High costs for fossil fuels and escalating installations of alternate energy sources are daunting main challenges in power systems by making the economic operation and planning of power system as high tasks among the ...
详细信息
High costs for fossil fuels and escalating installations of alternate energy sources are daunting main challenges in power systems by making the economic operation and planning of power system as high tasks among the major assignments in the power generation. In this paper we solve one of the main featured economic problems of power system by optimizing the economic load dispatch problem by linear programming and compared it with firefly algorithm and lambda iteration method. We have applied the proposed algorithm on different systems of generation units and the results proved the attainment of optimal point when compared with different algorithms.
As AI research surges in both impact and volume, conferences have imposed submission limits to maintain paper quality and alleviate organizational pressure. In this work, we examine the fairness of desk-rejection syst...
详细信息
Decentralized learning has emerged as a popular method due to its excellent scalability and parallel implementation of stochastic gradient methods. However, the main challenges in decentralized learning include the co...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Decentralized learning has emerged as a popular method due to its excellent scalability and parallel implementation of stochastic gradient methods. However, the main challenges in decentralized learning include the communication overhead and privacy concerns associated with sharing gradients with neighbors. In this work, we design a novel deep quantizer to address these simultaneously, ensuring differential privacy and communication efficiency. Specifically, we learn a deep quantizer such that the induced quantization noise can be modeled as additive Gaussian noise. We also propose an encoding-decoding scheme that ensures unbiasedness and bounded variance for the quantized output. For smooth objective functions, we bound the function values in terms of the norm of the gradient, the second-order gradient moment, and the induced quantization noise. We demonstrate superior performance of decentralized stochastic gradient with the proposed deep quantizer for a least square regression problem. Additionally, we analyze the performance of the proposed approach for various quantization levels, privacy budgets, batch sizes, and numbers of nodes in the network.
With the widespread integration of distributed energy resources, virtual power plants (VPPs) have emerged as an advanced management model for distributed energy. As technology continues to advance, achieving efficient...
详细信息
This paper presents an optimization method for air conditioner parameters based on dynamic simulation and genetic algorithms, aiming to reduce the time required to reach the target room temperature. A dynamic simulati...
详细信息
ISBN:
(数字)9798350389579
ISBN:
(纸本)9798350389586
This paper presents an optimization method for air conditioner parameters based on dynamic simulation and genetic algorithms, aiming to reduce the time required to reach the target room temperature. A dynamic simulation model was developed to analyze room temperature changes and estimate the time to achieve the target temperature. The model integrates room thermal properties, air conditioning performance, and principles of heat transfer. We considered a specific room model, including its dimensions, air mass, external wall area, and thermal transmittance, as well as the operating parameters of the air conditioner, such as airflow and cooling differential. To optimize the geometry, inlet/outlet configuration, and airflow characteristics of the air conditioner, we constructed an objective function to minimize cooling time and set a series of geometric and airflow constraints. Using the Adaptive Inversion Genetic Algorithm (AIGA), we enhanced the global and local optimization capabilities of the standard Genetic Algorithm (GA) through adaptive crossover, mutation, and inversion operations, optimizing the design parameters of the air conditioner. Finally, we optimized the air conditioner design parameters using a genetic algorithm, successfully reducing the cooling time from 100 seconds to 51 seconds while meeting volume and airflow balance constraints. The optimized air conditioner design parameters, including dimensions and inlet/outlet configurations, significantly improved air circulation efficiency, proving the effectiveness and practical potential of genetic algorithms in solving complex multi-constraint design problems.
Recently, heterogeneous wireless networks have been integrated to provide mobile users to access services without restriction of different access networks, e.g., cellular systems and WLANs. Thus, the mobile users can ...
详细信息
Recently, heterogeneous wireless networks have been integrated to provide mobile users to access services without restriction of different access networks, e.g., cellular systems and WLANs. Thus, the mobile users can obtain the services with higher data rate and quality in anywhere and at any time seamlessly. To support such scenario, it requires a vertical handover (VHO) mechanism that can decide to select the best connection among different access networks from various factors. An analytic hierarchy process (AHP) is one of the methods used in VHO decision by finding the optimal solution based on multiple attribute approach. However, there is a validity acceptance limitation of AHP, due to the score and weight of attributes, or network factors, are assigned by decision makers. This article proposes the VHO decision mechanism that improves a scoring method of AHP by deploying a linear programming (LP) technique instead of human knowledge. The LP is used to find the optimized values among various network factors. Then, the optimized values are taken to replace the human score in the AHP for VHO decision. The received signal strength (RSS), data rate, and throughput are used as the attributes, or variables, related to network factors. The experiment is conducted by simulation to verify the result of proposed VHO decision mechanism between a cellular network and WLANs. The simulation result expresses that the LP can provide the optimized network factors used for scoring in the AHP. It could also be implied that the proposed VHO decision mechanism yields the best network connection based on the optimized values obtained from the LP used instead of human knowledge.
In the field of network analysis, methods for identifying community structure often involve optimizing a specific objective function to achieve a single optimal allocation from network nodes to communities. However, i...
详细信息
ISBN:
(数字)9798331533816
ISBN:
(纸本)9798331533823
In the field of network analysis, methods for identifying community structure often involve optimizing a specific objective function to achieve a single optimal allocation from network nodes to communities. However, in practice, we often encounter multiple division schemes with high quality scores that are close to the overall optimum. In fact, an accurate depiction of the community structure is more appropriately achieved by a series of high-quality division schemes rather than relying on a single optimal solution alone. However, such a collection of network divisions may be difficult to interpret, as its size may rapidly expand to hundreds or even thousands. To this end, this paper introduces an innovative strategy to reveal the diversity of network community structures more comprehensively and to provide a set of more globally-visioned delineation results by clustering similar network divisions and then selecting representative divisions from each cluster.
The optimal transportation problem, first suggested by Gaspard Monge in the 18th century and later revived in the 1940s by Leonid Kantorovich, deals with the question of transporting a certain measure to another, usin...
详细信息
The decimation of high-frequency (HF) features during exhaustive low-dose computed tomography(LDCT) denoising introduces structural deformation. This paper addresses the aforementioned issue by introducing a GAN frame...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
The decimation of high-frequency (HF) features during exhaustive low-dose computed tomography(LDCT) denoising introduces structural deformation. This paper addresses the aforementioned issue by introducing a GAN framework that provides novel adversarial training via discriminators in the wavelet and spatial domains. The wavelet-domain discriminator forces the generator to gain knowledge of the HF features via HF wavelet details (LH, HL, HH) and minimizes structural distortion. The generator network uses a spatial-domain discriminator to preserve local and global pixel correlations without altering the low-frequency (LF) features. Furthermore, we develop a generator network using a novel stationary wavelet-based residual block (SWTRB), which adaptively integrates spatial and frequency-domain information. In addition, we propose a wavelet-domain objective function on HF components, further improving the diagnostic quality of CT images. The experimental results demonstrate that the proposed method outperforms several state-of-the-art techniques on publicly available datasets, including "2016 NIH-AAPM-Mayo Clinic LDCT " and "Low-dose CT image and projection."
Parangtritis, a popular tourist destination on the southern coast of Java, faces a high tsunami risk due to tectonic activity along nearby subduction zones. The main challenges in this area include a large number of t...
详细信息
ISBN:
(数字)9798331508616
ISBN:
(纸本)9798331508623
Parangtritis, a popular tourist destination on the southern coast of Java, faces a high tsunami risk due to tectonic activity along nearby subduction zones. The main challenges in this area include a large number of tourists, vulnerable populations such as the elderly and disabled, and limited shelter capacity, which can lead to congestion during evacuation. To address these issues, this study proposes a multi-objective approach using the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to support efficient and adaptive evacuation planning. The model optimizes five objective functions: evacuation distance, evacuation time, shelter capacity, congestion costs, and shelter distribution variance, while conducting sensitivity analysis to ensure solution stability. The implementation results show that NSGA-II effectively generates high-quality Pareto fronts, validated using hypervolume and Generational Distance (GD) metrics, and highlights trade-offs between evacuation objectives, offering data-driven insights for designing more efficient evacuation strategies in Parangtritis.
暂无评论