Review of distributed control and optimization in energy internet: From traditional methods to artificial intelligence‐based methods

Abstract

Energy internet (EI) can alleviate the arduous challenges brought about by the energy crisis and global warming and has aroused the concern of many scholars. In the research of EI control systems, the access of distributed energy causes the power system to exhibit complex nonlinearity, high uncertainty and strong coupling. Traditional control and optimization methods often have limited effectiveness in solving these problems. With the widespread application of distributed control technology and the maturity of artificial intelligence (AI) technology, the combination of distributed control and AI has become an effective method to break through current research bottlenecks. This study reviews the research progress of EI distributed control technologies based on AI in recent years. It can be found that AI-based distributed control methods have many advantages in maintaining EI stability and achieving optimal energy management. This combination of AI and distributed control makes EI control systems more intelligent, safe and efficient, which will be an important direction for future research. The purpose of this study is to provide a reference as well as useful research ideas for the study of EI control systems. | INTRODUCTION | Energy internetNowadays, the rapid development of human society has led to the massive consumption of fossil energy, forcing mankind to face many challenges such as energy crisis, environmental pollution and global warming. Therefore, people began to pay attention to the production and utilization of renewable energy [1,2]. According to statistics in [3], the annual growth of the world's total wind and solar power generation since 2000 is 22% and 40%, respectively. It is estimated that by 2050, renewable energy will account for 80% of the total power generation in the United States [4]. However, the traditional power grid cannot adapt to the large-scale access of renewable energy due to their disadvantages of intermittence and randomicity [5], which limit the use of clean energy. Taking wind power as an example, China's wind power curtailment in 2016 was as high as 4.97 � 10 10 kWÂůh, accounting for 17% of China's total wind power generation [6].This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Hierarchical Optimization and Grid Scheduling Model for Energy Internet: A Genetic Algorithm-Based Layered Approach

“…Each individual in the population is coded and corresponds to a candidate solution in the feasible region of the optimization problem. As a consequence, the population is a solution set made up of several viable alternatives (Zhong et al, 2005;Bevrani et al, 2016;Hua et al, 2018;Javaid et al, 2018;Hua et al, 2021;Perera et al, 2021). The fitness feature is a yardstick for measuring the advantages and disadvantages of individuals in the evolutionary phase (Li and Wang, 2019;Luo et al, 2019;Elmouatamid et al, 2020;Hussain et al, 2020;Wang et al, 2020b;Zand et al, 2020).…”

A Data-Driven Intelligent System for Assistive Design of Interior Environments

“…Serrano et al address the problems of low electrical energy utilization and waste in library lighting systems by analyzing the data collected from seated readers and designing a zoning lighting system that meets the behavior habits of readers while saving resources and reducing waste [ 10 ]. The research results were successfully applied to the secondary planning and renovation of the commercial street by using behavior models and computer simulation methods and based on the virtual visitation data of the online Expo, they obtained the behavior data of the visitors and carried out the temporal and spatial simulation of the multi-individual visitation behavior through the model, achieving the prediction and guidance of the number of visitors, the flow of people and the demand for facilities at the Expo [ 11 ]. The average accuracy of a single unit segment of the layout model without the word embedding layer is calculated to be 89.75%, and the average accuracy of the entire sequence of units is 73.48%; the average accuracy of a single unit segment of the layout model with the word embedding layer added is 98.60%.…”

Power Quality Enhancement based on Type 2 Fuzzy logic direct power control of a Microgrid connected photovoltaic system with battery storage feeding nonlinear load

“…Those techniques offer the advantage of being robust and efficient because they do not require exact knowledge of the mathematical model of the system. Moreover, those algorithms are characterized by good behavior in transitional regime [15].…”