Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Congestion control merupakan salah-satu mekanisme yang penting dalam jaringan komputer, termasuk Internet. Banyak penelitian yang telah mencoba menghasilkan congestion control yang efektif mengatur jaringan sehingga tidak terjadi congestion selagi memastikan Quality of Service (QoS) yang baik. Sejak tahun 1988, telah banyak algoritma congestion control yang dibuat untuk mengatasi hal tersebut. Selama ini, pada umumnya algoritma congestion control menggunakan konsep rule-based yang mana algoritma tersebut mengatur jaringan berdasarkan aturan-aturan yang sudah ditentukan oleh manusia. Seiring berkembangnya teknologi kecerdasan buatan dan pembelajaran mesin, semakin banyak congestion control yang mulai dikembangkan menggunakan teknologi tersebut. Salah satu teknologi pembelajaran mesin yang cocok digunakan untuk congestion control adalah deep reinforcement learning. Pembelajaran mesin dimanfaatkan untuk mengganti manusia dalam menciptakan aturan yang digunakan congestion control untuk menghasilkan congestion control berbasis deep reinfocement learning (DRL-CC). Penggunaan pembelajaran mesin dipercaya memiliki kemampuan untuk mengatasi kondisi jaringan yang semakin dinamis dibandingkan pada abad ke-20. Penelitian ini merupakan lanjutan dari penelitian sebelumnya yang bertujuan untuk memperbaiki algoritma DRL-CC yang sudah diciptakan yaitu Aurora dengan memodifikasi algoritma tersebut. Penelitian ini membandingkan Aurora dengan modifikasi DRL-CC tersebut pada kasus pemakaian yang semakin relevan pada masa ini yaitu streaming video untuk mencari tahu apakah modifikasi tersebut bersifat robust. Dilakukan eksperimentasi pada DRL-CC tersebut menggunakan Pantheon pada bermacam skenario jaringan termasuk skenario streaming video. Ditemukan bahwa pada skenario streaming video, modifikasi Aurora memiliki performa yang lebih baik dari Aurora asli. Terdapat penurunan sebesar 1.87 kali lebih rendah pada kategori delay yang dihasilkan oleh modifikasi Aurora. Selain itu, modifikasi Aurora mampu menekan loss rate yang dialami sebesar 2.36 kali lebih rendah. ......Congestion control is an essential mechanism in computer networks, including the Internet. Many studies have tried to produce congestion control that effectively regulates the network so that congestion does not occur while ensuring good Quality of Service (QoS). Since 1988, many congestion control algorithms have been created to overcome this. So far, congestion control algorithms generally use a rule-based concept where the algorithm manages the network based on rules that have been determined by humans. As artificial intelligence and machine learning technology develop, more and more congestion controls are starting to be developed using this technology. One machine learning technology that is suitable for congestion control is deep reinforcement learning. Machine learning is used to replace humans in creating the rules used by congestion control to produce deep reinforcement learning based congestion control (DRL-CC). The use of machine learning is believed to have the ability to overcome network conditions that are increasingly dynamic compared to those of the 20th century. This research is a continuation of previous research which aims to improve the DRL-CC algorithm that has been created, namely Aurora, by modifying the algorithm. This research compares Aurora with the modified DRL-CC algorithm in a use case that is increasingly relevant today, namely video streaming, to find out whether the modification is robust. Experiments were carried out on DRL-CC using Pantheon in various network scenarios, including video streaming. It was found that in the video streaming scenario, the modified Aurora performed better than the original Aurora. There was a decrease of 1.87 times in the delay category produced by the Aurora modification. Apart from that, the Aurora modification was able to reduce the loss rate experienced by 2.36 times lower.

Abstrak :
Mekanisme kontrol kongesti yang berbeda antara TCP dengan ATM menjadi latar belakang penelitian ini untuk meneliti bagaimana pengaruh interaksi kontroI kongesti TCP dan ATM terhadap performansi TCP pada jaringan ATM. Penelitian juga dilakukan terhadap pengaruh variasi ukuran window, kapasitas link dan jenis kontrol kongesti TCP terhadap performansi TCP pada ATM. Penelitian dilakukan pada model topologi network parking lot dengan menggunakan The NIST ATM/HFC Network Simulator. Dari hasil penelitian diperoleh bahwa meningkatkan prosentase goodput dengan meningkatkan ukuran advertised window dan kapasitas link dibatasi delay antrian pada switch dan cell loss pada jaringan ATM. Hasil penelitian juga menunjukkan adanya kontrol kongesti ASR pada layer ATM dapat mengurangi cell loss dan memperbaiki fairness index TCP pada ATM Adanya algoritma fast recovery pada TCP Reno hanya memperbaiki fairness index TCP pada ATM sedangkan prosentase goodput mengalami penurunan.

---

The difference congestion control between transmission control protocol (TCP) and asyncronous transfer mode (ATM) has motivated to research the influence of interaction between TCP and ATM congestion control to the performance of TCP over ATM. The research is also examine the impact of advertised window size, link capacity and the type of TCP congestion contol to TCP performance. This research is done on parking lot model and used The NIST ATM/HFC Network Simulator. The finding of the research is to increase goodput percentation by increasing advertised window size and link capacity is limited by queuing delay of the switch and cell loss of ATM Network. The outcome of the research also shows that there is ASR congestion control on ATM layer is to prevent more cell losses and improve fairness index of TCP over ATM. Fast recovery algorithm on TCP Reno is improving fairnes index of TCP over ATM meanwhile percentation goodput is decreasin.

Abstrak :
Congestion Control merupakan salah satu dari bagian dari manajemen jaringan yang menggunakan ATM. Karena terbatasnya sumber daya yang ada untuk dapat melayani seluruh transmisi cell yang berisi data aplikasi, maka kemungkinan terjadinya kongesti besar sekali. Untuk itu untuk menanggulangi dan mencegah adanya kongesti dibuat beberapa metode dengan salah satu metodenya adalah selective cell discard terhadap tagged cell (CLP=1). Pada skripsi ini dibahas mengenai perbandingan antara sistem yang memakai selective cell discard dengan yang tidak melalui pembuatan program guna menghitung peluang hilangnya cell, baik yang untagged maupun tagged cell serta delay untuk untagged cell. Dan model yang digunakan untuk memodelkan sistem antrian pada masukan buffer suatu trunk adalah Markov Modulated Poisson Process (MMPP). Diharapkan dari perbandingan ini dapat diketahui apakah penggunaan metode selective cell discard baik untuk congestion control dan pengaruhnya terhadap Quality of Sevice (QoS) jaringan.

Abstrak :
Cooperative communication is communications that cooperate with another user as and form a virtual array so that can balance the benefits of space diversity systems. In this paper proposed cooperative communication in the building, where two users used as the source, one user as a destination, and six user wich raised randomly as the relay. This research focus examined cross layer optimization which physical layer (example total power consumption) and network layer (example routing and traffic rate ) that influeced by congestion control. Results of examination are chosening the relay on basically of traffic rate, total power consumption, and joint oiptimization of both. And also, mean of traffic rate for source 1 is smaller than source 2 while mean of total power consumption for source 1 is bigger thatn source 2. and varian of traffic rate and total power consumption for source 1 is bigger than source 2.

Abstrak :
Kontrol kongesti merupakan hal yang mendasar dalam jaringan Asynchronous Transfer Mode (ATM) untuk mendukung layanan `best-effort' atau Available Bit Rate (ABR). Dengan kontrol kongesti yang memadai kita dapat memakai jaringan yang ada tanpa harus menegosiasikan kontrak terlebih dahulu dengan jaringan tersebut. Kongesti terjadi bila jumlah kecepatan masukan lebih besar dibandingkan dengan kapasitas keluaran saluran. Pemilihan kontrol kongesti yang tepat memungkinkan setiap kelas layanan dalam ATM berfungsi secara efektif, untuk itu dalam jaringan ATM dikenal dua macam kontrol kongesti `closed loop', yaitu rate-based dan credit-based. Dalam tesis ini akan dianalisa unjuk kerja dua macam skema kontrol kongesti dalam trafik ABR, yaitu skema ERICA dan MIST (rate-based), serta skema QFC (credit-based). Secara umum skema QFC mempunyai throughput keluaran dan Fairness Index yang lebih baik (82 % dan 1) dibandingkan dua skema lainnya pada aplikasi Metropolitan Area Network (MAN), sedangkan kebutuhan bufer ketiga skema relatif kecil. Pada aplikasi Wide Area Network (WAN), nilai throughput dan fairness index skema QFC sebesar 79% dan 0,999 juga merupakan yang terbaik diantara ketiga skema tersebut.

---

Congestion control is essential for Asynchronous Transfer Mode (ATM) network in providing 'best-effort' service, or Available Bit Rate (ABR). With proper congestion control, we can use the network at any time without first negotiating a traffic contract with the network. Congestion will occur when total input rate is larger than the output link capacity. To enable each service class to function effectively two closed loop congestion control, rate-based and credit-based have been introduced for ATM network. This thesis will analyzes performance of two congestion control in ABR traffic, that is ERICA and NIST scheme (rate-based), also QFC scheme (credit-based). As a result, QFC scheme has better throughput and fairness index (82 % and I) than the other scheme in the Metropolitan Area Network (MAN) application. Buffer requirement is relatively small for all schemes. In the Wide Area Network (WAN), QFC scheme is still the best with 79 % of throughput and 0,999 of fairness index.

Abstrak :
This book mainly discusses the most important issues in artificial intelligence-aided future networks, such as applying different ML approaches to investigate solutions to intelligently monitor, control and optimize networking. The authors focus on four scenarios of successfully applying machine learning in network space. It also discusses the main challenge of network traffic intelligent awareness and introduces several machine learning-based traffic awareness algorithms, such as traffic classification, anomaly traffic identification and traffic prediction. The authors introduce some ML approaches like reinforcement learning to deal with network control problem in this book.

Abstrak :
This book presents on the latest research findings, and innovative research methods and development techniques related to the emerging areas of broadband and wireless computing from both theoretical and practical perspectives. Information networking is evolving rapidly with various kinds of networks with different characteristics emerging and being integrated into heterogeneous networks. As a result, a number of interconnection problems can occur at different levels of the communicating entities and communication networks’ hardware and software design. These networks need to manage an increasing usage demand, provide support for a significant number of services, guarantee their QoS, and optimize the network resources. The success of all-IP networking and wireless technology has changed the way of life for people around the world, and the advances in electronic integration and wireless communications will pave the way for access to the wireless networks on the fly. This in turn means that all electronic devices will be able to exchange the information with each other in a ubiquitous way whenever necessary.