Most evolutionary optimization algorithms assume that the evaluation of the objective and constraint functions is straightforward. In solving many real-world optimization problems, however, such objective functions may not exist. Instead, computationally expensive numerical simulations or costly physical experiments must be performed for fitness evaluations. In more extreme cases, only historical data are available for performing optimization and no new data can be generated during optimization. Solving evolutionary optimization problems driven by data collected in simulations, physical experiments, production processes, or daily life are termed data-driven evolutionary optimization. In this paper, we provide a taxonomy of different data driven evolutionary optimization problems, discuss main challenges in data-driven evolutionary optimization with respect to the nature and amount of data, and the availability of new data during optimization. Real-world application examples are given to illustrate different model management strategies for different categories of data-driven optimization problems.

/pdf/data-driven-evolutionary-optimization-an-overview-and-case-4ikneg272y.pdf

Data-Driven Evolutionary Optimization: An Overview and Case Studies

Many real-world optimization problems can be solved by using the data-driven approach only, simply because no analytic objective functions are available for evaluating candidate solutions. In this paper, we address a class of expensive data-driven constrained multiobjective combinatorial optimization problems, where the objectives and constraints can be calculated only on the basis of a large amount of data. To solve this class of problems, we propose using random forests (RFs) and radial basis function networks as surrogates to approximate both objective and constraint functions. In addition, logistic regression models are introduced to rectify the surrogate-assisted fitness evaluations and a stochastic ranking selection is adopted to further reduce the influences of the approximated constraint functions. Three variants of the proposed algorithm are empirically evaluated on multiobjective knapsack benchmark problems and two real-world trauma system design problems. Experimental results demonstrate that the variant using RF models as the surrogates is effective and efficient in solving data-driven constrained multiobjective combinatorial optimization problems.

A Random Forest-Assisted Evolutionary Algorithm for Data-Driven Constrained Multiobjective Combinatorial Optimization of Trauma Systems

Better prediction models for the upcoming supply of renewable energy are important to decrease the need of controlling energy provided by conventional power plants. Especially for successful power grid integration of the highly volatile wind power production, a reliable forecast is crucial. In this chapter, we focus on short-term wind power prediction and employ data from the National Renewable Energy Laboratory (NREL), which are designed for a wind integration study in the western part of the United States. In contrast to physical approaches based on very complex differential equations, our model derives functional dependencies directly from the observations. Hereby, we formulate the prediction task as regression problem and test different regression techniques such as linear regression, k-nearest neighbors and support vector regression. In our experiments, we analyze predictions for individual turbines as well as entire wind parks and show that a machine learning approach yields feasible results for short-term wind power prediction.

Wind Power Prediction with Machine Learning

Cross-validation based K nearest neighbor imputation for software quality datasets: An empirical study

Self-adjusting parameter control for surrogate-assisted constrained optimization under limited budgets

The shift from traditional energy systems to distributed systems of energy suppliers and consumers and the power volatileness in renewable energy imply the need for effective short-term prediction models. These machine learning models are based on measured sensor information. In practice, sensors might fail for several reasons. The prediction models cannot naturally cannot work properly with incomplete patterns. If the imputation method, which completes the missing data, is not appropriately chosen, a bias may be introduced. The objective of this work is to propose the k-nearest neighbor (kNN) regression as geo-imputation preprocessing step for pattern-label-based short-term wind prediction of spatio-temporal wind data sets. The approach is compared to three other methods. The evaluation is based on four turbines with neighbors of the NREL Western Wind Data Set and the values are missing uniformly distributed. The results show that kNN regression is the most superior method for imputation.

KNN Regression as Geo-Imputation Method for Spatio-Temporal Wind Data

In many applications of constrained continuous black box optimization, the evaluation of fitness and feasibility is expensive. Hence, the objective of reducing the constraint function calls remains a challenging research topic. In the past, various surrogate models have been proposed to solve this issue. In this paper, a local surrogate model of feasibility for a self-adaptive evolution strategy is proposed, which is based on support vector classification and a pre-selection surrogate model management strategy. Negative side effects suchs as a decceleration of evolutionary convergence or feasibility stagnation are prevented with a control parameter. Additionally, self-adaptive mutation is extended by a surrogate-assisted alignment to support the evolutionary convergence. The experimental results show a significant reduction of constraint function calls and show a positive effect on the convergence.

Local SVM Constraint Surrogate Models for Self-adaptive Evolution Strategies

Wind energy is playing an increasingly important part for ecologically friendly power supply. The fast growing infrastructure of wind turbines can be seen as large sensor system that screens the wind energy at a high temporal and spatial resolution. The resulting databases consist of huge amounts of wind energy time series data that can be used for prediction, controlling, and planning purposes. In this work, we describe WindML, a Python-based framework for wind energy related machine learning approaches. The main objective of WindML is the continuous development of tools that address important challenges induced by the growing wind energy information infrastructures. Various examples that demonstrate typical use cases are introduced and related research questions are discussed. The different modules of WindML reach from standard machine learning algorithms to advanced techniques for handling missing data and monitoring high-dimensional time series.

A framework for data mining in wind power time series

Real-parameter blackbox optimization using evolution strategies (ES) is often applied when the fitness function or its characteristics are not explicitly given. The evaluation of fitness and feasibility might be expensive. In the past, different surrogate model approaches have been proposed to address this issue. In our previous work, local feasibility surrogate models have been proposed, which are trained with already evaluated individuals. This tightly coupled interdependency with the optimization process leads to complex side effects when applied with meta-heuristics like the covariance matrix adaption ES (CMA-ES). The objective of this paper is to propose a new type of constraint surrogate model, which uses the concept of active learning in multiple stages for the estimation of the constraint boundary for a stage-depending accuracy. The underlying linear model of the constraint boundary is estimated in every stage with binary search. In the optimization process the pre-selection scheme is employed to save constraint function calls. The surrogate model is evaluated on a simple adaptive (1 + 1)-ES as well as on the complex (1 + 1)-CMA-ES for constrained optimization. The results of both ES on a linearly-constrained test bed look promising.

Jendrik Poloczek

Papers

KNN Regression as Geo-Imputation Method for Spatio-Temporal Wind Data

Local SVM Constraint Surrogate Models for Self-adaptive Evolution Strategies

A framework for data mining in wind power time series

Multi-stage Constraint Surrogate Models for Evolution Strategies