Search

The surge of renewable energy systems can lead to increasing incidents that negatively impact economics and society, rendering incident detection paramount to understand the mechanism and range of those impacts. In this paper, a deep learning framework is proposed to detect renewable energy incidents from news articles containing accidents in various renewable energy systems. The pre-trained language models like Bidirectional Encoder Representations from Transformers (BERT) and word2vec are utilized to represent textual inputs, which are trained by the Text Convolutional Neural Networks (TCNNs) and Text Recurrent Neural Networks. Two types of classifiers for incident detection are trained and tested in this paper, one is a binary classifier for detecting the existence of an incident, the other is a multi-label classifier for identifying different incident attributes such as causal-effects and consequences, etc. The proposed incident detection framework is implemented on a hand-annotated dataset with 5 190 records. The results show that the proposed framework performs well on both the incident existence detection task (F1-score 91.4%) and the incident attributes identification task (micro F1-score 81.7%). It is also shown that the BERT-based TCNNs are effective and robust in detecting renewable energy incidents from large-scale textual materials. [ABSTRACT FROM AUTHOR]

The problem of wind curtailment is serious in China. It not only restricts the development of renewable energy, but also brings economic losses to the enterprises and the society. Unfortunately, the problem of wind power curtailment is difficult to eliminate under existing facilities and technical conditions. Therefore, it is a practicable way to control the wind power curtailment rate as far as possible on the premise of guaranteeing the profit of the power generation enterprise and meeting the demand for electricity users. In the context of the coordinated development of the Beijing-Tianjin-Hebei region, this article presents a deep analysis of other energy generation, power grid planning, social benefits, electricity prices, and other factors associated with the wind power generation, then we constructed a complete "cost of wind curtailment" model. Finally, an uncertainty analysis is added to show the impact of some uncertainties on the model, which makes the model more complete, and after calculating the cost and benefit of "reducing the rate of wind curtailment," some pertinent suggestions are given, which will provide policy basis for the development of renewable energy. [ABSTRACT FROM AUTHOR]

The growing share of renewable energy has an increasingly significant impact on the electricity market. Locational marginal price (LMP), as a sensitive price signal, has a potential but considerable correlation with renewable energy generation. In this context, this paper focuses on the joint fluctuation laws between LMP and renewables consumed to generate electricity. At first, LMP and renewables consumption data from Independent System Operator New England (ISO‐NE) are collected and preprocessed. Then, through highly comparative time‐series analysis (hctsa), it is found that discrete symbolization features have effective description ability. Therefore, a coarse‐grained method is conducted to convert the real matrix data into a symbol vector based on numerical distribution analysis. Next, joint fluctuation complex networks are constructed according to the symbol vector. From a global perspective, the joint fluctuation network follows an exponential distribution and exhibits hierarchical modularity. From a local perspective, the joint fluctuation network follows a power‐law distribution. The research results of this paper provide a new perspective to understand the evolution of the electricity market with large‐scale renewable energy and have reference value for identifying the valuable joint fluctuation patterns and improving the LMP forecast results. [ABSTRACT FROM AUTHOR]

Renewable energy is the inevitable choice for the sustainable development of society and economy. How to select the most appropriate renewable energy for a region is a complex multi-criterion decision making (MCDM) problem. Taking Jilin Province as an example, this paper proposes a new MCDM method. In order to better express the hesitancy, inconsistency and uncertainty of decision makers’ preferences, linguistic hesitant fuzzy set (LHFS) is proposed. On the basis of cloud model, the rule of transforming LHFS to quantitative values is defined. Subsequently, the distance measure and support measure are established. In consideration of the interdependency of criteria, an LHFS aggregation operator based on improved Choquet integral is proposed. Finally, the ranking result of the aggregated LHFS corresponding to each renewable energy alternative is obtained according to the expectation values. The result shows that the preferred renewable energy for Jilin is biomass energy, followed by wind energy, hydro energy and solar energy. The validation analysis and comparison analysis are given to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]