Data-driven Optimization Algorithm Research Articles

Data-Driven Linear Quadratic Optimization for Controller Synthesis With Structural Constraints.

For various typical cases and situations where the formulation results in an optimal control problem, the linear quadratic regulator (LQR) approach and its variants continue to be highly attractive. In certain scenarios, it can happen that some prescribed structural constraints on the gain matrix would arise. Consequently then, the algebraic Riccati equation (ARE) is no longer applicable in a straightforward way to obtain the optimal solution. This work presents a rather effective alternative optimization approach based on gradient projection. The utilized gradient is obtained through a data-driven methodology, and then projected onto applicable constrained hyperplanes. Essentially, this projection gradient determines a direction of progression and computation for the gain matrix update with a decreasing functional cost; and then the gain matrix is further refined in an iterative framework. With this formulation, a data-driven optimization algorithm is summarized for controller synthesis with structural constraints. This data-driven approach has the key advantage that it avoids the necessity of precise modeling which is always required in the classical model-based counterpart; and thus the approach can additionally accommodate various model uncertainties. Illustrative examples are also provided in the work to validate the theoretical results.

Key Issues and Solutions in the Study of Quantitative Mechanisms for Tropical Islands Zero Carbon Buildings

Faced with the challenges of global climate change, zero-carbon buildings (ZCB) serve as a crucial means to achieve carbon peak and carbon neutrality goals, particularly in the development of tropical island regions. This study aims to establish a ZCB technology system suitable for the unique climatic conditions of tropical islands. By employing methods such as energy flow boundaries, parametric design, and data-driven optimization algorithms, the research systematically analyzes the integrated mechanisms and optimization solutions for energy utilization, energy conservation, energy production, and intelligent systems. The study identifies and addresses key technical challenges faced by ZCB in tropical island regions, including the accurate identification of system design parameters, the precise quantification of the relationship between design parameters and building performance, and the comprehensive optimization of technical and economic goals for zero-carbon operational design solutions. The research results not only provide a comprehensive theoretical framework, promoting the development of architectural design theory, but also establish a practical framework for technology and methods, advancing the integration and application of ZCB technology. The study holds significant practical implications for the green transformation of the tropical island construction industry and the realization of national dual-carbon strategic goals. Future research should further explore the applicability of the technology system and the economic feasibility of optimized design solutions, promoting continuous innovation and development in ZCB technology.

Scaling Multiobjective Evolution to Large Data With Minions: A Bayes-Informed Multitask Approach.

In an era of pervasive digitalization, the growing volume and variety of data streams poses a new challenge to the efficient running of data-driven optimization algorithms. Targeting scalable multiobjective evolution under large-instance data, this article proposes the general idea of using subsampled small-data tasks as helpful minions (i.e., auxiliary source tasks) to quickly optimize for large datasets-via an evolutionary multitasking framework. Within this framework, a novel computational resource allocation strategy is designed to enable the effective utilization of the minions while guarding against harmful negative transfers. To this end, an intertask empirical correlation measure is defined and approximated via Bayes' rule, which is then used to allocate resources online in proportion to the inferred degree of source-target correlation. In the experiments, the performance of the proposed algorithm is verified on: 1) sample average approximations of benchmark multiobjective optimization problems under uncertainty and 2) practical multiobjective hyperparameter tuning of deep neural network models. The results show that the proposed algorithm can obtain up to about 73% speedup relative to existing approaches, demonstrating its ability to efficiently tackle real-world multiobjective optimization involving evaluations on large datasets.

A power regulation strategy for heat pipe cooled reactors based on deep learning and hybrid data-driven optimization algorithm

Heat pipe cooled reactors are ideal for use in remote or isolated locations as dependable, small-scale power sources, thanks to their excellent design characteristics. To tackle real-time changes in power demand within a dynamic environment, this research proposes a decision-making strategy for regulating the power of heat pipe cooled reactors. The strategy is founded on a hybrid data-driven optimization algorithm and deep learning, enabling the attainment of safe and efficient control of heat pipe cooled reactors under specified power requirements. Initially, a power forecast model founded on artificial neural networks for heat pipe cooled reactors is established. Then, an appraisal standard for power regulation arrangements, combining reactor safety and operational effectiveness, is developed based on the utility theory. Finally, this study introduces a hybrid data-driven optimization algorithm that efficiently identifies the power regulation scheme with the greatest utility for given power demands. The proposed technique's effectiveness was demonstrated by selecting the power regulation process of the MegaPower heat pipe cooled reactor as an example. The results indicate that the strategy can make steady, accurate, and near-optimal power regulation decisions for any power demand within 20 s.

A Data Stream Ensemble Assisted Multifactorial Evolutionary Algorithm for Offline Data-Driven Dynamic Optimization.

Existing work on offline data-driven optimization mainly focuses on problems in static environments, and little attention has been paid to problems in dynamic environments. Offline data-driven optimization in dynamic environments is a challenging problem because the distribution of collected data varies over time, requiring surrogate models and optimal solutions tracking with time. This paper proposes a knowledge-transfer-based data-driven optimization algorithm to address these issues. First, an ensemble learning method is adopted to train surrogate models to leverage the knowledge of data in historical environments as well as adapt to new environments. Specifically, given data in a new environment, a model is constructed with the new data, and the preserved models of historical environments are further trained with the new data. Then, these models are considered to be base learners and combined as an ensemble surrogate model. After that, all base learners and the ensemble surrogate model are simultaneously optimized in a multitask environment for finding optimal solutions for real fitness functions. In this way, the optimization tasks in the previous environments can be used to accelerate the tracking of the optimum in the current environment. Since the ensemble model is the most accurate surrogate, we assign more individuals to the ensemble surrogate than its base learners. Empirical results on six dynamic optimization benchmark problems demonstrate the effectiveness of the proposed algorithm compared with four state-of-the-art offline data-driven optimization algorithms. Code is available at https://github.com/Peacefulyang/DSE_MFS.git.

Distributed soft video transmission based on hybrid digital and analog scheme

This study presents a novel distributed soft video delivery scheme using hybrid digital and analog framework, which realizes a relatively lightweight encoder as well as good robustness. Specifically, after applying scalar quantization to the interframes, the scaled analog information (quantization error) and the scaled digital information (quantized source) are superimposed and then transmitted. In this way, the proposed scheme directly delivers pseudo-analog symbols over the orthogonal frequency division multiplexing (OFDM) channels and involves no complicated digital codec. Moreover, we utilize cross-frame correlation to implement a distributed paradigm which further reduces the encoder complexity since the complex motion estimation and compensation algorithms are transferred to the decoder. Accordingly, the power distortion optimization scheme, which resolve the allocation of power and the parameters optimization to achieve minimum transmission distortion, is proposed. To solve it, first, we formulate the power distortion expressions regarding quantization parameters and power allocation coefficients. Subsequently, we divide the problem into two sub-problems based on the fast coordinate descent method and further propose a greedy iterative algorithm to optimize them. We also develop a data-driven optimization algorithm based on deep learning that reduces the additional delay brought by the iterative optimization method. At the receiver, we estimate the quantization output and quantization error by the modified linear least squares estimation with the virtual noise variance. Based on the simulation results, the proposed framework has a better performance in terms of peak signal-to-noise ratio and structural similarity than the relevant cutting-edge schemes while maintaining good robustness.

Delve deep: Seismic revolution in acquisition and model building for exploration

Sparse-node acquisition is the latest approach to improve the earth model through the inclusion of ultra-long offsets and low-frequency generating sources. The new designs of node data collections with simultaneous shooting can be deployed on a regional basis, covering thousands of square miles in a cost-effective manner. In complex geologic settings such as salt environments, salt interpretation has a direct impact on subsalt imaging. However, salt interpretation can be quite time intensive and challenging. Full-waveform inversion (FWI), as a data-driven optimization algorithm with full-wavefield modeling, has become an essential tool for earth model building. However, its use in salt tectonic contexts, especially with streamer data collection, is limited because the frequencies acquired are not sufficiently low and the offsets are not sufficiently long. The recent advancement of the objective function enables the application of an FWI workflow, coupled with sparse-node acquisition in the deepwater settings of the Gulf of Mexico, to refine the salt geometry, correct the background velocity error in subsalt, and uncover a basin's structural framework. The increased frequency content of the FWI-updated fields enables us to extract the FWI-derived reflectivity (FDR), which is an image created by the FWI nonlinear iterative process with the full wavefield. Additionally, the classic extraction of amplitude-versus-angle/amplitude-variation-with-offset parameters employs the elastic Zoeppritz formulation to obtain rock-physics volumes and explain the amplitude on the prestack image gathers, which are typically generated by Kirchhoff or reverse time migration (RTM) depth migration. The next step is to substitute these migrations with FWI and output not only the poststack FDR but use it in a prestack mode to aid amplitude analysis at an early stage of model building.

Data-driven discovery of canonical large-scale brain dynamics.

Human behavior and cognitive function correlate with complex patterns of spatio-temporal brain dynamics, which can be simulated using computational models with different degrees of biophysical realism. We used a data-driven optimization algorithm to determine and classify the types of local dynamics that enable the reproduction of different observables derived from functional magnetic resonance recordings. The phase space analysis of the resulting equations revealed a predominance of stable spiral attractors, which optimized the similarity to the empirical data in terms of the synchronization, metastability, and functional connectivity dynamics. For stable limit cycles, departures from harmonic oscillations improved the fit in terms of functional connectivity dynamics. Eigenvalue analyses showed that proximity to a bifurcation improved the accuracy of the simulation for wakefulness, whereas deep sleep was associated with increased stability. Our results provide testable predictions that constrain the landscape of suitable biophysical models, while supporting noise-driven dynamics close to a bifurcation as a canonical mechanism underlying the complex fluctuations that characterize endogenous brain activity.

Data-driven optimization of sampling patterns for MR brain T1ρ mapping.

The goal of this study was to apply a fast data-driven optimization algorithm, called bias-accelerated subset selection, for MR brain T1ρ mapping to generate optimized sampling patterns (SPs) for compressed sensing reconstruction of brain 3D-T1ρ MRI. Five healthy volunteers were recruited, and fully sampled Cartesian 3D-T1ρ MRIs were obtained. Variable density (VD) and Poisson disc (PD) undersampling was used as the input to SP optimization process. The reconstruction used 3 compressed sensing methods: spatiotemporal finite differences, low-rank plus sparse with spatial finite differences, and low rank. The performance of images and T1ρ maps using PD-SP and VD-SP and their optimized sampling patterns (PD-OSP and VD-OSP) were compared to the fully sampled reference using normalized root mean square error (NRMSE). The VD-OSP with spatiotemporal finite differences reconstruction (NRMSE=0.078) and the PD-OSP with spatiotemporal finite differences reconstruction (NRMSE=0.079) at the highest acceleration factors (AF=30) showed the largest improvement compared to the respective nonoptimized SPs (VD NRMSE=0.087 and PD NRMSE=0.149). Prospective undersampling was tested at AF=4, with VD-OSP NRMSE=0.057 versus PD-OSP NRMSE=0.060, with optimized sampling performing better that input PD or VD sampling. For brain T1ρ mapping, the VD-OSP with low rank reconstruction for AFs <10 and VD-OSP with spatiotemporal finite differences for AFs >10 perform better. The study demonstrated that the appropriate use of data-driven optimized sampling and suitable compressed sensing reconstruction technique can be employed to potentially accelerate 3D T1ρ mapping for brain imaging applications.

Data-driven optimization for flutter suppression by using an aeroelastic nonlinear energy sink

Aeroelastic systems are at risk of flutter instabilities which can lead to structural failure. Recently, an innovative design of nonlinear energy sink (NES) has been introduced to suppress flutter instabilities by adding a NES to the flap control surface as a nonlinear energy absorber resulting in a flap-NES. Optimal choice of flap-NES parameters, however, requires a comprehensive characterization of the nonlinear response of the system in the design space. Performing this nonlinear analysis using traditional approaches demands massive theoretical and computational efforts. This work is a foundational study of flap-NES-based flutter control of a typical pitch–plunge section and focuses on obtaining flap-NES parameters using a data-driven optimization algorithm. The optimization is based on a genetic algorithm combined with a recently introduced data-driven bifurcation forecasting method that allows constructing the bifurcation diagram of the system dynamics using limited time series data. Results of this study show that an optimal design of the flap-NES system results in an increased linear flutter speed, reduced post-flutter limit cycle oscillation amplitudes, and improved nature of the bifurcation diagram from subcritical to supercritical.

Offline data‐driven evolutionary optimization based on model selection

• An offline data-driven optimization framework is proposed. • Two model selection criteria are designed for offline optimization. • A model pool with different smoothness is proposed for different problems. • The proposed method is effective compared to other offline methods. In data-driven evolutionary optimization, since different models are suitable for different types of problems, an appropriate surrogate model to approximate the real objective function is of great significance, especially in offline optimization. In this paper, an offline data-driven evolutionary optimization framework based on model selection (MS-DDEO) is proposed. A model pool is constructed by four radial basis function models with different smoothness degrees for model selection. Meanwhile, two model selection criteria are designed for offline optimization. Among them, Model Error Criterion uses some ranking-top data as test set to test the ability to predict optimum. Distance Deviation Criterion estimate reliability by distances between predicted solution and some ranking-top data. Combining the two criteria, we select the most suitable surrogate model for offline optimization. Experiments show that this method can effectively select suitable models for most test problems. Results on the benchmark problems and airfoil design example show that the proposed algorithm is able to handle offline problems with better optimization performance and less computational cost than other state-of-the-art offline data-driven optimization algorithms.

A federated data-driven evolutionary algorithm

Data-driven evolutionary optimization has witnessed great success in solving complex real-world optimization problems. However, existing data-driven optimization algorithms require that all data are centrally stored, which is not always practical and may be vulnerable to privacy leakage and security threats if the data must be collected from different devices. To address the above issue, this paper proposes a federated data-driven evolutionary optimization framework that is able to perform data driven optimization when the data is distributed on multiple devices. On the basis of federated learning, a sorted model aggregation method is developed for aggregating local surrogates based on radial-basis-function networks. In addition, a federated surrogate management strategy is suggested by designing an acquisition function that takes into account the information of both the global and local surrogate models. Empirical studies on a set of widely used benchmark functions in the presence of various data distributions demonstrate the effectiveness of the proposed framework.

Data-driven optimization for process systems engineering applications

Most optimization problems in engineering can be formulated as ‘expensive’ black box problems whose solutions are limited by the number of function evaluations. Frequently, engineers develop accurate models of physical systems that are differentiable and/or cheap to evaluate. These models can be solved efficiently, and the solution transferred to the real system. In the absence of gradient information or cheap-to-evaluate models, one must resort to efficient optimization routines that rely only on function evaluations. Creating a model can itself be considered part of the expensive black box optimization process. In this work, we investigate how perceived state-of-the-art derivative-free optimization (DFO) algorithms address different instances of these problems in process engineering. On the algorithms side, we benchmark both model-based and direct-search DFO algorithms. On the problems side, the comparisons are made on one mathematical optimization problem and five chemical engineering applications: model-based design of experiments, flowsheet optimization, real-time optimization, self-optimizing reactions, and controller tuning. Various challenges are considered such as constraint satisfaction, uncertainty, problem dimension and evaluation cost. This work bridges the gap between the derivative-free optimization and process systems literature by providing insight into the efficiency of data-driven optimization algorithms in the process systems domain to advance the digitalization of the chemical and process industries.

Multi-objective data-driven optimization for improving deep brain stimulation in Parkinson’s disease

Objective. Deep brain stimulation (DBS) is an effective treatment for Parkinson’s disease (PD) but its success depends on a time-consuming process of trial-and-error to identify the optimal stimulation settings for each individual patient. Data-driven optimization algorithms have been proposed to efficiently find the stimulation setting that maximizes a quantitative biomarker of symptom relief. However, these algorithms cannot efficiently take into account stimulation settings that may control symptoms but also cause side effects. Here we demonstrate how multi-objective data-driven optimization can be used to find the optimal trade-off between maximizing symptom relief and minimizing side effects. Approach. Cortical and motor evoked potential data collected from PD patients during intraoperative stimulation of the subthalamic nucleus were used to construct a framework for designing and prototyping data-driven multi-objective optimization algorithms. Using this framework, we explored how these techniques can be applied clinically, and characterized the design features critical for solving this optimization problem. Our two optimization objectives were to maximize cortical evoked potentials, a putative biomarker of therapeutic benefit, and to minimize motor potentials, a biomarker of motor side effects. Main Results. Using this in silico design framework, we demonstrated how the optimal trade-off between two objectives can substantially reduce the stimulation parameter space by 61 ± 19%. The best algorithm for identifying the optimal trade-off between the two objectives was a Bayesian optimization approach with an area under the receiver operating characteristic curve of up to 0.94 ± 0.02, which was possible with the use of a surrogate model and a well-tuned acquisition function to efficiently select which stimulation settings to sample. Significance. These findings show that multi-objective optimization is a promising approach for identifying the optimal trade-off between symptom relief and side effects in DBS. Moreover, these approaches can be readily extended to newly discovered biomarkers, adapted to DBS for disorders beyond PD, and can scale with the development of more complex DBS devices.

A framework for designing data-driven optimization systems for neural modulation

Objective. Neural modulation is a fundamental tool for understanding and treating neurological and psychiatric diseases. However, due to the high-dimensional space, subject-specific responses, and variability within each subject, it is a major challenge to select the stimulation parameters that have the desired effect. Data-driven optimization provides a range of different algorithms and tools for addressing this challenge, but each of these algorithms has specific strengths and limitations, and therefore must be carefully designed for a given neural modulation problem. Here we present a framework for designing data-driven optimization algorithms for neural modulation. Approach. We develop this framework using an optogenetic medial septum stimulation model, where the goal is to find the stimulation parameters that modulate hippocampal gamma power to a desired value. This framework proceeds in four steps: (a) collecting stimulation data, (b) creating high-throughput simulation models, (c) prototyping a range of different data-driven optimization algorithms and evaluating their performance, and (d) deploying the best performing algorithm in vivo. Main results. Following this framework, we prototype and design an algorithm specifically for finding the medial septum optogenetic stimulation parameters that maximize hippocampal gamma power. Building on this, we then change our objective function to find the stimulation parameters that modulate gamma to a specific setpoint, use the framework to understand and anticipate the results before deploying in vivo. Significance. We show that this framework can be used to design an effective optimization solution for a specific neural modulation problem, and discuss how it can potentially be applied beyond the optogenetic medial septum stimulation model.

Bi-level Mixed-Integer Data-Driven Optimization of Integrated Planning and Scheduling Problems

Supply chain management is an interconnected problem that requires the coordination of various decisions and elements across long-term (i.e., supply chain structure), medium-term (i.e., production planning), and short-term (i.e., production scheduling) operations. Traditionally, decision-making strategies for such problems follow a sequential approach where longer-term decisions are made first and implemented at lower levels, accordingly. However, there are shared variables across different decision layers of the supply chain that are dictating the feasibility and optimality of the overall supply chain performance. Multi-level programming offers a holistic approach that explicitly accounts for this inherent hierarchy and interconnectivity between supply chain elements, however, requires more rigorous solution strategies as they are strongly NP-hard. In this work, we use the DOMINO framework, a data-driven optimization algorithm initially developed to solve single-leader single-follower bi-level mixed-integer optimization problems, and further develop it to address integrated planning and scheduling formulations with multiple follower lower-level problems, which has not received extensive attention in the open literature. By sampling for the production targets over a pre-specified planning horizon, DOMINO deterministically solves the scheduling problem at each planning period per sample, while accounting for the total cost of planning, inventories, and demand satisfaction. This input-output data is then passed onto a data-driven optimizer to recover a guaranteed feasible, near-optimal solution to the integrated planning and scheduling problem. We show the applicability of the proposed approach for the solution of a two-product planning and scheduling case study.

Offline data-driven evolutionary optimization based on tri-training

Abstract In offline data-driven evolutionary optimization, no real fitness evaluations is allowed during the optimization, making it extremely challenging to build high-quality surrogates on limited amount of data. This is especially true for large-scale optimization problems where typically a large amount of data is needed for constructing reliable surrogate models. To overcome the data deficiency, semi-supervised learning is introduced to the offline data-driven evolutionary optimization process, where tri-training, a co-training variant, is used to update surrogate models. In the proposed algorithm, a tri-training algorithm selects candidate solutions with high-confidence fitness prediction to enrich the training data for surrogate models. The results on benchmark problems show that the proposed algorithm, compared with three most recent offline data-driven optimization algorithms, is competitive on the problems of up to 500 decision variables.

Recovery of energy losses using an online data-driven optimization technique

This paper investigates the energy loss due to rotor aging for a wind turbine and its recovery. Energy loss for a wind turbine is caused by formation of dust and bugs, and corrosion and erosion of the surface of the rotor by sand and rain. We present a real-time data-driven optimization algorithm that uses dither and demodulation signals to recover the energy loss by extracting online the sensitivity of the function of interest to optimize. We use a viscid–inviscid model to represent aerodynamic performance loss of the rotor due to aging. We employ time-domain aeroservoelastic simulation of the CART3 wind turbine of the National Renewable Energy Laboratory to provide a comprehensive assessment of aging and its recovery. We also investigate the impact of aging on structural loads and levelized cost of energy. Using annual energy production and WindPACT cost models of the National Renewable Energy Laboratory, the levelized cost of energy enables an overall assessment of aging and its recovery. To evaluate the impact of the energy loss recovery on structural loading, ultimate and fatigue loads for power production design load case are used. The results of this study show 6.9% reduction in the annual energy production due to aging for a class C wind condition based on IEC61400 standard. This energy loss increases the levelized cost of energy by 7.5%. Our online optimization algorithm can recover 1.7% of the energy losses, and it results in 2.0% reduction in the levelized cost of energy. Results of the ultimate loads indicate that an aged rotor reduces structural loading on most components except the main shaft where the bending moment shows an increase of 5.3%. Rotor aging also reduces the fatigue loads in most components except the tower bottom fore-aft moment with an increase of 5.5%. The statistical inference of the results shows that the proposed optimization algorithm is effective in recovering aging related energy losses of wind turbines with a confidence level of 84% based on the sampled data in this study.

Atomistic simulation and evolutionary optimization of Fe-Cr nanoparticles

ABSTRACT Iron-chromium nanoparticles have some very important real-life applications, for example in trapping the He bubbles in the nuclear reactors or as catalysts in organic reactions, e.g. the reduction of substituted aromatic ketones to alcohol. The only parameter which can be tweaked in Iron nanoparticles is their size. Once it is fixed, the properties of the particle are fixed. The addition of chromium implies there is more parameter to tune (along with the particle size), i.e. the concentration of chromium in the nanoparticle. Molecular dynamics is used to simulate the particle system, calculate the required parameters (average cohesive energy and average surface energy) for them under both static and dynamic loading conditions and then using the evolutionary data-driven modeling is used to optimize the particle parameters for finding out the best feasible parameters, that lead to the generation of a stable nanoparticle with properties suitable for practical applications. We find that using molecular dynamics along with a variety of evolutionary data-driven optimization algorithms provides the desired results, i.e., a variety of Fe-Cr nanoparticles with a range of diameters and compositions to choose from, in order to design alloys or catalysts with high surface energies and low cohesive energies.

Improving Efficiency of Volunteer-Based Food Rescue Operations

Food waste and food insecurity are two challenges that coexist in many communities. To mitigate the problem, food rescue platforms match excess food with the communities in need, and leverage external volunteers to transport the food. However, the external volunteers bring significant uncertainty to the food rescue operation. We work with a large food rescue organization to predict the uncertainty and furthermore to find ways to reduce the human dispatcher's workload and the redundant notifications sent to volunteers. We make two main contributions. (1) We train a stacking model which predicts whether a rescue will be claimed with high precision and AUC. This model can help the dispatcher better plan for backup options and alleviate their uncertainty. (2) We develop a data-driven optimization algorithm to compute the optimal intervention and notification scheme. The algorithm uses a novel counterfactual data generation approach and the branch and bound framework. Our result reduces the number of notifications and interventions required in the food rescue operation. We are working with the organization to deploy our results in the near future.