A comparative study of meta-heuristic and conventional optimization techniques of grid connected photovoltaic system

This paper presents the meta-heuristic and conventional optimizations techniques for the grid connected photovoltaic solar system. The perturb and observe (P&O) and particle swarm optimization (PSO) algorithms are proposed to track the maximum power point (MPP) of the photovoltaic solar system (PVSS). The regularization of the current supplied into the grid is ensured by the proportional integral (PI) corrector whose parameters are generated by the genetic algorithm (GA). The results of these two MPPT methods are compared and showed that the PSO is more efficient than the P&O. The use of GA algorithm to determine PI parameters allowed to obtain 0.89% of total distortion harmonic (THD).

Intelligent Interference Management in UAV-Based HetNets

Unmanned aerial vehicles (UAVs) can play a key role in meeting certain demands of cellular networks. UAVs can be used not only as user equipment (UE) in cellular networks but also as mobile base stations (BSs) wherein they can either augment conventional BSs by adapting their position to serve the changing traffic and connectivity demands or temporarily replace BSs that are damaged due to natural disasters. The flexibility of UAVs allows them to provide coverage to UEs in hot-spots, at cell-edges, in coverage holes, or regions with scarce cellular infrastructure. In this work, we study how UAV locations and other cellular parameters may be optimized in such scenarios to maximize the spectral efficiency (SE) of the network. We compare the performance of machine learning (ML) techniques with conventional optimization approaches. We found that, on an average, a double deep Q learning approach can achieve 93.46% of the optimal median SE and 95.83% of the optimal mean SE. A simple greedy approach, which tunes the parameters of each BS and UAV independently, performed very well in all the cases that we tested. These computationally efficient approaches can be utilized to enhance the network performance in existing cellular networks.

Optimal design of aerospace structures using recent meta-heuristic algorithms

Most conventional optimization approaches are deterministic and based on the derivative information of a problem’s function. On the other hand, nature-inspired and evolution-based algorithms have a stochastic method for finding the optimal solution. They have become a more popular design and optimization tool, with a continually growing development of novel algorithms and new applications. Flexibility, easy implementation, and the capability to avoid local optima are significant advantages of these algorithms. In this study, shapes, and shape perturbation limits of a bracket part, which is used in aviation, have been set using the hypermorph tool. The objective function of the optimization problem is minimizing the volume, and the constraint is maximum von Mises stress on the structure. The grey wolf optimizer (GWO) and the moth-flame Optimizer (MFO) have been selected as nature-inspired evolution-based optimizers.

Multi-Variable Multi-Objective Optimization Algorithm for Optimal Design of PMa-SynRM for Electric Bicycle Traction Motor

In this paper, internal division point genetic algorithm (IDP-GA) was proposed to lessen the computational burden of multi-variable multi-objective optimization problem using finite element analysis such as optimal design of electric bicycles. The IDP-GA could consider various objectives with normalized weighted sum method and could reduce the number of function calls with novel crossover strategy and vector-based pattern search method. The superiority of the proposed algorithm was verified by comparing performances with conventional optimization method at two mathematical test functions. Finally, the applicability of the IDP-GA in practical electric machine design was verified by successfully deriving an improved design of electric bicycle propulsion motor.

Reinforcement Learning-Based Multihop Relaying: A Decentralized Q-Learning Approach

Conventional optimization-based relay selection for multihop networks cannot resolve the conflict between performance and cost. The optimal selection policy is centralized and requires local channel state information (CSI) of all hops, leading to high computational complexity and signaling overhead. Other optimization-based decentralized policies cause non-negligible performance loss. In this paper, we exploit the benefits of reinforcement learning in relay selection for multihop clustered networks and aim to achieve high performance with limited costs. Multihop relay selection problem is modeled as Markov decision process (MDP) and solved by a decentralized Q-learning scheme with rectified update function. Simulation results show that this scheme achieves near-optimal average end-to-end (E2E) rate. Cost analysis reveals that it also reduces computation complexity and signaling overhead compared with the optimal scheme.

Predicting Human Discretion to Adjust Algorithmic Prescription: A Large-Scale Field Experiment in Warehouse Operations

Conventional optimization algorithms that prescribe order packing instructions (which items to pack in which sequence in which box) focus on box volume utilization yet tend to overlook human behavioral deviations. We observe that packing workers at the warehouses of the Alibaba Group deviate from algorithmic prescriptions for 5.8% of packages, and these deviations increase packing time and reduce operational efficiency. We posit two mechanisms and demonstrate that they result in two types of deviations: (1) information deviations stem from workers having more information and in turn better solutions than the algorithm; and (2) complexity deviations result from workers’ aversion, inability, or discretion to precisely implement algorithmic prescriptions. We propose a new “human-centric bin packing algorithm” that anticipates and incorporates human deviations to reduce deviations and improve performance. It predicts when workers are more likely to switch to larger boxes using machine learning techniques and then proactively adjusts the algorithmic prescriptions of those “targeted packages.” We conducted a large-scale randomized field experiment with the Alibaba Group. Orders were randomly assigned to either the new algorithm (treatment group) or Alibaba’s original algorithm (control group). Our field experiment results show that our new algorithm lowers the rate of switching to larger boxes from 29.5% to 23.8% for targeted packages and reduces the average packing time of targeted packages by 4.5%. This idea of incorporating human deviations to improve optimization algorithms could also be generalized to other processes in logistics and operations. This paper was accepted by Charles Corbett, operations management.

Artificial Intelligence and Its Application in Optimization under Uncertainty

Nowadays, the increase in data acquisition and availability and complexity around optimization make it imperative to jointly use artificial intelligence (AI) and optimization for devising data-driven and intelligent decision support systems (DSS). A DSS can be successful if large amounts of interactive data proceed fast and robustly and extract useful information and knowledge to help decision-making. In this context, the data-driven approach has gained prominence due to its provision of insights for decision-making and easy implementation. The data-driven approach can discover various database patterns without relying on prior knowledge while also handling flexible objectives and multiple scenarios. This chapter reviews recent advances in data-driven optimization, highlighting the promise of data-driven optimization that integrates mathematical programming and machine learning (ML) for decision-making under uncertainty and identifies potential research opportunities. This chapter provides guidelines and implications for researchers, managers, and practitioners in operations research who want to advance their decision-making capabilities under uncertainty concerning data-driven optimization. Then, a comprehensive review and classification of the relevant publications on the data-driven stochastic program, data-driven robust optimization, and data-driven chance-constrained are presented. This chapter also identifies fertile avenues for future research that focus on deep-data-driven optimization, deep data-driven models, as well as online learning-based data-driven optimization. Perspectives on reinforcement learning (RL)-based data-driven optimization and deep RL for solving NP-hard problems are discussed. We investigate the application of data-driven optimization in different case studies to demonstrate improvements in operational performance over conventional optimization methodology. Finally, some managerial implications and some future directions are provided.

Maintenance Optimization Based on Three-Stage Failure Process under Performance-Based Contracting

As a new form of support contract, performance-based contracting has been extensively applied in both public and private sectors. However, maintenance policies under performance-based contracting have not gotten enough attention. In this paper, a preventive maintenance optimization model based on three-stage failure process for a single-component system is investigated with an objective of maximizing the profit and improving system performance at a lower cost under performance-based contracting. Different from conventional optimization models, the step revenue function is used to correlate profit with availability and cost. Then, a maintenance optimization model is proposed to maximize profit by optimizing the inspection interval. Moreover, the customers’ upper limit of funds is considered when we use the revenue function, which has rarely been considered in past studies. Finally, a case study on the cold water pumps along with comparison of linear and step revenue function and sensitivity analysis is provided to illustrate the applicability and effectiveness of our proposed approach.

Accurate Solar Cell Modeling via Genetic Neural Network-Based Meta-Heuristic Algorithms

Accurate solar cell modeling is essential for reliable performance evaluation and prediction, real-time control, and maximum power harvest of photovoltaic (PV) systems. Nevertheless, such a model cannot always achieve satisfactory performance based on conventional optimization strategies caused by its high-nonlinear characteristics. Moreover, inadequate measured output current-voltage (I-V) data make it difficult for conventional meta-heuristic algorithms to obtain a high-quality optimum for solar cell modeling without a reliable fitness function. To address these problems, a novel genetic neural network (GNN)-based parameter estimation strategy for solar cells is proposed. Based on measured I-V data, the GNN firstly accomplishes the training of the neural network via a genetic algorithm. Then it can predict more virtual I-V data, thus a reliable fitness function can be constructed using extended I-V data. Therefore, meta-heuristic algorithms can implement an efficient search based on the reliable fitness function. Finally, two different cell models, e.g., a single diode model (SDM) and double diode model (DDM) are employed to validate the feasibility of the GNN. Case studies verify that GNN-based meta-heuristic algorithms can efficiently improve modeling reliability and convergence rate compared against meta-heuristic algorithms using only original measured I-V data.