Automatic Generation Control Strategy for Integrated Energy System Based on Ubiquitous Power Internet of Things

Article Energy & Fuels

Dynamic stability analysis of power grid in high proportion new energy access scenario based on deep learning

Zengyao Tian et al.

Summary: This paper uses the dual-stream CNN algorithm in the deep learning technology, based on dynamic stability theory, to study and model the dynamic stability issues of the power system caused by high proportion of new energy access. By quickly identifying the main oscillation modes and conducting qualitative evaluation, it provides reliable technical support for subsequent dispatching operation of the power system and helps improve its safe and stable operation level.

ENERGY REPORTS (2022)

添加到收藏夹

Article Chemistry, Physical

Coordinated control of gas supply system in PEMFC based on multi-agent deep reinforcement learning

Jiawen Li et al.

Summary: An intelligent control framework is proposed for coordinating the air and hydrogen supply systems in PEMFCs, using ensemble imitation learning and multi-trick deep deterministic policy gradient approach to enhance exploration efficiency. Multiple reinforcement learning explorers and control algorithm explorers are utilized to address sparse rewards and improve training efficiency. Multiple tricks are applied to improve the overestimated Q value, resulting in a model-free intelligent control algorithm with better global searching ability.

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY (2021)

添加到收藏夹

Article Energy & Fuels

Efficient experience replay based deep deterministic policy gradient for AGC dispatch in integrated energy system

Jiawen Li et al.

Summary: A novel automatic generation control dispatch was proposed to balance stochastic power disturbance in integrated energy system, aiming to reduce control deviation and regulation mileage payment while improving training efficiency and action quality through multiple experience pool probability replay strategy. The proposed algorithm was verified on a two-area load frequency control model and Hainan province IES for different energy demand.

APPLIED ENERGY (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

Two-Stage Full-Data Processing for Microgrid Planning With High Penetrations of Renewable Energy Sources

Xiaobo Wang et al.

Summary: This paper proposes a data-driven method for microgrid planning, utilizing a two-stage data processing approach to obtain representative operating periods at different time scales. By establishing two time series in the planning model, the method caters to the different requirements of investment and operational decisions, improving efficiency through reducing data scale and accelerating the solution process.

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Automatic Generation Control Based on Multiple Neural Networks With Actor-Critic Strategy

Lei Xi et al.

Summary: This article proposes a deep-reinforcement-learning-based three-network double-delay actor-critic control strategy for improving power grid control performance and achieving optimal coordinated control. Simulation studies demonstrate the strategy's excellent stability and learning ability.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

添加到收藏夹

Review Energy & Fuels