Adaptive multi-objective swarm intelligence for containerized microservice deployment

Multi-objective swarm intelligence approach for bias mitigation in decision-making software

Hybrid offshore renewable energy platforms have been proposed to optimise power production and reduce the levelised cost of energy by integrating or co-locating several renewable technologies. One example is a hybrid wave-wind energy system that combines offshore wind turbines with wave energy converters (WECs) on a single floating foundation. The design of such systems involves multiple parameters and performance measures, making it a complex, multi-modal, and expensive optimisation problem. This paper proposes a novel, robust and effective multi-objective swarm optimisation method (DMOGWA) to provide a design solution that best compromises between maximising WEC power output and minimising the effect on wind turbine nacelle acceleration. The proposed method uses a chaotic adaptive search strategy with a dynamic archive of non-dominated solutions based on diversity to speed up the convergence rate and enhance the Pareto front quality. Furthermore, a modified exploitation technique (Discretisation Strategy) is proposed to handle the large damping and spring coefficient of the Power Take-off (PTO) search space. To evaluate the efficiency of the proposed method, we compare the DMOGWA with four well-known multi-objective swarm intelligence methods (MOPSO, MALO, MODA, and MOGWA) and four popular evolutionary multi-objective algorithms (NSGA-II, MOEA/D, SPEA-II, and PESA-II) based on four potential deployment sites on the South Coast of Australia. The optimisation results demonstrate the dominance of the DMOGWA compared with the other eight methods in terms of convergence speed and quality of solutions proposed. Furthermore, adjusting the hybrid wave-wind model’s parameters (WEC design and PTO parameters) using the proposed method (DMOGWA) leads to a considerably improved power output (average proximate boost of 138.5%) and a notable decline in wind turbine nacelle acceleration (41%) throughout the entire operational spectrum compared with the other methods. This improvement could lead to millions of dollars in additional income per year over the lifespan of hybrid offshore renewable energy platforms.

Arsenic is a carcinogen, and long-term exposure to it may result in the development of multi-organ disease. Understanding the underlying intricate molecular network of toxicity and carcinogenicity is crucial for identifying a small set of differentially expressed biomarker genes to predict the risk of the exposed population. In this paper, a multiple kernel learning (MKL) embedded multi-objective swarm intelligence technique has been proposed to identify the candidate biomarker genes from the transcriptomic profile of arsenicosis samples. To achieve the optimal classification accuracy along with the minimum number of genes, a multi-objective random spatial local best particle swarm optimization (MO-RSplbestPSO) has been utilized. The proposed MO-RSplbestPSO also guides the multiple kernel learning mechanism which provides data specific classification. The proposed computational framework has been applied to the developed whole genome DNA microarray prepared using blood samples collected from a specific arsenic exposed area of the Indian state of West Bengal. A set of twelve biomarker genes, with four novel genes, are successfully identified for the classification of exposure to arsenic and its subcategories, which can be used as future prognostic biomarkers for screening of arsenic exposed populations. Also, the biological significance of each gene is detailed to delineate the complex molecular networking and mode of toxicity.

Planning a practical three-dimensional (3-D) flight path for unmanned aerial vehicles (UAVs) is a key challenge for the follow-up management and decision making in disaster emergency response. The ideal flight path is expected to balance the total flight path length and the terrain threat, to shorten the flight time and reduce the possibility of collision. However, in the traditional methods, the tradeoff between these concerns is difficult to achieve, and practical constraints are lacking in the optimized objective functions, which leads to inaccurate modeling. In addition, the traditional methods based on gradient optimization lack an accurate optimization capability in the complex multimodal objective space, resulting in a nonoptimal path. Thus, in this article, an accurate UAV 3-D path planning approach in accordance with an enhanced multiobjective swarm intelligence algorithm is proposed (APPMS). In the APPMS method, the path planning mission is converted into a multiobjective optimization task with multiple constraints, and the objectives based on the total flight path length and degree of terrain threat are simultaneously optimized. In addition, to obtain the optimal UAV 3-D flight path, an accurate swarm intelligence search approach based on improved ant colony optimization is introduced, which can improve the global and local search capabilities by using the preferred search direction and random neighborhood search mechanism. The effectiveness of the proposed APPMS method was demonstrated in three groups of simulated experiments with different degrees of terrain threat, and a real-data experiment with 3-D terrain data from an actual emergency situation.

Improved combined system and application to precipitation forecasting model

The majority of water pipelines are subjected to serious deterioration and degradation challenges. This research examines the application of optimized neural network models for estimating the condition of water pipelines in Shaker Al-Bahery, Egypt. The proposed hybrid models are compared against the classical neural network, adaptive neuro-fuzzy inference system, and group method of data handling using four evaluation metrics. These metrics are; Fraction of Prediction within a Factor of Two (FACT2), Willmott's index of agreement (WI), Root Mean Squared Error (RMSE), and Mean Bias Error (MBE). The results show that the neural network trained using Particle Swarm Optimization (PSO) algorithm (FACT2 = 0.93, WI = 0.96, RMSE = 0.09, and MBE = 0.05) outperforms other machine learning models. Furthermore, three multi-objective swarm intelligence algorithms are applied to determine the near-optimum intervention strategies, namely PSO salp swarm optimization, and grey wolf optimization. The performances of the aforementioned algorithms are evaluated using Generalized Spread (GS), Spread (Δ), and Generational Distance (GD). The results yield that the PSO algorithm (GS = 0.54, Δ = 0.82, and GD = 0.01) exhibits better results when compared to the other algorithms. The obtained near-optimum solutions are ranked using a new additive ratio assessment and grey relational analysis decision-making techniques. Finally, the overall ranking is obtained using a new approach based on the half-quadratic theory. This aggregated ranking obtains a consensus index and a trust level of 0.97.

Multi-objective swarm intelligence (MOSI) metaheuristics were proposed to solve multi-objective optimization problems (MOPs) that consists of two or more conflict objectives, in which improving an objective leads to the degradation of the other. The MOSI algorithms are based on the integration of single objective algorithms and multi-objective optimization (MOO) approach. The MOO approaches include scalarization, Pareto dominance, decomposition and indicator-based. In this paper, the status of MOO research and state-of-the-art MOSI algorithms namely, multi-objective particle swarm, artificial bee colony, firefly algorithm, bat algorithm, gravitational search algorithm, grey wolf optimizer, bacterial foraging and moth-flame optimization algorithms have been reviewed. These reviewed algorithms were mainly developed to solve continuous MOPs. The review is based on how the algorithms deal with objective functions using MOO approaches, the benchmark MOPs used in the evaluation and performance metrics. Furthermore, it describes the advantages and disadvantages of each MOO approach and provides some possible future research directions in this area. The results show that several MOO approaches have not been used in most of the proposed MOSI algorithms. Integrating other different MOO approaches may help in developing more effective optimization algorithms, especially in solving complex MOPs. Furthermore, most of the MOSI algorithms have been evaluated using MOPs with two objectives, which clarifies open issues in this research area.

Multiobjective heuristic algorithm for de novo protein design in a quantified continuous sequence space

Recently, multiobjective swarm intelligence optimization (SIO) algorithms have attracted considerable attention as disease model-free methods for detecting high-order single nucleotide polymorphism (SNP) interactions. However, a strict Pareto optimal set may filter out some of the SNP combinations associated with disease status. Furthermore, the lack of heuristic factors for finding SNP interactions and the preference for discrimination approaches to disease models are considerable challenges for SIO. We compared MP-HS-DHSI with four state-of-the-art SIO algorithms for detecting high-order SNP interactions for 20 simulation disease models and a real dataset of age-related macular degeneration. The experimental results revealed that our proposed method can accelerate the search speed efficiently and enhance the discrimination ability of diverse epistasis models. https://github.com/shouhengtuo/MP-HS-DHSI. Supplementary data are available at Bioinformatics online.

The combined effect of optimal control and swarm intelligence on optimization of cancer chemotherapy

Nowadays, data are generated from smart devices in huge volumes, different formats, and high pace, which comply with Big Data characteristics. Big Data led to the emergence of new technologies, such as Hadoop and Spark to provide both data management and analysis. Analysing Big Data is a time-consuming process. Particle swarm and ant colony optimisation are population-based meta-heuristic methods. They have been combined with data mining techniques to solve MultiObjective Problems (MOPs) of small and medium sized data, presenting good performance. However, when applying these methods to solve MOPs in Big data, an efficient scalable framework will be required. In this paper, we summarise new technologies proposed to manage and analyse Big Data. We present how meta-heuristics can be adapted with Big Data technologies. We characterise problems arose when analysing MO Big Data problems, in addition to proposed methods to overcome these problems, giving examples in Bioinformatics field.

Nowadays, data are generated from smart devices in huge volumes, different formats, and high pace, which comply with Big Data characteristics. Big Data led to the emergence of new technologies, such as Hadoop and Spark to provide both data management and analysis. Analysing Big Data is a time-consuming process. Particle swarm and ant colony optimisation are population-based meta-heuristic methods. They have been combined with data mining techniques to solve MultiObjective Problems (MOPs) of small and medium sized data, presenting good performance. However, when applying these methods to solve MOPs in Big data, an efficient scalable framework will be required. In this paper, we summarise new technologies proposed to manage and analyse Big Data. We present how meta-heuristics can be adapted with Big Data technologies. We characterise problems arose when analysing MO Big Data problems, in addition to proposed methods to overcome these problems, giving examples in Bioinformatics field.

Joint optimization of geophysical data using multi-objective swarm intelligence

A fault on a power distribution system may cause electricity interruption for several consumers, so a good restoration plan is required to decrease such interruptions duration and, consequently, assure the quality of service. Among the measures for service restoration, there is the dispatch of inspection and maintenance crews. The routing of these teams can be classified as a case of the multiple traveling salesman problem. Although involved in series of decision problems, the power distribution system maintenance crews routing is addressed, in the most part of the literature, as a single-objective problem, an instance of a multi-objective one, or as a multi-objective aggregating approach, which generates a single solution in an optimization run, in contrast with the set of equally good solutions, known as Pareto set, the result of a multi-objective problem. In this paper, a Pareto based multi-objective discrete particle swarm optimization approach was applied with the aim of reducing the patrol duration and also the total crews displacement. Wherein the concept of epsilon-dominance was used to update the set of non-dominated solutions, resulting in a good spreading and convergence of them. To promote an uniform exploration of the Pareto set, the selection of the local leaders of the archive was based on square root distance metrics. The Dijkstra algorithm was employed to find the shortest path between two consecutive points of the route of each team. As a result, a set of solutions were obtained for the routing of maintenance crews for power distribution system restoration.

In this study, we aim to develop a system optimization model of Railway Freight Transportation Routing Design (RFTRD) and conduct solution analysis which is based on the improved multi-objective swarm intelligence algorithm. The proposed improved multi-objective swarm intelligence algorithm is applied to solve the combinatorial optimization problem of railway door-to-door freight transportation through design, and provide decision support for railway vehicle door-to-door freight transportation through design. The optimization results shows that, the random multi-neighborhood based multi-objective shuffled frog-leaping algorithm with path relinking (RMN-MOSFLA-PR) can be better applied to solve the combined multi-objective optimization problem, and this proposed improved algorithm can find Pareto frontier through the comparative analysis in the design example of railway door-to-door freight transportation. The frontier can provide support for railway transportation enterprises, arrange the decision-making of the starting and ending stations for multiple shippers, and optimize the use of existing transportation resources, so as to reduce the transportation cost and time of the system.

With the development of railway transportation, the railway transportation enterprises expand their freight transportation from station-to-station transportation to door-to-door transportation, which makes the routing design more complicated. The existing classical optimization algorithms are difficult to meet the needs of practical applications. Therefore, the paper introduces an Improved Multi-objective Quantum-behaved Particle Swarm Optimization algorithm (IMOQPSO). Then based on the continuous coding for the Railway Freight Transportation Routing Design, the proposed improved algorithm was applied to solve the problem to verify the performance of algorithm. Finally, the paper compared the performance of Improved Multi-objective Quantum-behaved Particle Swarm Optimization algorithm with other four continuous multi-objective swarm intelligence algorithms. The results shown that the proposed algorithm obtained the best Pareto front which is closer to the real Pareto front of Railway Freight Transportation Routing Design. Hence, the proposed Improved Multi-objective Quantum-behaved Particle Swarm Optimization algorithm can provide support for the railway transport enterprises routing design decisions to some extent.

The large-scale tasks processing for big data using cloud computing has become a hot research topic. Most of previous work on task processing is directly customized and achieved through existing methods. It may result in relatively more system response time, high algorithm complexity and resource waste, etc. Based on this argument, aiming at realizing overall load balancing, bandwidth cost minimization and energy conservation while satisfying resource requirements, a novel large-scale tasks processing approach called TOPE (Two-phase Optimization for Parallel Execution) is developed. The deep reinforcement learning model is designed for virtual link mapping decisions. We treat whole network as a multi-agent system and the whole process of selecting each node's next hop node is formalized via Markov decision process. We train the learning agent by deep neural network to store parameters of deep network model while approximating the value function, rather than tons of state-action values. The virtual node mapping is achieved by designed distributed multi-objective swarm intelligence to realize our two-phase optimization for task allocation in topology structure of Fat-tree. We provide experiments to show the ability of TOPE in analyzing task requests and infrastructure network. The superiority of TOPE for large-scale tasks processing is convincingly demonstrated by comparing with state-of-the-art approaches in cloud environment.

A suite of swarm dynamic multi-objective algorithms for rebalancing extremely imbalanced datasets

A partial feedback reporting scheme for LTE mobile video transmission with QoS provisioning