Wind farm control technologies: from classical control to reinforcement learning

Abstract

Wind power plays a vital role in the global effort towards net zero. The recent figure shows that 93GW new wind capacity was installed worldwide in 2020, leading to a 53% year-on-year increase. Control system is the core in wind farm operations and has essential influences on the farm’s power capture efficiency, economic profitability, and operation & maintenance cost. However, wind farms’ inherent system complexities and the aerodynamic interactions among wind turbines bring significant barriers to control systems design. The wind industry has recognized that new technologies are needed to handle wind farm control tasks, especially for large-scale offshore wind farms. This paper provides a comprehensive review of the development and most recent advances of wind farm control technologies. This covers the introduction of fundamental aspects in wind farm control in terms of system modelling, main challenges, and control objectives. Existing wind farm control methods for different purposes, including layout optimization, power generation maximization, fatigue loads minimization, and power reference tracking, are investigated. Moreover, a detailed discussion regarding the differences and connections among model-based, model-free and data-driven wind farm approaches is presented. In addition, highlights are made on the state-of-the-art wind farm control technologies based on reinforcement learning - a booming machine learning technique that has drawn worldwide attention. Future challenges and research avenues in wind farm control are also analysed.

Reinforcement Learning-Based Wind Farm Control: Toward Large Farm Applications via Automatic Grouping and Transfer Learning

“…In the RL algorithm, the minimum and maximum values of α i , γ i , δα i , and δγ i are restricted based on turbine specifications. The function C i that decides the reward is defined in (2), which is related to the turbine's power generation P i , the yaw angle γ i , and the change of the induction state δα i . The local observations (i.e.…”

“…The wind industry has been growing dramatically in recent years, and many new wind farms have been planned globally to meet the needs of net zero. Among all the sub-systems, the wind farm control/operation system is essential and directly decides wind farms' power generation process and economic profitability [2]. With the continuous increase of global wind energy capacity, operating wind farms more efficiently and economically has become a key need in the wind industry, especially for large offshore wind farms.…”

“…However, the high system complexity and strong aerodynamic interactions between turbines render the design of wind farm control systems challenging. Particularly, it is well-understood and widely reported [2], [3], [4], [5] that the power generation efficiency of downstream turbines in a wind farm can be severely affected by the wakes (with reduced wind speeds and increased turbulence levels compared to the free stream) induced by upstream turbines. Currently, most wind farms ignore such wake effects in practical operation.…”

Data–Driven Wake Steering Control for a Simulated Wind Farm Model

“…Learning-based control, sometimes in connection with Reinforcement Learning (RL) methods, has recently demonstrated interesting properties, and it may be considered for the problem of wake steering when all wind turbines are active. For example, the works [9] and [10] exploited RL for maximising wind farm power generation. On the other hand, [11,12] applied RL to the related problem of power tracking, thus matching the output power of the wind farm as a function of the electricity grid.…”

Integrated simulation-based calibration and sensitivity analysis of a compressed air energy storage system

“…Renewable energy sources are expected to grow worldwide to mitigate GHG emissions from conventional power plants (IEA, 2020), which generate around 25% of GHGs (Dai et al, 2022). Renewable technologies are sustainable options for energy systems; wind energy contributed a third of the total green energy generated in 2018 (Dong et al, 2022). However, wind-based technologies face a key challenge of the expected variability of wind speed, which accounts for an imbalance between energy generation and consumption (Meng et al, 2019).…”