Efficient Heuristic Algorithm Research Articles

Prerequisite knowledge‐based automated course planning with semantics consideration

AbstractThe knowledge‐based prerequisite framework (KPF) is an alternative to the course‐based prerequisite framework (CPF), which is widely used for curriculum design. The KPF is more flexible because it only requires essential prerequisite knowledge, while the CPF is more rigid and requires students to take all prerequisite courses. Since the number of prerequisite knowledge terms is, in general, much greater than the number of prerequisite courses, flexibility can cause additional complexity. Furthermore, the KPF inevitably requires handling semantics of defined knowledge terms. This work presents a novel Artificial Intelligence (AI) Planning mathematical model that enables the KPF by automatically verifying prerequisite knowledge and incorporating hierarchical semantic relationships among knowledge terms into the model. The proposed model significantly improves the quality of course planning solutions by finding hidden or better solutions that could not be obtained without semantics consideration. The results of the comprehensive experiments show the optimality of the solutions obtained by the mathematical model and demonstrate the outperformance of incorporation of the semantics into the mathematical model, in terms of the quality of solutions. Finally, the experimental results on scalability show the necessity of the development of efficient heuristic algorithms.

Energy optimization in freight train operations: Algorithmic development and testing

This research applies multi-objective dynamic programming – specifically, goal programming – solved using a computationally efficient heuristic minimum path-finding algorithm (A*) to improve energy efficiency in freight train operations. The investigation focuses on the U.S. freight network, evaluating the impact of the proposed system on six powertrain technologies, namely diesel, biodiesel, diesel-hybrid, biodiesel-hybrid, hydrogen fuel cell, and battery electric on energy consumption and travel time. The primary findings indicate that when prioritizing energy reduction, diesel and biodiesel hybrids emerge as the most effective, achieving a 47% decrease in energy consumption compared to scenarios without optimization. Hydrogen and battery electric technologies demonstrate a 26% energy saving. In contrast, diesel and biodiesel powertrains show the least improvement, with a 21.5% reduction in energy consumption, accompanied by a 60% increase in travel time for all powertrains except hydrogen, which incurs only a 29% increase. Furthermore, when the multi-objective optimization model incorporates travel time, assigning a 70% weight to energy consumption and a 30% weight to travel time, the results are consistent. In this scenario, diesel and biodiesel hybrids yield an 11% reduction in energy consumption, followed by a 7% reduction for hydrogen fuel cells and a 6% reduction for battery electric trains, with diesel and biodiesel powertrains achieving a 5% reduction. This optimization leads to a mere 7% increase in travel time compared to the non-optimized scenario.

Manifold-guided multi-objective gradient algorithm combined with adjoint method for supersonic aircraft shape design

The aerodynamic design of supersonic aircraft necessitates the comprehensive consideration of multiple conflicting design objectives and multi-disciplinary characteristics. However, the efficiency of heuristic algorithms in solving multi-objective aerodynamic problems significantly decreases with the increase in the number of design variables and objectives. Although gradient-based adjoint optimization methods can eliminate the constraints of design variables on aerodynamic optimization and have high optimization efficiency, they are prone to getting stuck in local optima and are difficult to apply in multi-objective optimization. To overcome these shortcomings, a manifold-guided multi-objective gradient-based algorithm (MG-MOGBA) is proposed. This algorithm enhances the optimization efficiency of the algorithm by coupling the multi-objective gradient operator with the predicted Pareto front (PF) manifold structure to guide the population search direction and reduce the search space. A multi-objective aerodynamic optimization framework based on the discrete adjoint method is developed to automate the aerodynamic optimization process. Test functions and airfoil optimization results confirm that the proposed algorithm achieves superior results with fewer iterations and is more efficient than heuristic algorithms. The four-objective supersonic civil aircraft example demonstrates that the algorithm can effectively handle high-dimensional multi-objective aerodynamic optimization problems. A potential equilibrium solution increased the cruise factor by 17.5% and 12.8% under supersonic and transonic conditions respectively, reduced the maximum overpressure of the sonic boom by 25.1%, and decreased the root bending moment by 20.3%. Overall, MG-MOGBA can efficiently solve high-dimensional multi-objective aerodynamic optimization problems and has good scalability for the dimensions of design objectives and variables.

Optimal Cooperative Eco-Driving of Multitrain With TLET Comprehensive System

Aiming to minimize the total electricity usage in realistic operation of urban rail transit (URT) trains, this paper establishes the coupled model for the train-line-electric network-timetable (TLET) comprehensive system, and proposes a multi-train cooperative eco-driving method to achieve the system energy optimal. The dynamic power flow within the DC railway system with multiple trains is analyzed by modeling the traction power supply system (TPSS), and an improved power flow calculation (PFC) method is proposed to calculate the dynamic power flow distribution. To achieve the total substation energy minimization, a space-time-speed (STS) three-dimensional network is presented to transform continuous train motion process into discrete states on space-speed plane, and a multiple individuals dynamic programming (MIDP) algorithm is throughly developed to cooperatively optimize the multi-train trajectories along the time horizon, with which the optimal speed profiles and timetables of each train can be obtained simultaneously. Moreover, a computationally efficient heuristic algorithm together with a train-to-train (T2T) communication policy are developed as a comparative study. Numerical experiment with field data from Guangzhou Metro Line 8 is implemented, to illustrate the energy-saving performance of the proposed methods.

Noise-aware resource allocation with integrated key generation and consumption for CV-QKD over WDM networks

Continuous-variable quantum key distribution (CV-QKD) has been regarded as a promising approach to secure optical communications over wavelength division multiplexing (WDM) networks. Conventionally, the key generation and the key consumption were considered separately, thus potentially leading to a possible mismatch between them and significantly degrading the network efficiency. A few studies considered these two parts jointly but assumed the worst noise condition, which may lead to an over-supply of quantum keys. In this paper, we propose a noise-aware resource allocation (NARA) scheme and design a framework to balance the generation and the consumption of quantum keys for CV-QKD over WDM networks. We formulate the NARA problem as a mixed-integer linear programming (MILP) model. An efficient heuristic algorithm with three allocation schemes, including threshold-based noise loading (TNL), stress-based noise loading (SNL), and noise margin reservation (NMR), has been designed. Simulation results show that NARA with the NMR scheme can significantly reduce the total number of wavelengths used and the total network cost under all system parameters by more than 10% and 20%, respectively, compared to the other two schemes.

Models and algorithms for the preventive maintenance optimization of railway vehicles

The motivation of this paper follows strictly from industrial needs to improve competitiveness in railway companies by the efficient rolling stock utilization affected by the obligatory preventive maintenances of vehicles, which cause their temporary unavailability. Nevertheless, it is economically essential to minimize the total time on maintenances of vehicles, which can be achieved in a certain range by the scheduling of transport tasks taking into account maintenance policies of the vehicles, their mileage and date since the last maintenance, and the workload related to the tasks. Therefore, to face the problem, we model the consider issue as the job scheduling problem to maximize the availability of railway vehicles under preventive maintenances. We prove that the problem is strongly NP-hard and we propose efficient heuristic and metaheuristic algorithms that are characterized by a low computational complexity and they are able to find solutions satisfying from the perspective of industrial practice. The simulations based on real-life data reveal that our approach can provide schedules, which significantly improve availability of locomotives resulting in high potential financial benefits for railway companies.

TMDS: Temperature-aware Makespan Minimizing DAG Scheduler for Heterogeneous Distributed Systems

To meet application-specific performance demands, recent embedded platforms often involve the use of intricate micro-architectural designs and very small feature sizes leading to complex chips with multi-million gates. Such ultra-high gate densities often make these chips susceptible to inappropriate surges in core temperatures. Temperature surges above a specific threshold may throttle processor performance, enhance cooling costs, and reduce processor life expectancy. This work proposes a generic temperature management strategy that can be easily employed to adapt existing state-of-the-art task graph schedulers so that schedules generated by them never violate stipulated thermal bounds. The overall temperature-aware task graph scheduling problem has first been formally modeled as a constraint optimization formulation whose solution is shown to be prohibitively expensive in terms of computational overheads. Based on insights obtained through the formal model, a new fast and efficient heuristic algorithm called TMDS has been designed. Experimental evaluation over diverse test case scenarios shows that TMDS is able to deliver lower schedule lengths compared to the temperature-aware versions of four prominent makespan minimizing algorithms, namely, HEFT , PEFT , PPTS , and PSLS . Additionally, a case study with an adaptive cruise controller in automotive systems has been included to exhibit the applicability of TMDS in real-world settings.

Stateful Serverless Application Placement in MEC With Function and State Dependencies

Serverless computing is emerging as an enabling technology for elastic and low-cost AI applications in the edge of core networks. It allows AI developers to decompose a complex training and time-sensitive inference task into multiple functions with dependency, and upload the task to a Multi-access Edge Computing platform (MEC) for execution. Serverless computing adopts a popular design principle: the disaggregation of storage and computation, making the functions ‘stateless’. However, most AI applications are ‘stateful’ and rely on an external storage service to manage their states (ephemeral data). This will incur a prohibitively long delay for delay-sensitive AI applications if external services storing the states are far from the serverless functions. Motivated by this critical issue, in this paper we investigate a fundamental problem in serverless computing – the stateful serverless application placement problem, for which, we first propose an efficient heuristic algorithm, and then devise an approximation algorithm with a provable approximation ratio for one of its special cases. We also consider the online version of the problem, and develop an online learning-driven algorithm with a bounded regret. The crux of the online algorithm is the adoption of the multi-armed bandits technique for dynamic admissions of inference requests, under the uncertainty of both data volumes of requests and network delays. We finally evaluate the performance of the proposed algorithms through experimental simulations. Simulation results show that the proposed algorithms outperform their counterparts, reducing at least <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$32\%$</tex-math></inline-formula> in the total cost and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$27\%$</tex-math></inline-formula> of the average delay.

Optimization Models for the Vehicle Routing Problem under Disruptions

In this paper, we study the role of disruptions in the multi-period vehicle routing problem (VRP), which naturally arises in humanitarian logistics and military applications. We assume that at any time during the delivery phase, each vehicle could have chance to be disrupted. When a disruption happens, vehicles will be unable to continue their journeys and supplies will be unable to be delivered. We model the occurrence of disruption as a given probability and consider the multi-period expected delivery. Our objective is to either minimize the total travel cost or maximize the demand fulfillment, depending on the supply quantity. This problem is denoted as the multi-period vehicle routing problem with disruption (VRPMD). VRPMD does not deal with disruptions in real-time and is more focused on the long-term performance of a single routing plan. We first prove that the proposed VRPMD problems are NP-hard. We then present some analytical properties related to the optimal solutions to these problems. We show that Dror and Trudeau’s property does not apply in our problem setting. Nevertheless, a generalization of Dror and Trudeau’s property holds. Finally, we present efficient heuristic algorithms to solve these problems and show the effectiveness of the proposed models and algorithms through numerical studies.

Multi-objective green scheduling of integrated flexible job shop and automated guided vehicles

The traditional flexible job shop scheduling problem (FJSP) ignores transportation issues or merely introduces a time lag for transportation tasks while assuming an infinite number of transportation resources. With the development of intelligent manufacturing, automated guided vehicles (AGVs), which are the key transportation equipment for manufacturing enterprises, have been widely used for their high flexibility and stability. In addition, the increase in energy consumption and the trend of green manufacturing make it critical to take into account energy-related objectives in the decision-making of scheduling. Therefore, the multi-objective green scheduling problem of integrated flexible job shop and AGVs (MOGSP-IFJS&AGVs) is addressed in this paper. To solve this problem effectively, the multi-objective mixed-integer programming (MMIP) model is formulated to minimize total energy consumption and makespan simultaneously. An efficient heuristic algorithm (EHA) is designed to solve the MMIP model. In the EHA, one solution encoding scheme and corresponding greedy insertion decoding method considering the selection of AGVs are presented. To acquire a high-quality initial population, the population initialization method balancing the processing time and energy consumption is designed. Further, a local search strategy is presented to enhance the quality of solutions and accelerate the convergence speed of the EHA. Experiment results of 45 test instances indicate that the EHA can obtain better solutions than that of comparison algorithms, which confirms the effectiveness of the EHA for solving the MOGSP-IFJS&AGVs.

An Improved Influence Maximization Method for Online Advertising in Social Internet of Things.

Recently, a new subject known as the Social Internet of Things (SIoT) has been presented based on the integration the Internet of Things and social network concepts. SIoT is increasingly popular in modern human living, including applications such as smart transportation, online health care systems, and viral marketing. In advertising based on SIoT, identifying the most effective diffuser nodes to maximize reach is a critical challenge. This article proposes an efficient heuristic algorithm named Influence Maximization of advertisement for Social Internet of Things (IMSoT), inspired by real-world advertising. The IMSoT algorithm consists of two steps: selecting candidate objects and identifying the final seed set. In the first step, influential candidate objects are selected based on factors, such as degree, local importance value, and weak and sensitive neighbors set. In the second step, effective influence is calculated based on overlapping between candidate objects to identify the appropriate final seed set. The IMSoT algorithm ensures maximum influence and minimum overlap, reducing the spreading caused by the seed set. A unique feature of IMSoT is its focus on preventing duplicate advertising, which reduces extra costs, and considering weak objects to reach the maximum target audience. Experimental evaluations in both real-world and synthetic networks demonstrate that our algorithm outperforms other state-of-the-art algorithms in terms of paying attention to weak objects by 38%-193% and in terms of preventing duplicate advertising (reducing extra cost) by 26%-77%. Additionally, the running time of the IMSoT algorithm is shorter than other state-of-the-art algorithms.

Optimized Controller Provisioning in Software-Defined LEO Satellite Networks

The controller provisioning, which adjusts the number, locations, and members of satellite controllers adaptive to the dynamic network load and topology, fundamentally impacts the performance of software-defined satellite networks (SDSNs). An ideal provisioning strategy should achieve a low total control overhead throughout the entire satellite operation period, which is extremely challenging since the network load can only be predicted in a short time scale. Existing methods can hardly achieve this goal for they greedily configure controllers in each time slot, where switches have to frequently migrate from one controller to another. In this paper, we focus on achieving globally optimized strategies with only current network load information. We firstly propose a comprehensive control overhead model and formulate the Controller Provisioning Problem (CPP) in SDSNs as a non-convex integer programming problem. To solve the problem, we propose an approximate algorithm named AROA by introducing a regularization framework and based on randomized rounding. We theoretically derive its competitive ratio. To produce strategies in time for future large satellite constellations, we further propose a more efficient heuristic algorithm HROA. Evaluations on our built simulation system show that our proposed methods significantly outperform related schemes in control overhead, latency, and scalability.

An Efficient PSO-Based Algorithm for Finding Maximal Exact Match in Large DNA Sequences

With the appearance of complete mammalian genomes, comparative approaches have experienced a recent upsurge. Searching maximal exact match is among the most used tasks in sequence searching within a larger DNA sequence or database. Many exact algorithms have been designed to deal with this problem. The best improvements made by these algorithms have led to a time and space complexity of O(n) and they remain practically less effective for large sequences. Heuristic methods will therefore be a good alternative to implement. In this work, we present an efficient heuristic algorithm based on PSO metaheuristic to deal with the problem of searching the maximal exact match of small searched sequences in large ones. The time and space complexity of the designed algorithm is of O(1). The experimental results showed the efficiency of the proposed search algorithm for finding maximal exact match in large sequences when compared with two other sequence searching algorithms.

Energy-Aware, Device-to-Device Assisted Federated Learning in Edge Computing

The surging of deep learning brings new vigor and vitality to shape the prospect of intelligent Internet of Things (IoT), and the rise of edge intelligence enables provisioning real-time deep neural network (DNN) inference services for mobile users. To perform efficient and effective DNN model training in edge computing environments while preserving training data security and privacy of IoT devices, federated learning has been envisioned as an ideal learning paradigm for this purpose. In this paper, we study energy-aware DNN model training in edge computing. We first formulate a novel energy-aware, Device-to-Device (D2D) assisted federated learning problem with the aim to minimize the global loss of a training DNN model, subject to bandwidth capacity on an edge server and energy capacity on each IoT device. We then devise a near-optimal learning algorithm for the problem when the training data follows the i.i.d. data distribution. The crux of the proposed algorithm is to explore using the energy of neighboring devices of each device for its local model uploading, by reducing the problem to a series of weighted maximum matching problems in corresponding auxiliary graphs. We also consider the problem without the assumption of the i.i.d. data distribution, for which we propose an efficient heuristic algorithm. We finally evaluate the performance of the proposed algorithms through experimental simulations. Experimental results show that the proposed algorithms are promising.

FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement

With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these models is composed of lots of dense algebras, requiring a huge amount of hardware resources. Recently, sparsely-gated Mixture-of-Experts (MoEs) are becoming more popular and have demonstrated impressive pretraining scalability in various downstream tasks. However, such a sparse conditional computation may not be effective as expected in practical systems due to the routing imbalance and fluctuation problems. Generally, MoEs are becoming a new data analytics paradigm in the data life cycle and suffering from unique challenges at scales, complexities, and granularities never before possible. In this paper, we propose a novel DNN training framework, FlexMoE, which systematically and transparently address the inefficiency caused by dynamic dataflow. We first present an empirical analysis on the problems and opportunities of training MoE models, which motivates us to overcome the routing imbalance and fluctuation problems by a dynamic expert management and device placement mechanism. Then we introduce a novel scheduling module over the existing DNN runtime to monitor the data flow, make the scheduling plans, and dynamically adjust the model-to-hardware mapping guided by the real-time data traffic. A simple but efficient heuristic algorithm is exploited to dynamically optimize the device placement during training. We have conducted experiments on both NLP models (e.g., BERT and GPT) and vision models (e.g., Swin). And results show FlexMoE can achieve superior performance compared with existing systems on real-world workloads --- FlexMoE outperforms DeepSpeed by 1.70x on average and up to 2.10x, and outperforms FasterMoE by 1.30x on average and up to 1.45x.

An Enhanced Path Planner for Electric Vehicles Considering User-Defined Time Windows and Preferences

A number of decision support tools facilitating the use of Electric Vehicles (EVs) have been recently developed. Due to the EVs’ limited autonomy, routing and path planning are the main challenges treated in such tools. Specifically, determining at which Charging Stations (CSs) to stop, and how much the EV should charge at them is complex. This complexity is further compounded by the fact that charging times depend on the CS technology, the EV characteristics, and follow a nonlinear function. Considering these factors, we propose a path-planning methodology for EVs with user preferences, where charging is performed at public CSs. To achieve this, we introduce the Electric Vehicle Shortest Path Problem with time windows and user preferences (EVSPPWP) and propose an efficient heuristic algorithm for it. Given an origin and a destination, the algorithm prioritizes CSs close to Points of Interest (POIs) that match user inputted preferences, and user-defined time windows are considered for activities such as lunch and spending the night at hotels. The algorithm produces flexible solutions by considering clusters of charging points (CPs) as separate CSs. Furthermore, the algorithm yields resilient paths by ensuring that recommended paths have a minimum number of CSs in their vicinity. The main contributions of our methodology are the following: modeling user-defined time windows, including user-defined weights for different POI categories, creating CSs based on clusters of CPs with sufficient proximity, using resilient paths, and proposing an efficient algorithm for solving the EVSPPWP. To facilitate the use of our methodology, the algorithm was integrated into a web interface. We demonstrate the use of the web interface, giving usage examples and comparing different settings.

Router Activation Heuristics for Energy-Saving ECMP and Valiant Routing in Data Center Networks

This paper addresses the energy conservation problem in computing systems. The focus is on energy-efficient routing protocols. We formulated and solved a network-wide optimization problem for calculating energy-aware routing for the recommended network configuration. Considering the complexity of the mathematical models of data center networks and the limitations of calculating routing by solving large-scale optimization problems, and methods described in the literature, we propose an alternative solution. We designed and developed several efficient heuristics for equal-cost multipath (ECMP) and Valiant routing that reduce the energy consumption in the computer network interconnecting computing servers. Implementing these heuristics enables the selection of routing paths and relay nodes based on current and predicted internal network load. The utility and efficiency of our methods were verified by simulation. The test cases were carried out on several synthetic network topologies, giving encouraging results. Similar results of using our efficient heuristic algorithm and solving the optimization task confirmed the usability and effectiveness of our solution. Thus, we produced well-justified recommendations for energy-aware computing system design to conclude the paper.

A Three-Stage model for Clustering, Storage, and joint online order batching and picker routing Problems: Heuristic algorithms

The online shopping center is an electronic commerce where customer orders arrive over time. The joint online order batching and picker routing is essential for managing online shopping, as it allows for the retrieval of products from storage locations as order arrival timings become known. Meanwhile, the picker routing performance is substantially affected by the product allocation to storage locations, whereas the success of the storage assignment depends on the product grouping. In order to handle such a system, this study offers a novel three-stage model, the first stage of which aims to classify products according to various available capacity levels to maximize similarity measures among products. The second stage determines the assignments of the obtained classes to carriers and storage locations in a multi-block 3D warehouse to minimize the total transportation costs and the energy costs of carriers. The third stage provides a joint online order batching and picker routing model in a picker-to-parts system to minimize completion time in the 3D warehouse. Since learning effects affect the search and pick times, and pickers’ horizontal and vertical velocities are dissimilar, these crucial factors are considered for calculating travel time of pickers. In addition, two efficient heuristic algorithms are proposed to solve the developed models in the first two stages, and an effective online 2-competitive heuristic algorithm is developed to solve the proposed model in the third stage. Moreover, a broad range of numerical experiments illustrates the validity and applicability of the proposed models and solution approaches. What is more, a competitive analysis evaluates the effectiveness of the proposed online heuristic algorithm. The results reveal that the developed hierarchical framework can provide high-quality solutions in a reasonable time and reduce the total cost and makespan by 35.65% and 12.48% on average, respectively.

Maximizing Heterogeneous Server Utilization with Limited Availability Times for Divisible Loads Scheduling on Networked Systems

Most of the available divisible-load scheduling models assume that all servers in networked systems are idle before workloads arrive and that they can remain available online during workload computation. In fact, this assumption is not always valid. Different servers on networked systems may have heterogenous available times. If we ignore the availability constraints when dividing and distributing workloads among servers, some servers may not be able to start processing their assigned load fractions or deliver them on time. In view of this, we propose a new multi-installment scheduling model based on server availability time constraints. To solve this problem, we design an efficient heuristic algorithm consisting of a repair strategy and a local search strategy, by which an optimal load partitioning scheme is derived. The repair strategy guarantees time constraints, while the local search strategy achieves optimality. We evaluate the performance via rigorous simulation experiments and our results show that the proposed algorithm is suitable for solving large-scale scheduling problems employing heterogeneous servers with arbitrary available times. The proposed algorithm is shown to be superior to the existing algorithm in terms of achieving a shorter makespan of workloads.

Bounded Wang tilings with integer programming and graph-based heuristics

Wang tiles enable efficient pattern compression while avoiding the periodicity in tile distribution via programmable matching rules. However, most research in Wang tilings has considered tiling the infinite plane. Motivated by emerging applications in materials engineering, we consider the bounded version of the tiling problem and offer four integer programming formulations to construct valid or nearly-valid Wang tilings: a decision, maximum-rectangular tiling, maximum cover, and maximum adjacency constraint satisfaction formulations. To facilitate a finer control over the resulting tilings, we extend these programs with tile-based, color-based, packing, and variable-sized periodic constraints. Furthermore, we introduce an efficient heuristic algorithm for the maximum-cover variant based on the shortest path search in directed acyclic graphs and derive simple modifications to provide a 1/2 approximation guarantee for arbitrary tile sets, and a 2/3 guarantee for tile sets with cyclic transducers. Finally, we benchmark the performance of the integer programming formulations and of the heuristic algorithms showing that the heuristics provide very competitive outputs in a fraction of time. As a by-product, we reveal errors in two well-known aperiodic tile sets: the Knuth tile set contains a tile unusable in two-way infinite tilings, and the Lagae corner tile set is not aperiodic.