Control Theory and Informatics www.iiste.org ISSN 2224-5774 (Paper) ISSN 2225-0492 (Online) Vol.10, 2020 33 COMPARATIVE ANALYSIS OF NEURO- FUZZY AND SIMPLEX OPTIMIZATION MODEL FOR CONGESTION CONTROL IN ATM NETWORK. 1 Sochima Vincent Egoigwe , 2 Stephen Sunday Okika , 3 Timothy Oluwaseun Araoye, 4 Chukwudozie Chukwudi Michael and 5 Nwobi Chukwudumebi Gibson 1,3 Department of Mechatronics Engineering, University of Nigeria, Nsukka, Nigeria. 2 Department of Electrical and Electronics Engineering, Enugu State University of Science and Technology, Enugu State, Nigeria. 4,5 Department of Electronics Engineering, University of Nigeria, Nsukka, Nigeria. Corresponding Author: Sochima Vincent Egoigwe Abstract Congestion always occurred when the transmission rate increased the data handling capacity of the network. Congestion normally arises when the network resources are not managed efficiently. Therefore if the source delivers at a speed higher then service rate queue, the queue size will be higher. Also if the queue size is finite, then the packet will observed delay. MATLAB Software was used to carry out simulations to develop Congestion control optimization Scheme for ATM Network with the aims to reducing the congestion of Enugu ATM Network. The results of the research reveal the minimization of congestion application model for Enugu ATM using optimization and Neuro-fuzzy. The result shows that congestion control model with Optimization and Neuro-fuzzy were 0.00003153 and 0.00002098 respectively. The ATM Congestion was reduced by 0.0000105, which is 18.2% decrease after Neuro-fuzzy controller was used. The results show the application of Neuro-fuzzy model which can use to control and minimized the ATM Congestion of Enugu ATM Network. The result shows that when Neuro-fuzzy is applied the congestion and the packet queue length in the buffer will be minimized. Key words: Congestion, MATLAB, Optimization, Neuro-fuzzy, ATM DOI: 10.7176/CTI/10-05 Publication date:July 31 st 2020 1. Introduction Congestion normally occurred when the transmission Source rate exceeds the data capacity of the network. The degradation in performance is observed. Congestion is said to be occurred if network resources are not efficiently managed. If the source delivers at a rate higher than service rate of queue, then the size of queue will grow. If the size of queue is finite, then packets will experience delay & losses will occur. End users experience delay in delivery of packets, even loss of packets also occurred [3]. Networks that try to send more data than network capacity, lead to data loss and excessive delays in packet delivery [2]. Due to unstable fluctuations and burstiness of traffic flow in ATM networks, congestion occurs frequently [4]. There is choice that show the congestion and where can influence a choice of a control approach with respect to location [3]. Congestion control is a process in which networks adjusts the amount of input data, so that the Quality of Service (QoS) is not degraded and simultaneously try to utilize the network resources efficiently [2].The ATM technique provides an attractive solution to the problem of integrating different types of services, with widely different bit- rates, through common interface and switching fabrics. It is a compromise between packet switching and circuit switching techniques. The traffic control set functions must be provided by the ATM network to ensure the QoS of each service and to produce a high network utilization. The wide range of service characteristics, such as bit rates, burstiness factors, cell delay constraints (latency), cell loss tolerance (accuracy), and priority combined with the need for adaptive, and sometimes real-time services makes the use of traditional control methods very difficult. Although ATM networks can support a wide variety of transmission rates and provide transmission efficiency by asynchronous multiplexing, a cell might be lost in ATM switches if cells are excessively fed into the networks. In order to avoid this situation, the terminals are required to declare their transmission rates as traffic parameters, e.g., peak cell rate (PCR) and sustainable cell rate (SCR), in advance of transmission. According to these declarations of transmission rates, ATM switches judge whether the required QoS can be achieved. if the QoS can be met without deteriorating those of the existing calls, then the call is admitted, otherwise it is rejected. This traffic control function for an ATM system, called connection admission control (CAC), decides whether to accept or reject a call based upon availability of capacity required to support its QoS. Thus an estimate of the