Optimization-based Approach Research Articles

Accuracy-diversity optimization in personalized recommender system via trajectory reinforcement based bacterial colony optimization

Personalized recommender systems have been extensively studied in human-centered intelligent systems. Existing recommendation techniques have achieved comparable performance in predictive accuracy; however, the trade-off between recommendation accuracy and diversity poses new challenges, as diversification may lead to accuracy loss, whereas it can solve the over-fitting problem and enhance the user experience. In this study, we propose a heuristic optimization-based recommendation model that jointly optimizes accuracy and diversity performance by obtaining a set of optimized solutions. To establish the best accuracy-diversity balance, a novel trajectory-reinforcement-based bacterial colony optimization algorithm was developed. The improved bacterial colony optimization algorithm was comprehensively evaluated by comparing it with eight popular and state-of-the-art algorithms on ten benchmark testing problems with different degrees of complexity. Furthermore, an optimization-based recommendation model was applied to a real-world recommendation dataset. The results demonstrate that the improved bacterial colony optimization algorithm achieves the best overall performance for benchmark problems in terms of convergence and diversity. In the real-world recommendation task, the proposed approach improved the diversity performance by 1.62% to 8.62% while maintaining superior (1.88% to 40.32%) accuracy performance. Additionally, the proposed personalized recommendation model can provide a set of nondominated solutions instead of a single solution to accommodate the ever-changing preferences of users and service providers. Therefore, this work demonstrates the excellence of an optimization-based recommendation approach for solving the accuracy-diversity trade-off.

Wastewater System Integration: A Biogenic Waste Biorefinery Eco-Industrial Park

In recent years, great interest has been shown in the utilization of biogenic wastes in biorefineries as part of the concept of a circular bioeconomy. However, various challenges arise including the availability, cost and characteristics of the biogenic wastes in ensuring consistent biorefinery production processes. This work presents an optimization-based approach of a biogenic waste biorefinery eco-industrial park (BWB EIP). An indirect integration scheme is presented with a wastewater treatment plant (WWTP) acting as a centralized utility hub to treat the biogenic wastes generated from the participating plants and to supply volatile fatty acid (VFA) demanded by the participating plants through the WWTP interceptors. The objective of minimizing the VFA demanded by the participating plants from external sources is achieved. To further assess the influence of a future increase in VFA demand for one of the participating plants which is the polyhydroxyalkanoate (PHA) plant on the integration network, a sensitivity analysis is conducted. The results indicated that two WWTP interceptors are required with a 32.8% and 27.4% reduction in fresh VFA from external sources achieved through the integration network before and after sensitivity analysis. This work provides an insight into developing the framework for other BWB processes.

Measurement and ranking of important link combinations in the analysis of transportation network vulnerability envelope buffers under multiple-link disruptions

This study proposes an optimization-based approach to rank the importance of link combinations and analyze network vulnerability in extreme and near-extreme cases of disruption under the simultaneous disruption of multiple links. A vulnerability envelope concept is used, which considers the worst and best network performance under multiple-link disruptions. This study goes a step further than previous studies, which have focused on the extreme cases that form the boundary of a vulnerability envelope, to investigate the near-extreme cases inside an envelope and the network performance buffers (i.e., the differences in network performance) between different cases. A flexible framework based on combinatorial optimization modeling is used to determine the most important link combinations and the lower and upper bounds of network performance under their disruptions, which form the vulnerability envelope. A constraint-based method is developed to iteratively identify sub-important link combinations that lead to the formation of buffers of the lower and upper bounds of the vulnerability envelope. Numerical experiments are conducted to illustrate the properties and applicability of the proposed method. The results demonstrate that the consideration of near-extreme cases yields additional valuable information that is not generated by the traditional vulnerability analysis, which is focused on extreme cases. Ranking of the most and sub-most important link combinations enables the identification of non-unique worst/best cases, thereby revealing alternative link combinations to better inform decision-making. Consideration of the network performances in extreme and near-extreme cases affords a less conservative vulnerability assessment and reveals the potential cost of considering only extreme cases in decision-making processes.

Tabular Open Circuit Voltage Modelling of Li-Ion Batteries for Robust SOC Estimation

Battery management systems depend on open circuit voltage (OCV) characterization for state of charge (SOC) estimation in real time. The traditional approach to OCV-SOC characterization involves collecting OCV-SOC data from sample battery cells and then fitting a polynomial model to this data. The parameters of these polynomial models are known as the OCV-parameters, or OCV-SOC parameters, in battery management systems and are used for real-time SOC estimation. Even though traditional OCV-SOC characterization approaches are able to abstract the OCV-SOC behavior of a battery in a few parameters, these parameters are only applicable in high precision computing systems. However, many practical battery applications do not have access to high-precision computing resources. The typical approach in a low-precision system is to round the OCV-parameters. This paper highlights the perils of rounding the OCV parameters and proposes an alternative OCV-SOC table. First, several existing OCV-SOC parameters are compared in terms of their expected system requirements and accuracy losses due to rounding. Then, a systematic optimization-based approach is introduced to create an OCV-SOC table that is robust to rounding. A formal performance evaluation metric is introduced to measure the robustness of the resulting OCV-SOC table. It is shown that the OCV-SOC table obtained through the proposed optimization approach outperforms the traditional parametric OCV-SOC models with respect to rounding.

Dynamic job shop scheduling based on deep reinforcement learning for multi-agent manufacturing systems

• The manufacturing equipment in the workshop is constructed as an equipment agent with the support of edge computing node, and a multi-agent manufacturing system with the ability of online scheduling and scheduling strategy optimization is presented. • A self-organizing negotiation mechanism based on contract network protocol (CNP) is proposed to guide the cooperation and competition among multiple agents , and to provide support for intelligent decision-making. • The decision-making module of equipment agent called artificial intelligence (AI) scheduler is established based on the multi-layer perceptron, and enables the manufacturing equipment to intelligently generate an optimal production strategy according to the perceived workshop state. • An adaptive learning strategy of AI scheduler based on proximal policy optimization (PPO) algorithm is proposed to improve its decision-making performance under the disturbance of orders and resources. • Experimental results show that the proposed methodology achieves better performance in terms of production strategy learning and disturbance handling compared with other optimization-based approaches and dispatching rules . Personalized orders bring challenges to the production paradigm, and there is an urgent need for the dynamic responsiveness and self-adjustment ability of the workshop. Traditional dispatching rules and heuristic algorithms solve the production planning and control problems by making schedules. However, the previous methods cannot work well in a changeable workshop environment when encountering a large number of stochastic disturbances of orders and resources. Recently, the potential of artificial intelligence (AI) algorithms in solving the dynamic scheduling problem has attracted researchers' attention. Therefore, this paper presents a multi-agent manufacturing system based on deep reinforcement learning (DRL), which integrates the self-organization mechanism and self-learning strategy. Firstly, the manufacturing equipment in the workshop is constructed as an equipment agent with the support of edge computing node, and an improved contract network protocol (CNP) is applied to guide the cooperation and competition among multiple agents, so as to complete personalized orders efficiently. Secondly, a multi-layer perceptron is employed to establish the decision-making module called AI scheduler inside the equipment agent. According to the perceived workshop state information, AI scheduler intelligently generates an optimal production strategy to perform task allocation. Then, based on the collected sample trajectories of scheduling process, AI scheduler is periodically trained and updated through the proximal policy optimization (PPO) algorithm to improve its decision-making performance. Finally, in the multi-agent manufacturing system testbed, dynamic events such as stochastic job insertions and unpredictable machine failures are considered in the verification experiments. The experimental results show that the proposed method is capable of obtaining the scheduling solutions that meet various performance metrics, as well as dealing with resource or task disturbances efficiently and autonomously.

Optimization-Based Decision-Making Approach for Incorporating the Length Constraint of Preventive Maintenance into Pavement Maintenance and Rehabilitation Planning

Optimization-Based Decision-Making Approach for Incorporating the Length Constraint of Preventive Maintenance into Pavement Maintenance and Rehabilitation Planning

From Inertial Measurements to Smart Cities [About This Issue

Autonomous vehicle technology is advancing rapidly. Their control capabilities often rely on high-bandwidth state estimation incorporating inertial measurements. High-performance state estimation incorporates inertial measurement error models through the process of state augmentation to enable on-the-fly instrument calibration. The feature article “Inertial Measurement Unit Error Modeling Tutorial” by Jay A. Farrell, Felipe O. Silva, Farzana Rahman, and J. Wendel provides a tutorial describing the process and issues related to developing a state-space model for the stochastic errors affecting an inertial measurement unit (IMU). The starting point is the instrument error characterization data sheet provided by the manufacturer, which is typically either an Allan standard deviation graph or the Allan variance parameters extracted from that graph. The desired output of the modeling process is a linear, discrete-time, state-space model of the IMU stochastic errors suitable for augmentation to the INS error-state model. Along with this tutorial, supplementary open source software is available. One software component does the following: 1) Given a continuous-time state-space IMU stochastic error model selected by the designer to match the Allan variance, the software computes a discrete-time equivalent state-space model. 2) Given that discrete-time model, it produces a stochastic error sequence suitable for Allan variance computations. 3) Given a sequence of stochastic errors, it computes and plots the Allan variance. Given Allan variance data and a specific continuous-time state-space IMU stochastic error model structure, a second software component implements an optimization-based approach for selecting the model parameters to match the Allan variance data.

Model predictive control of a thermal chimney and dynamic solar shades for an all-glass facades building

Controlling the operation of HVAC (Heating, Ventilation, and Air-Conditioning) systems is arguably the most effective way to reach desired indoor conditions in buildings. Nevertheless, such control may involve complex dynamics when dealing with passive energy technologies. In this paper, we focus on maximizing the passive operation of HVAC in a novel low-energy building design by means of Model Predictive Control (MPC). The low-energy building design, located in The Green Village, consists of a thermal chimney and solar shades over all-glass facades to provide the required indoor air conditioning as passively as possible. The MPC controller is based on a transient grey box model and a hierarchical control architecture to satisfy thermal comfort while minimizing the active energy requirements. Using sensor data collected from the actual building in April and May 2021, the grey box model shows a good agreement with the measurements, since the variance accounted for is 90% in most cases. Moreover, via a comparative study among different MPC architectures we show that managing the distinct transient response of each component (shades and chimney) is the best for successful overall performance – e.g. considering linear agents for shading and nonlinear agents for ventilation. The hierarchical MPC architecture established outperforms the standard ones by 22.7% in terms of control performance. We also compare the proposed MPC approach against the rule-based control method currently implemented in the actual building, which indicates that MPC demands about 78% less active energy, highlighting the proposed optimization-based control approach.

Model predictive control for retinal laser treatment at 1 kHz

Abstract Laser photocoagulation is a technique applied in the treatment of retinal disease, which is often done manually or using simple control schemes. We pursue an optimization-based approach, namely Model Predictive Control (MPC), to enforce bounds on the peak temperature and, thus, to ensure safety during the medical treatment procedure – despite the spot-dependent absorption of the tissue. The desired laser repetition rate of 1 kHz is renders the requirements on the computation time of the MPC feedback a major challenge. We present a tailored MPC scheme using parametric model reduction, an extended Kalman filter for the parameter and state estimation, and suitably tuned stage costs and verify its applicability both in simulation and experiments with porcine eyes. Moreover, we give some insight on the implementation specifically tailored for fast numerical computations.

An efficient hybrid grey wolf optimization-based KELM approach for prediction of the discharge coefficient of submerged radial gates

Accurately prediction of discharge coefficient through radial gates is considered as a challenging hydraulic subject, particularly under highly submerged flow conditions. Incurring the advantages of kernel-depend extreme learning machine (KELM), this study offers a grey wolf optimization-based KELM (GWO-KELM) for effective prediction of discharge coefficient through submerged radial gates. Additionally, support vector machine (SVM) and Gaussian process regression (GPR) methods are also presented for comparative purposes. To build prediction models using GWO-KELM, GPR, and SVM, an extensive experimental database was established, consisting of 2125 data samples gathered by the US Bureau of Reclamation. From simulation results, it is observed that the proposed GWO-KELM approach with radial basis function and input parameters of the ratio of the downstream flow depth to the gate opening and submergence ratio provides the best performance with the correlation coefficient (R) of 0.983, the determination coefficient (DC) of 0.966 and the root-mean-squared error (RMSE) of 0.027. The obtained results showed that the proposed GWO-KELM with RBF kernel function gives better prediction accuracy than employed GPR and SVM approaches. Furthermore, the obtained results showed that the employed kernel-depend methods are capable of a statistically predicting the discharge coefficient under varied submergence conditions with satisfactory level of accuracy. Amon theme, proposed hybrid GWO-KELM method gave the most accurate results (R = 0.873, DC = 0.744, and RMSE = 0.035) for extremely highly submerged flow. Moreover, the results reflected that the employed kernel-depend methods give better predictions than the developed dimensionless formulas.

Evaluating port efficiency dynamics: A risk-based approach

This study proposes a new methodology to quantify the efficiency dynamics of a port over time. While efficiency evaluation has gained full attention in port management, researchers conducting related studies are challenged by temporal variations observed in the collected data. Existing approaches have almost exclusively relied on multivariate normal distributional assumptions of the input and output data, but empirical evidence from real data shows that the port operations data demonstrate long-tail distributions and violate the distributional assumptions. In addition, many existing models are intractable (non-convex) or lack interpretability. Motivated by these challenges, we develop an optimization-based approach for efficiency measurement under uncertainty that is compatible with the conventional non-parametric method. In particular, inspired by the coherent risk measure, we create a risk-based index to measure the efficiency of any operating unit by comparing its observations against a benchmark that is guaranteed to be production possible under a certain risk level. To facilitate the computation of the index, we develop a risk-based port efficiency evaluation (RPE) model, which can be reformulated as an exponential cone program (ECP) and solved efficiently by off-the-shelf solvers. We test our model for a multipurpose port on a real dataset of 3,394 observations showing the proposed approach’s merits. We find that the port productivity peaks on Tuesday and Saturday and troughs on Friday. We also provide evidence for the Chinese New Year effect from a port management perspective and draw managerial insights from the study.

Berth planning and real-time disruption recovery: a simulation study for a tidal port

With the increasing volume of container freight transport, future port planning is crucial. Simulation models provide a means to gain insight in the effects of terminal expansions. Detailed simulations incorporate berth allocation: assigning vessels a time and location at the quay wall, where the vessel is loaded and unloaded. This article develops decision models for both offline preliminary berth planning and for online recovery of this plan during simulation. First, we develop an optimisation-based approach that incorporates realistic aspects—cyclic vessel arrivals, tidal windows, and minimisation of vessel draught during low water periods—in order to develop a cyclic baseline berth allocation plan. The approach can proactively incorporate slack for increased robustness. Exploiting a constraint-based solver, we can obtain optimal or satisficing solutions for a year’s operation of a large port. The resulting preliminary berth plan is used as a basis for the arrival times. However, disruptions can occur, such as vessel arrival and loading times varying from the planned. Hence, second, we develop a real-time disruption management decision model. This multi-level heuristic approach reacts to disruptions while minimising perturbation of the original berth plan. Computational experiments with a high-resolution simulator show our recovery approach finds good solutions until a tipping point of disturbance. Results also show that when the expected occupation of a terminal is higher, strengthening robustness of the preliminary plan has increased importance. The approach described in the article is implemented for a major European inland tidal port, forming the basis of a simulation-based decision support tool for operational planning and exploring port expansion options.

An Event Matching Energy Disaggregation Algorithm Using Smart Meter Data

Energy disaggregation algorithms disintegrate aggregate demand into appliance-level demands. Among various energy disaggregation approaches, non-intrusive load monitoring (NILM) algorithms requiring a single sensor have gained much attention in recent years. Various machine learning and optimization-based NILM approaches are available in the literature, but bulk training data and high computational time are their respective drawbacks. Considering these drawbacks, we devised an event matching energy disaggregation algorithm (EMEDA) for NILM of multistate household appliances using smart meter data. Having limited training data, K-means clustering was employed to estimate appliance power states. These power states were accumulated to generate an event database (EVD) containing all combinations of appliance operations in their various states. Prior to matching, the test samples of aggregate demand events were decreased by event-driven data compression for computational effectiveness. The compressed test events were matched in the sorted EVD to assess the contribution of each appliance in the aggregate demand. To counter the effects of transient spikes and/or dips that occurred during the state transition of appliances, a post-processing algorithm was also developed. The proposed approach was validated using the low-rate data of the Reference Energy Disaggregation Dataset (REDD). With better energy disaggregation performance, the proposed EMEDA exhibited reductions of 97.5 and 61.7% in computational time compared with the recent smart event-based optimization and optimization-based load disaggregation approaches, respectively.

Chaotic-Enabled Phase Modulation in Time-Modulated Arrays for Secure Transmission

The “time” factor in time-modulated arrays (TMAs) offers a new degree of freedom for securing wireless communication. However, the widely used periodic time modulation introduces limited randomness for eavesdropping receivers, and thus gives weak security. To meet this challenge, this work proposes a TMA with chaotic-enabled phase modulation (CPM) for secure transmission. The proposed CPM technique offers the chaos features of high randomness, unpredictability, and initial condition sensitive characteristic, to increase the information uncertainty for eavesdropping receivers. An optimization-based time sequence design approach is introduced to design optimal CPM time sequences for secure transmission in a given direction. Thus, a variety of security strategies including beam scanning, directional modulation (DM), and chaotic encryption are simultaneously enabled by the optimized CPM time sequence. Moreover, the CPM is a radio frequency (RF)-domain security technique without requiring any baseband modulation modules, which exhibits a simplified hardware architecture. Numerical analysis and experimental results are presented to illustrate the effectiveness of the proposed CPM technique. The results indicate that the security is improved by lowering the bit error rate (BER) between the legitimate receiver and the transmitter, and reducing the mutual information between eavesdropping receivers and the transmitter.

Utility-scale energy storage system for load management under high penetration of electric vehicles: A marginal capacity value-based sizing approach

To determine a trade-off between the battery energy storage system (BESS) size and corresponding benefits in managing the load of distribution systems under high penetration of electric vehicles (EVs), a marginal capacity value-based sizing approach is proposed in this study. First, the yearly load profiles of EVs are estimated considering different factors, such as EV parameters, driver behavior, day types, and customers at each secondary distribution transformer. Then, a utilization index is proposed to quantify the benefits of increasing the BESS size. To this end, an iterative method is proposed to determine the BESS size with a given utilization target. To expedite the convergence speed, a binary and interpolation search-inspired algorithm is proposed, which can determine the BESS size within a limited number of iterations. The performance of the proposed BESS sizing approach is compared with three other approaches, i.e., optimization-based sizing approach, metaheuristic sizing approach, and enumeration-based sizing approach. The obtained results are tested and validated using the data of a real distribution system. Finally, a sensitivity analysis of different user defined factors such as granularity level in BESS size and utilization target levels is carried out. Simulation results have shown that the proposed method can significantly reduce the BESS size while having minute impact on the peak shaving.

Control Approach to Fault Disambiguation

To ensure resilience, systems must be endowed with capabilities for rapid detection, response, and recovery to disruptiveevents. In this paper we focus on faults as disruptive events and use a diagnosis engine for their detection and isolation. In particular we use model-based diagnosis, where the diagnosis engine is provided with a model of the system, nominal values of the parameters of the model and values of some of its inputs and outputs. However, there is no guarantee that the information measured by sensors is sufficient to distinguish between multiple root-causes. We address this challenge using an optimal control approach: we design control inputs such that the similarity between outputs in ambiguous fault modes is reduced. We show that under certain assumptions on the system model, minimizing a similarity metric in terms of outputs is equivalent to increasing the diagnosis certainty. We use an optimization-based approach to input design, where the system model acts as a constraint. We show that by using a surrogate model expressed with constructs endowed with differential operators, we improve the time efficiency of the optimal control problem. We demonstrate our approach on a fuel line system, where feedback control is used to ensure the mass flow rate at the engine follows a prescribed reference. We consider leak faults that affect the fuel lines. We show that under the control inputs generated by the nominal controller, mass flow rate measurements are not enough to accurately isolate leaks. We demonstrate that by using custom inputs that minimize the similarity between the outputs in the ambiguous faults modes, the diagnosis uncertainty is eliminated.

Adaptive Nonlinear Model Predictive Horizon Using Deep Reinforcement Learning for Optimal Trajectory Planning

This paper presents an adaptive trajectory planning approach for nonlinear dynamical systems based on deep reinforcement learning (DRL). This methodology is applied to the authors’ recently published optimization-based trajectory planning approach named nonlinear model predictive horizon (NMPH). The resulting design, which we call ‘adaptive NMPH’, generates optimal trajectories for an autonomous vehicle based on the system’s states and its environment. This is done by tuning the NMPH’s parameters online using two different actor-critic DRL-based algorithms, deep deterministic policy gradient (DDPG) and soft actor-critic (SAC). Both adaptive NMPH variants are trained and evaluated on an aerial drone inside a high-fidelity simulation environment. The results demonstrate the learning curves, sample complexity, and stability of the DRL-based adaptation scheme and show the superior performance of adaptive NMPH relative to our earlier designs.

Wide-Band Butterfly Network: Stable and Efficient Inversion Via Multi-Frequency Neural Networks

We introduce an end-to-end deep learning architecture called the wide-band butterfly network (WideBNet) for approximating the inverse scattering map from wide-band scattering data. This architecture incorporates tools from computational harmonic analysis, such as the butterfly factorization, and traditional multi-scale methods, such as the Cooley–Tukey FFT algorithm, to drastically reduce the number of trainable parameters to match the inherent complexity of the problem. As a result, WideBNet is efficient: it requires fewer training points than off-the-shelf architectures and has stable training dynamics which are compatible with standard weight initialization strategies. The architecture automatically adapts to the dimensions of the data with only a few hyper-parameters that the user must specify. WideBNet is able to produce images that are competitive with optimization-based approaches, but at a fraction of the cost, and we also demonstrate numerically that it learns to super-resolve scatterers with a full aperture configuration.

A weight optimization-based transfer learning approach for plant disease detection of New Zealand vegetables.

Deep learning (DL) is an effective approach to identifying plant diseases. Among several DL-based techniques, transfer learning (TL) produces significant results in terms of improved accuracy. However, the usefulness of TL has not yet been explored using weights optimized from agricultural datasets. Furthermore, the detection of plant diseases in different organs of various vegetables has not yet been performed using a trained/optimized DL model. Moreover, the presence/detection of multiple diseases in vegetable organs has not yet been investigated. To address these research gaps, a new dataset named NZDLPlantDisease-v2 has been collected for New Zealand vegetables. The dataset includes 28 healthy and defective organs of beans, broccoli, cabbage, cauliflower, kumara, peas, potato, and tomato. This paper presents a transfer learning method that optimizes weights obtained through agricultural datasets for better outcomes in plant disease identification. First, several DL architectures are compared to obtain the best-suited model, and then, data augmentation techniques are applied. The Faster Region-based Convolutional Neural Network (RCNN) Inception ResNet-v2 attained the highest mean average precision (mAP) compared to the other DL models including different versions of Faster RCNN, Single-Shot Multibox Detector (SSD), Region-based Fully Convolutional Networks (RFCN), RetinaNet, and EfficientDet. Next, weight optimization is performed on datasets including PlantVillage, NZDLPlantDisease-v1, and DeepWeeds using image resizers, interpolators, initializers, batch normalization, and DL optimizers. Updated/optimized weights are then used to retrain the Faster RCNN Inception ResNet-v2 model on the proposed dataset. Finally, the results are compared with the model trained/optimized using a large dataset, such as Common Objects in Context (COCO). The final mAP improves by 9.25% and is found to be 91.33%. Moreover, the robustness of the methodology is demonstrated by testing the final model on an external dataset and using the stratified k-fold cross-validation method.

A hybrid constrained Particle Swarm Optimization-Model Predictive Control (CPSO-MPC) algorithm for storage energy management optimization problem in micro-grid

This paper investigates energy management systems in micro-grid using an optimization-based approach, optimizing the operating cost related to the energy purchased from the utility grid, the operation cost of the energy storage system, and revenue from the selling of energy to the utility grid. This research uses a constrained Particle Swarm Optimization-Based Model Predictive Control (CPSO-MPC) and a Linear Program-Based Optimization approach to solve the constrained optimization problem formulated in micro-grid energy management. Due to the absence of constraint management strategies in the traditional PSO algorithm, it is incapable of solving constrained optimization problems. Hence, to overcome this drawback, an intuitive approach known as Deb’s rule is applied to handle the constraints. The simulation results show the modified particle swarm optimization’s effective performance embedded in the model predictive control algorithm compared to the linear programming algorithm.