Dual-objective Problem Research Articles

Workshop Facility Layout Optimization Based on Deep Reinforcement Learning

With the rapid development of intelligent manufacturing, the application of virtual reality technology to the optimization of workshop facility layout has become one of the development trends in the manufacturing industry. Virtual reality technology has put forward engineering requirements for real-time solutions to the Workshop Facility Layout Optimization Problem (WFLOP). However, few scholars have researched such solutions. Deep reinforcement learning (DRL) is effective in solving combinatorial optimization problems in real time. The WFLOP is also a combinatorial optimization problem, making it possible for DRL to solve the WFLOP in real time. Therefore, this paper proposes the application of DRL to solve the dual-objective WFLOP. First, this paper constructs a dual-objective WFLOP mathematical model and proposes a novel dual-objective DRL framework. Then, the DRL framework decomposes the WFLOP dual-objective problem into multiple sub-problems and then models each sub-problem. In order to reduce computational workload, a neighborhood parameter transfer strategy is adopted. A chain rule is constructed for the appealed sub-problem, and an improved pointer network is used to solve the bi-objective WFLOP of the sub-problem. Finally, the effectiveness of this method is verified by using the facility layout of a chip production workshop as a case study.

Nondominated sorting genetic algorithm-II with Q-learning for the distributed permutation flowshop rescheduling problem

The distributed permutation flowshop problem (DPFSP) has been extensively studied in recent years. However, most of the research has overlooked the disturbance factors in the processing environment, such as the arrival of new jobs. To address this issue, a nondominated sorting genetic algorithm-II (NSGA-II) with Q-learning has been developed. First, an iterated greedy algorithm (IG) is proposed to generate an initial solution for the first stage. Then, the NSGA-II algorithm is designed to optimize dual-objective problems in the second stage, and the Q-learning algorithm is used to adjust the algorithm parameters. Next, two local search strategies based on key factories are adopted, including critical factory-based insert and swap operations. Finally, a comprehensive experiment of the proposed algorithm against other advanced multiobjective algorithms is conducted. The results confirm that the proposed algorithm can solve the distributed permutation flowshop rescheduling problem with high efficiency.

Genetic algorithm-based congestion control optimisation for mobile data network

Abstract Mobile data network is featured by long delay and moving terminals, which affect the user service quality performance of transmission control protocol’s (TCP) congestion control algorithm Vegas. To solve this problem, this paper first proposed to optimise the congestion control algorithm using a genetic algorithm, build ns-3 network topology structure and adopt mobile data network trace for optimisation and simulation; and the Vegas optimisation problem as a multivariate dual-objective problem was solved with Non-dominated Sorting Genetic Algorithm II (NSGA-II). The ns-3 simulation results indicate that Vegas with optimised parameters have high throughput and short delay, which significantly promotes TCP Vegas’s QoS under a mobile scene.

Privacy Preservation in Social Network Data using Evolutionary Model

Social Networks have seen an exponential increase in their user activity. The corresponding user data can be extremely valuable, for improving user experience, identifying trends to make business decisions, and analyzing local and global user behavior. There are concerns over how this data is handled, largely because there are no stringent measures to regulate its handling. Anonymizing user data is vital to ensure the re-identification risk is minimum while retaining as much possible useful information from it. This work proposes a novel method to anonymize user data and ensure it satisfies the three privacy constraints of K-Anonymity (KA), L-Diversity (LD), and T-Closeness (TC), while also keeping information loss from anonymization techniques to the minimum. This dual objective problem is solved through a minimization approach.

Multi-Objective Optimization of Energy Saving and Throughput in Heterogeneous Networks Using Deep Reinforcement Learning.

Wireless networking using GHz or THz spectra has encouraged mobile service providers to deploy small cells to improve link quality and cell capacity using mmWave backhaul links. As green networking for less CO2 emission is mandatory to confront global climate change, we need energy efficient network management for such denser small-cell heterogeneous networks (HetNets) that already suffer from observable power consumption. We establish a dual-objective optimization model that minimizes energy consumption by switching off unused small cells while maximizing user throughput, which is a mixed integer linear problem (MILP). Recently, the deep reinforcement learning (DRL) algorithm has been applied to many NP-hard problems of the wireless networking field, such as radio resource allocation, association and power saving, which can induce a near-optimal solution with fast inference time as an online solution. In this paper, we investigate the feasibility of the DRL algorithm for a dual-objective problem, energy efficient routing and throughput maximization, which has not been explored before. We propose a proximal policy (PPO)-based multi-objective algorithm using the actor-critic model that is realized as an optimistic linear support framework in which the PPO algorithm searches for feasible solutions iteratively. Experimental results show that our algorithm can achieve throughput and energy savings comparable to the CPLEX.

Fuzzy Optimized Gravitational Search Algorithm for Disease Prediction

In this article, fuzzy logic and gravitational search algorithms have been amalgamated and explored for feature selection in the automated prediction of diseases. The gravitational search algorithm has been used for search optimization while fuzzy logic had been used for its parameter tuning. Feature selection has been considered as a dual objective problem in the article, i.e. selecting minimum number of features without compromising the accuracy of classification, which is performed using K-Nearest Neighbour classifier. The improved algorithm has been tested with various publicly available medical datasets to analyse its effectiveness. The results indicate that the approach not only reduces the feature set by an average of 67.66% but also increases the accuracy by an average of 12%. Further, the results have also been compared with the prior work wherein the feature selection has been done using other evolutionary techniques. It is observed that the proposed approach is able to generate better results in most of the cases.

Genetic Algorithm Based Prototype Filter Design for Oriented Side Lobe Energy Suppression in FBMC System

The prototype filter design problem is investigated for the filter bank multicarrier (FBMC) system of the fifth generation (5G) physical-layer wireless communications. In order to further suppress the side lobe energy within a certain frequency range, different constraint factors need to be introduced to meet the various side lobe energy suppression demands. In this paper, we formulate a dual-objective optimization problem which minimizes the stopband energy with constrained factors and subjects to the ISI/ICI constraints. Considering the uncertain constrained factors, a suboptimization problem is proposed by constraining the total stopband energy and the side lobe energy of the first segment to minimize the side lobe energy of the second or the third segments. Then, the nested sequential quadratic program-genetic algorithm (NSGA), one of the artificial intelligence (AI) aided algorithms, is introduced to obtain the optimal solution of the dual-objective problem, in which the genetic algorithm (GA) is applied to acquire the optimal constrained factors and the sequential quadratic program (SQP) is applied to acquire the optimal filter coefficients. Numerical results validate that the proposed method can achieve orientated side lobe energy suppression at specified segments for satisfying different side lobe energy suppression requirements with the confirmed algorithm convergence.

COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle Using Deep Reinforcement Learning

Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics. For many decades, they have been subject to academic study, leading to a vast number of proposed approaches. However, they have mostly been treated as separate problems, and have typically relied on non-linear first-principles models with parameters that can only be determined experimentally. The rise of deep reinforcement learning in recent years suggests an alternative approach: end-to-end learning of the optimal guidance policy from scratch by means of a trial-and-error based approach. In this article, we explore the potential of Proximal Policy Optimization, a deep reinforcement learning algorithm with demonstrated state-of-the-art performance on Continuous Control tasks, when applied to the dual-objective problem of controlling an autonomous surface vehicle in a COLREGs compliant manner such that it follows an a priori known desired path while avoiding collisions with other vessels along the way. Based on high-fidelity elevation and AIS tracking data from the Trondheim Fjord, an inlet of the Norwegian sea, we evaluate the trained agent's performance in challenging, dynamic real-world scenarios where the ultimate success of the agent rests upon its ability to navigate non-uniform marine terrain while handling challenging, but realistic vessel encounters.

Taming an Autonomous Surface Vehicle for Path Following and Collision Avoidance Using Deep Reinforcement Learning

In this article, we explore the feasibility of applying proximal policy optimization, a state-of-the-art deep reinforcement learning algorithm for continuous control tasks, on the dual-objective problem of controlling an underactuated autonomous surface vehicle to follow an a priori known path while avoiding collisions with non-moving obstacles along the way. The artificial intelligent agent, which is equipped with multiple rangefinder sensors for obstacle detection, is trained and evaluated in a challenging, stochastically generated simulation environment based on the OpenAI gym python toolkit. Notably, the agent is provided with real-time insight into its own reward function, allowing it to dynamically adapt its guidance strategy. Depending on its strategy, which ranges from radical path-adherence to radical obstacle avoidance, the trained agent achieves an episodic success rate between 84 and 100%.

Evacuation and Settlement Model of Personnel in Major Flood Disasters and Its Application

In order to select the most suitable rescue boat stop and personnel resettlement point for rapid evacuation and placement of “isolated island” victims. According to the characteristics of “isolated island” problem, considering the factors of total evacuation time and total evacuation cost, a dual-objective emergency evacuation model is constructed. By using the method of fuzzy matrix, the dual-objective problem is transformed into a single-objective problem. Finally, the Hungarian method is used to solve the problem. The results of an example show that the model can realize the selection of the best berth point and personnel placement point.

Thrust-versus-endurance trade-off optimization in swimming

ABSTRACTThis article applies methods typically used in engineering applications to the optimization of human locomotion, more specifically a swimmer's underwater ‘dolphin kick’. This is a dual-objective problem which seeks the optimal trade-off between thrust (simulated using Lighthill's fish propulsion method) and the force in the muscles to produce this thrust (simulated using musculoskeletal modelling). The expense of the analyses leads to the use of a surrogate modelling based optimization technique (multi-objective expected improvement using Kriging). The results indicate that optimal human motion does in many respects follow that of fish, with low frequency eel-like techniques suitable for endurance and a high frequency tuna-like kick for high thrust. The MATLAB® code, including thrust and muscle activity models, is made available in an online repository.

A Type-2 Fuzzy Chance-Constrained Fractional Integrated Modeling Method for Energy System Management of Uncertainties and Risks

In this study, a type-2 fuzzy chance-constrained fractional integrated programming (T2FCFP) approach is developed for the planning of sustainable management in an electric power system (EPS) under complex uncertainties. Through simultaneously coupling mixed-integer linear programming (MILP), chance-constrained stochastic programming (CCSP), and type-2 fuzzy mathematical programming (T2FMP) techniques into a fractional programming (FP) framework, T2FCFP can tackle dual objective problems of uncertain parameters with both type-2 fuzzy characteristics and stochastic effectively and enhance the robustness of the obtained decisions. T2FCFP has been applied to a case study of a typical electric power system planning to demonstrate these advantages, where issues of clean energy utilization, air-pollutant emissions mitigation, mix ratio of renewable energy power generation in the entire energy supply, and the displacement efficiency of electricity generation technologies by renewable energy are incorporated within the modeling formulation. The suggested optimal alternative that can produce the desirable sustainable schemes with a maximized share of clean energy power generation has been generated. The results obtained can be used to conduct desired energy/electricity allocation and help decision-makers make suitable decisions under different input scenarios.

A dual objective approach for aggregator managed demand side management (DSM) in cloud based cyber physical smart distribution system

This paper presents an incentive based framework for demand response scheduling in smart distribution networks with commercial, residential and industrial load sectors using designated cloud storage in cyber physical cloud based smart distribution system. The proposed approach consists of a two stage procedure where dual objective problem is modeled to achieve both responsive load agent (RLA) economic benefits as well as distribution system operator (DSO) preferences. The two stage coordinated scheduling of RLAs with DSO network operation preferences is carried out by demand response aggregation agent (DRAA) through incentives. The cloud based information exchange between different stakeholders provides the necessary communication at different stages of responsive load scheduling. The concept of private, shared and community clouds are incorporated into the cyber physical cloud based DAM framework proposed in this work. The first stage scheduling of responsive loads is carried out by RLAs with electricity payment minimization objective looking into the tariff structure. Whereas, the second stage scheduling is carried out by DRAA in which incentives are offered to RLAs for the deviation from personalized schedules of first stage. The customer characterization and behavior (risk averse, incentive preferences etc.) of scheduling the responsive loads is considered through incentive range based clusters. The proposed DRAA coordinated DR scheduling framework is simulated using IEEE 37 bus distribution test system with commercial, residential and industrial sectors. The impact of stage 1 and stage 2 scheduling of responsive loads is analyzed with respect to system performance indices such as total operational cost, load factor, total network losses etc. The sensitivity analysis is performed to examine the impact of weightage assignment to DSO and RLA objectives on system performance aspects. The proposed DRAA coordinated two stage framework has shown considerable improvement in techno-economic aspects of responsive load scheduling in distribution network that can be appended to real world applications at distribution level/retail markets.

Using the method of ideal point to solve dual-objective problem for production scheduling

In practice, there are often problems, which must simultaneously optimize several criterias. This so-called multi-objective optimization problem. In the article we consider the use of the method ideal point to solve the two-objective optimization problem of production planning. The process of finding solution to the problem consists of a series of steps where using simplex method, we find the ideal point. After that for solving a scalar problems, we use the method of Lagrange multipliers

Integrated production planning and preventive maintenance in deteriorating production systems

The traditional production planning model based upon the famous linear programming formulation has been well documented. However, the integration of preventive maintenance planning in the same model is a recent problem. This paper proposes an extended linear programming model as a hybrid approach for computing the optimum production plan with minimum total cost. The dual objective problem of production planning and maintenance is treated into a mixed integer linear program. This program is not only considering cases of multi-lines, multi-periods and multi-items but also taking into account the deterioration of the lines. This deterioration is represented in the model as a reduction of production lines capacities in function of the time evolution. Maintenance operations are supposed to provide lines in an operational state as good as new, i.e. with a maximum capacity. Through the study of the models limits, it is shown that the proposed approach can deal with a broader range of problems than that of Aghezzaf and Najid (2008) [3]. An optimal relaxation technique based on the polyhedral theory is developed to improve the computational time and expand the limits of the proposed model. Also, a “Fix and Relax heuristic” is developed for complex problems. Their computation time and their difference are computed referring to the same lower bound and the same considerations as those presented by Aghezzaf and Najid. It is proved through more than 880 several simulations for each model with different capacities and different setup costs, that this approach can solve large size problems with moderate computational time and gap.

Multi-objective due-date setting in a make-to-order environment

This paper presents a new dual-objective problem of due-date setting over a rolling planning horizon in make-to-order manufacturing and proposes a bi-criterion integer programming formulation for its solution. In the proposed model the due-date setting decisions are directly linked with available capacity. A simple critical load index is introduced to quickly identify the system bottleneck and the overloaded periods. The problem objective is to select a maximal subset of orders that can be completed by the customer requested dates and to quote delayed due dates for the remaining acceptable orders to minimise the number of delayed orders or the total number of delayed products as a primary optimality criterion and to minimise total or maximum delay of orders as a secondary criterion. A weighted-sum program based on a scalarisation approach is compared with a two-level due-date setting formulation based on the lexicographic approach. In addition, a mixed-integer programming model is provided for scheduling customer orders over a rolling planning horizon to minimise the maximum inventory level. Numerical examples modeled after a real-world make-to-order flexible flowshop environment in the electronics industry are provided and, for comparison, the single-objective solutions that maximise total revenue subject to service level constraints are reported.

Conceptual design of UAV using Kriging based multi-objective genetic algorithm

AbstractThis paper highlights unmanned aerial vehicle (UAV) conceptual design using the multi-objective genetic algorithm (MOGA). The design problem is formulated as a multidisciplinary design optimisation (MDO) problem by coupling aerodynamic and structural analysis. The UAV considered in this paper is a low speed, long endurance aircraft. The optimisation problem uses endurance maximization and wing weight minimisation as dual objective functions. In this multi-objective optimisation, aspect ratio, wing loading, taper ratio, thickness-to-chord ratio, loiter velocity and loiter altitude are considered as design variables with stall speed, maximum speed and rate of climb as constraints. The MDO system integrates the aircraft design code, RDS and an empirical relation for objective function evaluation. In this study, the optimisation problem is solved in two approaches. In the first approach, the RDS code is directly integrated in the optimisation loop. In the second approach, Kriging model is employed. The second approach is fast and efficient as the meta-model reduces the time of computation. A relatively new multi-objective evolutionary algorithm named NSGA-II (non-dominated sorting genetic algorithm) is used to capture the full Pareto front for the dual objective problem. As a result of optimisation using multi-objective genetic algorithm, several non-dominated solutions indicating number of useful Pareto optimal designs is identified.

Multi-Objective Optimization of Communication Satellites with Two-Branch Tournament Genetic Algorithm

In spacecraft design, many specialized state-of-the-art design tools are employed to optimize the performance of various subsystems. However, there is no structured system-level concept-definition process. Consequently, designers usually compromise some mission goals to satisfy only one of the primary design objectives. The conceptual stage of the spacecraft design process is formulated into a multi-objective discrete optimization problem. The use of multi-objective design allows the designer to evaluate different design alternatives across the whole set of design objectives. This work addresses two key design objectives for the spacecraft design process: the minimization of total launch mass and the maximization of spacecraft overall reliability. To predict values for the objective and constraint functions, a satellite design tool, which includes a satellite sizing model and a deterministic reliability model, was built and integrated with a genetic algorithm that employs a two-branch tournament to address the dual objective problem. The multi-objective approach was successful in determining sets of discrete design parameters that would minimize the launch mass as well as maximize the reliability of a geostationary communication satellite, using specified payload requirements. The designs generated by this approach appear to fall into three regions of the tradeoff space between the satellite launch mass and the satellite reliability objectives.