Abstract With the rapid development of telecommunication networks, predictability network traffic is significant interest in analysis and optimization, bandwidth allocation, load balancing adjustment. Consequently, recent years, research attention has been paid to forecasting traffic. Telecommunication problems can be considered a time‐series problem, wherein periodic historical data fed as input model. Time‐series approaches are broadly categorized statistical machine learning (ML) methods...

Home energy management requires accurate information about the appliances' consumption pattern. This can help consumers save energy, control their usage by shifting to off-peak hours and reduce electricity costs. Non-intrusive load monitoring (NILM) in which power profile of appliances are extracted from aggregated signal a household, provides this information. For NILM problem, machine learning approaches as training-based solutions require large training datasets for an disaggregation...

Extensive research has focused on enhancing the efficiency and stability of robotic arms. Sliding mode control (SMC) is commonly used in industrial robots due to its robustness simplicity. However, SMC approaches have challenges such as chattering slow convergence rates which can compromise tracking accuracy. To address these issues, this paper proposes a novel Super-Twisting Fast Non-singular Terminal Mode Control (ST-FNTSMC) strategy for 3-DOF arm robot. The proposed approach significantly...

Abstract Deep learning-based approaches for diagnosing bearing faults have attracted considerable attention in the last years. However, real-world applications, these methods face challenges. For proper training of models, a amount labeled data are necessary, and due to limitations industry, obtaining this may not be possible. Because load variations, distribution test vary, which reduces accuracy trained model various working conditions. Furthermore, noise has significant impact on fault...

In this paper, we introduce a distributed secondary frequency control scheme for an islanded ac microgrid under event-triggered communication. An integral type mechanism is proposed by which each generator (DG) asynchronously and periodically checks its triggering condition determines whether to update inputs broadcast states neighboring DGs. contrast existing strategies on of microgrids, the sampled-data based mechanism, DGs need not be synchronized common clock individual DG periodically,...

Synchronization between two coupled complex networks with fractional-order dynamics, hereafter referred to as outer synchronization, is investigated in this work. In particular, we consider systems consisting of interconnected nodes. The state variables each node evolve time according a set (possibly nonlinear and chaotic) differential equations. One the plays role master system drives second network by way an open-plus-closed-loop (OPCL) scheme. Starting from simple analysis synchronization...

In this paper, a robust fractional-order controller is designed to control the congestion in transmission protocol (TCP) networks with time-varying parameters. Fractional controllers can increase stability and robustness. Regardless of advantages fractional controllers, they are still not common TCP networks. The network parameters time-varying, so important design. Therefore, we focused on PID developed based active queue management (AQM). D-partition technique used. most property...

Nowadays, the demand for electrical energy is increasing, and conventional power systems will face major problems in future if they cannot generate extra energy. One of best solutions solving use renewable resources to produce The main aim this study designing controlling microgrid voltage frequency. This proposed frequency control an islanded based on fuzzy logic controller. system considered consists Proton‐Exchange Membrane Fuel Cell (PEMFC) that connected parallel inverters convert DC AC...

In terms of network topology, one the extensively utilized technologies is intrusion detection system (IDS). Despite applying numerous machine learning approaches (supervised and unsupervised) to enhance efficacy, reaching high-grade performance still a challenging problem for existing algorithms. This study presents new technique IDS that focuses on various deep neural networks (DNNs) their combination data classification. The proposed model consists three parts: (1) feature selection...

Network traffic forecasting means estimating future network from previous observations. analysis has various applications in a wide range of fields, and considerable research attention been paid to this area recent years. Accurate plays an important role management improving the Quality Of Services (QoS). For purpose, techniques have applied such as neural network-based methods data mining methods. This paper concentrated on examining analyzing based deep learning. Therefore several...

In this letter, the formation control problem of multi-agent systems with directed communication graphs is considered. A novel distributed event-triggered approach, which involves complex Laplacian, proposed to address problem. The event condition depends on periodic samplings agent states, automatically eliminates possibility Zeno behavior. Then, it shown that, under simple verifiable conditions, strategy results in desired agents. Finally, are verified by numerical examples.

Using inverter‐based topologies and lack of rotational masses can lead to a noticeable reduction in the inertia modern systems have detrimental effects on resiliency, stability strengths microgrids. Effective frequency control ancillary services adaptive mechanisms be proposed resolve mentioned challenges practically. From this perspective, several flexible intelligent approaches been recently introduced create balance between generation load demand during various operational conditions...

In the majority of current supervised nonintrusive load monitoring (NILM) techniques characteristics training and test datasets are assumed to be constant. However, in practice, a new appliance may added set electrical appliances, an replaced by one, efficiency change during time, or fault occur. All these issues appliances cause abnormal consumption total signal not detecting them reduces NILM accuracy. this sense, submetering is widely used address above challenge. it leads additional...

The objective of this study was to determine the effect different durations n-3 supplementation during peripartal period on production and reproduction performance Holstein dairy cows. Thirty-two dry cows (16 multiparous 16 primiparous) were blocked within parity for similar expected calving dates 8 wk before calving. Cows blocks assigned randomly 1 4 treatments: (1) control without fatty acid (FA) period; (2) FA whole (8 wk); (3) early (first 5 wk; far-off), or (4) late (last 3 close-up)....