Blue-green algae are ancient organisms capable of photosynthesis with strong vitality. However, the toxins they produce pose a threat to human health and water safety. Global warming and water pollution have led to fr...
详细信息
ISBN:
(纸本)9789819607945;9789819607952
Blue-green algae are ancient organisms capable of photosynthesis with strong vitality. However, the toxins they produce pose a threat to human health and water safety. Global warming and water pollution have led to frequent outbreaks of algal blooms worldwide. Therefore, accurate prediction of blue-green algae concentration and early warning is crucial for effective algae management. However, current prediction models often lack accuracy and robustness, limiting their effectiveness in real-world applications. To enhance cyanobacterial bloom prediction accuracy, this paper proposes a time series prediction model for cyanobacterial concentration. The main structure includes wavelet decomposition, a many-objective optimization algorithm, and Gated Recurrent Unit neural network. The main process involves three steps: initially, the cyanobacteria concentration data and environmental variables undergo discrete wavelet decomposition to extract low-frequency trends and high-frequency features. Then, the decomposed data are fed into a two-layer GRU network, fine-tuned by the many-objective optimization algorithm for prediction. Lastly, the predicted outputs are combined to derive the final concentration prediction. To validate the model, we selected three metrics: RMSE (root mean square error), NSE (Nash-Sutcliffe efficiency coefficient), and CORR (correlation coefficient), to evaluate the prediction results. Meanwhile, we conducted tests in three regions: Morgan, Murray Bridge, and Tailem Bend, with RMSE values of 2721, 672, and 470 respectively;NSE values of 0.962, 0.979, and 0.969 respectively;and CORR values of 0.984, 0.990, and 0.986 respectively. The results demonstrate the generalizability of the model.
The characteristics of randomness, running style, and unpredictability of user requirements in the cloud environment, brings great challenges to task scheduling. Meanwhile, the scheduling efficiency of cloud task allo...
详细信息
The characteristics of randomness, running style, and unpredictability of user requirements in the cloud environment, brings great challenges to task scheduling. Meanwhile, the scheduling efficiency of cloud task allocation is an important factor affecting cloud resource systems. Therefore, this paper takes into account the characteristics of tasks, systems and users, a many-objective task scheduling model was constructed in cloud computing. In order to better solve the proposed many-objective task scheduling model, a reference vector guided evolutionary algorithm based on angle-penalty distance of normal distribution (RVEA-NDAPD) is proposed, and compared with the existing standard many-objective evolutionary algorithms (MaOEAs). Simulation results show that the algorithm can effectively improve the performance of the proposed model in cloud computing and obtain a suitable task allocation strategy.
Task scheduling problem refers to how to reasonably arrange many tasks provided by users in virtual machines, which is very important in the cloud computing. And the quality of the scheduling performance directly affe...
详细信息
Task scheduling problem refers to how to reasonably arrange many tasks provided by users in virtual machines, which is very important in the cloud computing. And the quality of the scheduling performance directly affects the customer satisfaction and the provider benefits. In order to describe the task scheduling problem of cloud computing more precisely and improve the scheduling performance. This paper establishes many-objective cloud model, including four objectives: minimizing time, minimizing costs, maximizing resource utilization, and balancing load. At the same time, a many-objective optimization algorithm based on hybrid angles (MaOEA-HA) is proposed to solve this model. Hybrid angle strategy is designed to optimize the algorithm better, which combines two angle strategies: individual-to-individual angle and individual-to-reference point angle. One by one elimination strategy was introduced to remain individuals with better performance. By comparing with five other advanced many-objective optimization algorithms, MaOEA-HA shows the best performance on the DTLZ test suite. Moreover, different algorithms are applied to solve the cloud task scheduling problem, and MaOEA-HA algorithm achieves best results.
Neural networks are arising a wave in the various areas of artificial intelligence and they have adopted in daily life successfully. The structure tuning of neural networks is crucial when building the relative models...
详细信息
Neural networks are arising a wave in the various areas of artificial intelligence and they have adopted in daily life successfully. The structure tuning of neural networks is crucial when building the relative models. The structure of neural networks is usually designed and tuned with experience and plenty of attempts. To reduce the difficulty and cost of structure tuning meanwhile improving its rationality, we propose a new method to tune the structure of neural networks adaptively. In this method, the related structure parameters are optimised. A many-objective algorithm is employed as the optimised tool to get a better structure. We design the experiments combining convolutional neural network (CNN) with Non-dominated Sorting Genetic algorithm III (NSGA-III). The related experiments are conducted on the MNIST and Malware image datasets. Results show that the method has promising performance on neural networks tuning and can improve the robustness.
Due to the growth of users' requests for various resources in cloud computing, the optimal resource allocation is one of the most important challenges in cloud environments. The optimal resource allocation is achi...
详细信息
Due to the growth of users' requests for various resources in cloud computing, the optimal resource allocation is one of the most important challenges in cloud environments. The optimal resource allocation is achieved by considering user requirements stated in Service Level Agreements (SLAB) and the Quality of Services (QoSs) provided by resources. Since some user requirements (objectives) conflict with some others, a optimal trade-off between them is required in the selection of resources. Obtaining such a trade-off is a complicated and NP-hard problem because we may come up with a lot of permutations (choices) of the resources with the desired QoS. If a cloud environment is geographically distributed, the problem becomes more complicated because in the geographically distributed cloud there are a lot of candidate datacenters with qualified resources. The user requirements considered in this paper are availability and reliability of resources should be maximized and resource cost and response time should be minimized as well as the minimization of the network traffic. The maximization of and the minimization of the requirements conflict with each other;therefore a trade-off between them is required. In this paper, a hierarchical structure with two resource selections methods called Simplex Linear Programming (SLP) Method and GrEA-based method are used where the hierarchical structure is used to present connections between distributed datacenters and the methods are used to select optimal resources among the datacenters. The most important feature of the hierarchical structure is to prevent the occurrence of an accumulation of requests in a datacenter leading to increase the rate of finding optimal VMs. Moreover, in most studies on geographically distributed clouds, one user requirement is considered for the optimal selection of resources;however, in this study, datacenters are selected based on 4 user requirements as well as the network traffic. Moreover, while in
The performance of multi-objective evolutionary algorithms can severely deteriorate when applied to problems with 4 or more objectives, called many-objective problems. For Pareto dominance based techniques, available ...
详细信息
The performance of multi-objective evolutionary algorithms can severely deteriorate when applied to problems with 4 or more objectives, called many-objective problems. For Pareto dominance based techniques, available information about some optimal solutions can be used to improve their performance. This is the case of corner solutions. This work considers the behaviour of three multi-objectivealgorithms [Non-dominated sorting genetic algorithm (NSGA-II), Speed-constrained multi-objective particle swarm optimization (SMPSO) and generalized differential evolution (GDE3)] when corner solutions are inserted into the population at different evolutionary stages. The problem of finding corner solutions is addressed by proposing a new algorithm based in multi-objective particle swarm optimization (MOPSO). Results concerning the behaviour of the aforementioned algorithms in five benchmark problems (DTLZ1-5) and respective analysis are presented.
暂无评论