in power grids by machine learning

It is a very urgent issue to reduce energy-related carbon emissions in China. The three northeastern provinces (Heilongjiang (HLJ), Jilin (JL), and Liaoning (LN)) are typical heavy industrial regions in China, playing an important role in the national carbon emission reduction target. In this study, we analyzed the energy consumption, carbon dioxide (CO2) emissions, and CO2 emission intensity of each sector in the three regions, and we compared them with the national level and those of China’s most developed province Guangdong (GD). Then, based on an input–output (I–O) framework, linkage analysis of production and CO2 emission from sector–system and sector–sector dimensions was conducted. The results showed that the three regions accounted for about 1/10 of China’s energy consumption and 1/6 of China’s CO2 emissions in 2012. In addition, the level of energy structure, CO2 emission intensity, and sectoral structure lagged behind China’s average level, much lower than those for GD. According to the sectoral characteristics of each region and unified backward/forward linkages of production and CO2 emissions, we divided sectoral clusters into those whose development was to be encouraged and those whose development was to be restricted. The results of this paper could provide policy–makers with reference to exploring potential pathways toward energy-related carbon emission reduction in heavy industrial regions.

Download Full-text

Short-Term Forecasting of Photovoltaic Solar Power Production Using Variational Auto-Encoder Driven Deep Learning Approach

Applied Sciences ◽

10.3390/app10238400 ◽

2020 ◽

Vol 10 (23) ◽

pp. 8400 ◽

Cited By ~ 1

Author(s):

Abdelkader Dairi ◽

Fouzi Harrou ◽

Ying Sun ◽

Sofiane Khadraoui

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Solar Power ◽

Power Production ◽

Superior Performance ◽

Support Vector ◽

Learning Models ◽

Short Term ◽

Learning Methods ◽

Short Term Forecasting

The accurate modeling and forecasting of the power output of photovoltaic (PV) systems are critical to efficiently managing their integration in smart grids, delivery, and storage. This paper intends to provide efficient short-term forecasting of solar power production using Variational AutoEncoder (VAE) model. Adopting the VAE-driven deep learning model is expected to improve forecasting accuracy because of its suitable performance in time-series modeling and flexible nonlinear approximation. Both single- and multi-step-ahead forecasts are investigated in this work. Data from two grid-connected plants (a 243 kW parking lot canopy array in the US and a 9 MW PV system in Algeria) are employed to show the investigated deep learning models’ performance. Specifically, the forecasting outputs of the proposed VAE-based forecasting method have been compared with seven deep learning methods, namely recurrent neural network, Long short-term memory (LSTM), Bidirectional LSTM, Convolutional LSTM network, Gated recurrent units, stacked autoencoder, and restricted Boltzmann machine, and two commonly used machine learning methods, namely logistic regression and support vector regression. The results of this investigation demonstrate the satisfying performance of deep learning techniques to forecast solar power and point out that the VAE consistently performed better than the other methods. Also, results confirmed the superior performance of deep learning models compared to the two considered baseline machine learning models.

Download Full-text

Short-term forecasting for Wind Speed based on machine learning using weather observation data

Journal of the Korean Data and Information Science Society ◽

10.7465/jkdi.2020.31.5.823 ◽

2020 ◽

Vol 31 (5) ◽

pp. 823-837

Author(s):

Hyeong-Se Jeong

Keyword(s):

Machine Learning ◽

Wind Speed ◽

Observation Data ◽

Short Term ◽

Short Term Forecasting ◽

Weather Observation

Download Full-text