We consider perturbation-based extremum seeking, which recovers an approximate gradient of an analytically unknown objective function through measurements. Using classical needle variation analysis, we are able to explicitly quantify the recovered gradient in the scalar case. We reveal that it corresponds to an averaged gradient of the objective function, even for very general extremum seeking systems. From this, we create a recursion which represents the learning dynamics along the recovered gradient. These results give rise to the interpretation that extremum seeking actually optimizes a function other than the original one. From this insight, a new perspective on global optimization of functions with local extrema emerges: because the gradient is averaged over a certain time period, local extrema might be evened out in the learning dynamics. Moreover, a multidimensional extension of the scalar results is given.
The paper deals with a well-known extremum seeking scheme by proving uniformity properties with respect to the amplitudes of the dither signal and of the cost function. Those properties are then used to show that the scheme guarantees the global minimiser to be semi-global practically stable despite the presence of local saddle points. To achieve these results, we analyse the average system associated with the extremum seeking scheme via arguments based on the Fourier series.
Extremum seeking (ES) optimization approach has been very popular due to its non-model based analysis and implementation. This approach has been mostly used with gradient based search algorithms. Since least squares (LS) algorithms are typically observed to be superior, in terms of convergence speed and robustness to measurement noises, over gradient algorithms, it is expected that LS based ES schemes will also provide faster convergence and robustness to sensor noises. In this paper, with this motivation, a recursive least squares (RLS) estimation based ES scheme is designed and analysed for …
We propose two perturbation-based extremum seeking control (ESC) schemes for general single input single output nonlinear dynamical systems, having structures similar to that of the classical ESC scheme. We propose novel adaptation laws for the excitation signal amplitudes in each scheme that drive the amplitudes to zero. The rates of decay for both the laws are governed by the gradient measures of the unknown reference-to-output equilibrium map. We show that the proposed ESC schemes achieve practical asymptotic convergence to the extremum with a proper tuning of the parameters in the proposed…
In this paper we consider the problem of finding a Nash equilibrium (NE) via zeroth-order feedback information in games with merely monotone pseudogradient mapping. Based on hybrid system theory, we propose a novel extremum seeking algorithm which converges to the set of Nash equilibria in a semi-global practical sense. Finally, we present two simulation examples. The first shows that the standard extremum seeking algorithm fails, while ours succeeds in reaching NE. In the second, we simulate an allocation problem with fixed demand.
In an active power distribution system, Volt-VAR optimization (VVO) methods are employed to achieve network-level objectives such as minimization of network power losses. The commonly used model-based centralized and distributed VVO algorithms perform poorly in the absence of a communication system and with model and measurement uncertainties. In this paper, we proposed a model-free local Volt-VAR control approach for network-level optimization that does not require communication with other decision-making agents. The proposed algorithm is based on extremum-seeking approach that uses only loca…
Wireless communication offers many benefits for control such as substantially reduced deployment costs, higher flexibility, as well as easier data access. It is thus not surprising that smart and wireless sensors and actuators are increasingly used in industry. With these enhanced possibilities, exciting new technologies such as Control-as-a-Service arise, where (for example) controller design or tuning based on input-output-data can be outsourced to a cloud or mobile device. This implies, however, that sensitive plant information may become available to service providers or, possibly, attacke…
Event-Triggered Newton Extremum Seeking for Multivariable Optimization
State University of Rio de Janeiro (UERJ)（里约热内卢州立大学）；University of California at San Diego (UCSD)（加利福尼亚大学圣地亚哥分校）；University of California at Los Angeles (UCLA)（加利福尼亚大学洛杉矶分校）
This paper proposes a multivariable extremum seeking scheme using Fast Fourier Transform (FFT) for a network of subsystems working towards optimizing the sum of their local objectives, where the overall objective is the only available measurement. Here, the different inputs are perturbed with different dither frequencies, and the power spectrum of the overall output signal obtained using FFT is used to estimate the steady-state cost gradient w.r.t. each input. The inputs for the subsystems are then updated using integral control in order to drive the respective gradients to zero. This paper pr…
In this paper, we consider the problem of learning a generalized Nash equilibrium (GNE) in strongly monotone games. First, we propose a novel continuous-time solution algorithm that uses regular projections and first-order information. As second main contribution, we design a data-driven variant of the former algorithm where each agent estimates their individual pseudo-gradient via zero-order information, namely, measurements of their individual cost function values, as typical of extremum seeking control. Third, we generalize our setup and results for multi-agent systems with nonlinear dynami…
For N-dimensional (ND) static quadratic map, we present a time-delay approach to gradient-based extremum seeking (ES) both, in the continuous and, for the first time, the discrete domains. As in the recently introduced (for 2D maps in the continuous domain), we transform the system to the time-delay one (neutral type system in the form of Hale in the continuous case). This system is O($\varepsilon$)-perturbation of the averaged linear ODE system, where $\varepsilon$ is a period of averaging. We further explicitly present the neutral system as the linear ODE, where O($\varepsilon$)-terms are co…
In this paper, we propose the concept of accelerated convergence that has originally been developed to speed up the convergence of numerical methods for extremum seeking (ES) loops. We demonstrate how the dynamics of ES loops may be analyzed to extract structural information about the generated output of the loop. This information is then used to distil the limit of the loop without having to wait for the system to converge to it.
This paper presents an extremum seeking control algorithm with an adaptive step-size that adjusts the aggressiveness of the controller based on the quality of the gradient estimate. The adaptive step-size ensures that the integral-action produced by the gradient descent does not destabilize the closed-loop system. To quantify the quality of the gradient estimate, we present a batch least squares estimator with a novel weighting and show that it produces bounded estimation errors, where the uncertainty is due to the curvature of the unknown cost function. The adaptive step-size then maximizes t…
This paper presents a combined power system with a common dc bus that contains solar power, wind power, battery storage, and a constant dc load (CDL). In wind system, an AC-DC uncontrolled rectifier is used at the first stage and the DC-DC converter is controlled by a maximum power point tracker (MPPT) at second stage. In the solar system, two cascaded boost converters are controlled through a sliding mode controller (SMC) to regulate the power flow to the load. A supervisory control strategy is also introduced to maximize the simultaneous energy harvesting from both renewable sources and bala…
In this paper, we systematically investigate the feasibility of different extremum-seeking (ES) control schemes to improve the conversion efficiency of wave energy converters (WECs). Continuous-time and model-free ES schemes based on the sliding mode, relay, least-squares gradient, self-driving, and perturbation-based methods are used to improve the mean extracted power of a heaving point absorber subject to regular and irregular waves. This objective is achieved by optimizing the resistive and reactive coefficients of the power take-off (PTO) mechanism using the ES approach. The optimization …
Robust Reduced-Order Model Stabilization for Partial Differential Equations Based on Lyapunov Theory and Extremum Seeking with Application to the 3D Boussinesq Equations
Mitsubishi Electric Research Laboratories（三菱电机研究实验室）；Interdisciplinary Center for Applied Mathematics, Virginia Tech（弗吉尼亚理工大学跨学科应用数学中心）；Department of Aeronautics and Astronautics, Massachusetts Institute of Technology（麻省理工学院航空航天系）
On Delay-robustness of Extremum Seeking of Nonlinear Static Maps with Small Disturbance
School of Information and Control Engineering, Southwest University of Science and Technology（西南科技大学信息与控制工程学院）；College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院）
In this paper, we solve the problem of learning a generalized Nash equilibrium (GNE) in merely monotone games. First, we propose a novel continuous semi-decentralized solution algorithm without projections that uses first-order information to compute a GNE with a central coordinator. As the second main contribution, we design a gain adaptation scheme for the previous algorithm in order to alleviate the problem of improper scaling of the cost functions versus the constraints. Third, we propose a data-driven variant of the former algorithm, where each agent estimates their individual pseudogradi…
