Adaptive Resource Allocation in Cloud Data Centers using Actor-Critical Deep Reinforcement Learning for Optimized Load Balancing

International Journal on Recent and Innovation Trends in Computing and Communication, Journal Year: 2023, Volume and Issue: 11(5s), P. 310 - 318

Published: May 18, 2023

This paper proposes a deep reinforcement learning-based actor-critic method for efficient resource allocation in cloud computing. The proposed uses an actor network to generate the strategy and critic evaluate quality of allocation. networks are trained using learning algorithm optimize strategy. is evaluated simulation-based experimental study, results show that it outperforms several existing methods terms utilization, energy efficiency overall cost. Some algorithms managing workloads or virtual machines have been developed previous works effort reduce consumption; however, these solutions often fail take into account high dynamic nature server states not implemented at sufficiently enough scale. In order guarantee QoS while simultaneously lowering computational consumption physical servers, this study Actor Critic based Compute-Intensive Workload Allocation Scheme (AC-CIWAS). AC-CIWAS captures feature continuous manner, considers influence different on consumption, accomplish logical task determine how best allocate efficiency, Deep Reinforcement Learning (DRL)-based (AC) calculate projected cumulative return over time. Through simulation, we see can workload job scheduled with assurance by around 20% decrease compared baseline methods. report also covers ways which technology could be used computing offers suggestions future study.

Language: Английский

---

An optimal wavelet transform grey multivariate convolution model to forecast electricity demand: a novel approach

Grey Systems Theory and Application, Journal Year: 2023, Volume and Issue: 14(2), P. 233 - 262

Published: Nov. 10, 2023

Purpose For some years now, Cameroon has seen a significant increase in its electricity demand, and this need is bound to grow within the next few owing current economic growth ambitious projects underway. Therefore, one of state's priorities mastery demand. In order get there, it would be helpful have reliable forecasting tools. This study proposes novel version discrete grey multivariate convolution model (ODGMC(1,N)). Design/methodology/approach Specifically, linear corrective term added structure, parameterisation done way that consistent modelling procedure cumulated function ODGMC(1,N) obtained through an iterative technique. Findings Results show more stable can extract relationships between system's input variables. To demonstrate validate superiority ODGMC(1,N), practical example drawn from projection demand till 2030 used. The findings reveal proposed higher prediction precision, with 1.74% mean absolute percentage error 132.16 root square error. Originality/value These interesting results are due (1) stability resulting good adequacy parameters estimation their implementation, (2) addition takes into account impact time t on model's performance (3) removal irrelevant information data by wavelet transform filtration. Thus, suggested ODGMC robust predictive monitoring tool for tracking evolution needs.

Language: Английский

---

Short-term power load forecasting based on SKDR hybrid model

Electrical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 13, 2024

Language: Английский

---

Prediction of Clean Coal Ash Content in Coal Flotation through a Convergent Model Unifying Deep Learning and Likelihood Function, Incorporating Froth Velocity and Reagent Dosage Parameters

Processes, Journal Year: 2023, Volume and Issue: 11(12), P. 3425 - 3425

Published: Dec. 13, 2023

This study successfully achieved high-precision detection of the clean coal ash content in froth flotation domain by integrating deep learning with likelihood function. Methodologically, a novel data processing and prediction framework was established combining Keras neural network function from probability statistics. The SIFT algorithm utilized to extract key feature points descriptors images, keypoint matching mean-shift clustering algorithms were employed accurately obtain information on foam motion trajectories velocities. For parameter optimization, maximum estimation applied find optimal estimates function, ensuring enhanced model accuracy. By incorporating optimized parameters into network, an efficient constructed for dosage reagents, velocity, content. model’s evaluation involved six performance metrics. experimental results highly significant, R2 at 0.99997%, RMSE 0.04458%, MAE 0.00170%, MAPE 0.02329%, RRSE 0.00994%, MAAPE 0.00067%.

Language: Английский

---

Research on construction and management strategy of carbon neutral stadiums based on CNN-QRLSTM model combined with dynamic attention mechanism

Frontiers in Ecology and Evolution, Journal Year: 2023, Volume and Issue: 11

Published: Oct. 17, 2023

Introduction Large-scale construction projects such as sports stadiums are known for their significant energy consumption and carbon emissions, raising concerns about sustainability. This study addresses the pressing issue of developing carbon-neutral by proposing an integrated approach that leverages advanced convolutional neural networks (CNN) quasi-recurrent long short-term memory (QRLSTM) models, combined with dynamic attention mechanisms. Methods The proposed employs CNN-QRLSTM model, which combines strengths CNN QRLSTM to handle both image sequential data. Additionally, mechanisms adaptively adjust weights based on varying situations, enhancing model's ability capture relevant information accurately. Results Experiments were conducted using four datasets: EnergyPlus, ASHRAE, CBECS, UCl. results demonstrated superiority model compared other achieving highest scores 97.79% accuracy, recall rate, F1 score, AUC. Discussion integration deep learning models in stadium management offers a more scientific decision support system stakeholders. facilitates sustainable choices reduction resource utilization, contributing development stadiums.

Language: Английский

---