4.6 Article

Evaluation on the impact of digital transformation on the economic resilience of the energy industry in the context of artificial intelligence

Journal

ENERGY REPORTS
Volume 9, Issue -, Pages 785-792

Publisher

ELSEVIER
DOI: 10.1016/j.egyr.2022.12.019

Keywords

Economic management; Economic resilience; Digital change; Artificial intelligence; Energy industry; Support Vector Machines

Categories

Ask authors/readers for more resources

The energy industry has achieved rapid development based on energy resources in recent years, but traditional energy companies are also facing challenges under the background of green development strategy. However, the development of technologies such as the Internet and artificial intelligence has provided opportunities for the digital transformation of the energy industry. The key to the successful digital transformation lies in improving the industry's economic resilience.
In recent years, the energy industry based on energy resources has achieved rapid development, but under the background of green development strategy, traditional energy companies are also in trouble during the development process. However, the accompanying development of technologies such as the Internet and artificial intelligence has opened the door to a new world of digital transformation of the energy industry. The focus of whether the energy industry can truly achieve digital transformation lies in how to improve its own level of economic resilience. In order to explore how digital transformation affects the economic resilience of the energy industry in the context of artificial intelligence, after discussing the development dilemma of the energy industry and the integration of artificial intelligence and digital transformation, this paper established a Particle Swarm Optimization-based Least Squares Support Vector Machine (PSO-LSSVM) algorithm. Experiments have shown that the model built in this paper has a good prediction effect on the economic resilience index, and the average prediction error after training is 0.0028. Compared with the standard least squares support vector machine and back-propagation neural network methods, this method not only has more stable prediction results, but also greatly improves the prediction accuracy.(c) 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available