• Energy Research
• CN close
• GB close
• FR close
• Applied Energy close

Abstract To enhance prediction accuracy and reduce computation complexity, a decomposition–ensemble methodology with data-characteristic-driven reconstruction is proposed for crude oil price forecasting, based on two promising principles of “divide and conquer” and “data-characteristic-driven modeling”. Actually, this proposed model improves the existing decomposition–ensemble techniques in the “divide and conquer” framework, by formulating and incorporating a data-characteristic-driven reconstruction method based on the “data-characteristic-driven modeling”. Four main steps are involved in the proposed methodology, i.e., data decomposition for simplifying the complex data, component reconstruction based on the “data-characteristic-driven modeling” for capturing inner factors and reducing computational cost, individual prediction for each reconstructed component via a certain artificial intelligence (AI) tool, and ensemble prediction for final output. In the proposed data-characteristic-driven reconstruction, all decomposed modes are thoroughly analyzed to explore the hidden data characteristics, and are accordingly reconstructed into some meaningful components. For illustration and verification, the West Texas Intermediate (WTI) and Brent crude oil spot prices are used as the sample data, and the empirical results indicate that the proposed model statistically outperforms all considered benchmark models (including popular AI single models, typical decomposition–ensemble models without reconstruction, and similar decomposition–ensemble models with other existing reconstruction methods), since it has higher prediction accuracy and less computational time.

Abstract Algae have been considered as a promising biodiesel feedstock. One of the major factors affecting large-scale algae technology application is poor wintering cultivation performance. In this study, an integrated approach is investigated combining freshwater microalgae Chlorella zofingiensis wintering cultivation in pilot-scale photobioreactors with artificial wastewater treatment. Mixotrophic culture with the addition of acetic acid (pH-regulation group) and autotrophic culture (control group) were designed, and the characteristics of algal growth, lipid and biodiesel production, and nitrogen and phosphate removal were examined. The results showed that, by using acetic acid three times per day to regulate pH at between 6.8 and 7.2, the total nitrogen (TN) and total phosphate (TP) removal could be increased from 45.2% to 73.5% and from 92.2% to 100%, respectively. Higher biomass productivity of 66.94 mg L−1 day−1 with specific growth rate of 0.260 day−1 was achieved in the pH-regulation group. The lipid content was much higher when using acetic acid to regulate pH, and the relative lipid productivity reached 37.48 mg L−1 day−1. The biodiesel yield in the pH-regulated group was 19.44% of dry weight, with 16–18 carbons as the most abundant composition for fatty acid methyl esters. The findings of the study prove that pH adjustment using acetic acid is efficient in cultivating C. zofingiensis in wastewater in winter for biodiesel production and nutrient reduction.

Abstract Oil-related events have increased the uncertainty and complexity of the worldwide oil market. This paper investigates the effects of four types of oil-related events on world oil prices, using an event study methodology and an AR-GARCH model. The Internet information concerning these events, which is derived from search query volumes in Google, is introduced in an analytical framework to identify the magnitude and significance of the market response to oil-related events. The results indicate that world oil prices responding to different oil-related events display obvious differentiation. The cumulative abnormal returns, which reflect the influence of the global financial crisis, tend to drop first and then reverse and rise, while the cumulative abnormal returns induced by other oil-related events present a stronger persistent effect. The impact of the global financial crisis on oil price returns is significantly negative, while the impact of the Libyan war and hurricanes is significantly positive. However, the reactions of oil price returns to different OPEC production announcements are inconsistent.

Effectively analyzing and then treating energy-related air pollution requires examining every factor, from the pollution source to the end of treatment. This paper applies index decomposition analysis and a whole process treatment perspective to identify the factors facilitating air pollution reduction across three stages: source prevention, process control, and end-of-pipe treatment. Empirical research using data from China’s Jiangsu Province and its 13 cities reveals differences in local approaches to pollution prevention. At the provincial level, end-of-pipe treatment remains the primary approach to control air pollution emissions, indicating that the pattern of “pollute first, govern later” has not yet been fundamentally reversed. At the city level, 13 cities can be divided into four types, based on their approach to air pollution treatment: the leading type, process-dependent type, end-dependent type, and lagging type. Of these, 7 cities are using multiple control approaches, reflecting the comprehensive effect of whole process treatment. The Jiangsu Province should consider further strengthening effective whole process air pollution treatment models, by transitioning to pollution control, adjusting industrial structure, promoting technological progress, and consuming clean energy.

Nowadays, the electric power system and natural gas network are becoming increasingly coupled and interdependent. A harmonized integration of natural gas and electricity network with bi-directional energy conversion is expected to accommodate high penetration levels of renewables in terms of system flexibility. This work focuses on the steady-state analysis of the integrated natural gas and electric power system with bi-directional energy conversion. A unified energy flow formulation is developed to describe the nodal balance and branch flow in both systems and it is solved with the Newton–Raphson method. Both the unification of units and the per-unit system are proposed to simplify the system description and to enhance the computation efficiency. The applicability of the proposed method is demonstrated by analyzing an IEEE-9 test system integrated with a 7-node natural gas network. Later, time series of wind power and power load are used to investigate the mitigation effect of the integrated energy system. At last, the effect of wind power and power demand on the output of Power to Gas (P2G) and gas-fired power generation (GPG) has also been investigated.

This paper proposes a data-driven diagnostic approach for Polymer Electrolyte Membrane Fuel Cell (PEMFC) systems. Fault detection and isolation (FDI) is realized by analyzing individual cell voltages. A feature extraction method Fisher Discriminant Analysis (FDA) and a multi-class classification method Directed Acyclic Graph Support Vector Machine (DAGSVM) are utilized successively to extract the useful features from raw data and classify the extracted features into various classes related to health states. Experimental data of two different stacks are used to validate the proposed approach. The results show that five concerned faults can be detected and isolated with a high accuracy. Moreover, the light computational cost of the approach enhances the possibility of its online implementation.