A Prediction-Based Overload Control Algorithm for SIP Servers

Garroppo, Rosario G.; Giordano, Stefano; Niccolini, Saverio; Spagna, Stella

doi:10.1109/tnsm.2011.011211.1000010

Cited by 28 publications

(22 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A PI controller has been designed to regulate the retransmissions rate at the upstream server to track a set-point of redundant messages rate, thus mitigating overload of the downstream server without requiring an explicit feedback. In [24] an overload mechanism combining local and remote control has been proposed, the former using a priority FIFO queue at the SIP proxy during overload episodes, the latter based on a prediction technique placed at the remote control loop.…”

Section: Related Workmentioning

confidence: 99%

“…Finally, it is worth noting that performance evaluation of the proposed controllers in [4], [21], [22], [29], [24], [27] has been carried out only by using discrete events simulators whereas an experimental evaluation is not provided. The only exception is [26], which evaluates the performance mostly through simulations but also considers a brief experimental evaluation.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Local SIP Overload Control: Controller Design and Optimization by Extremum Seeking

Cicco

Cofano

Mascolo

2015

IEEE Trans. Control Netw. Syst.

View full text Add to dashboard Cite

The Session Initiation Protocol (SIP) is a signaling protocol for managing various types of real time sessions between parties over an Internet Protocol network. An open issue is the control of overload situations that occur when the incoming flow of requests to a SIP server overcomes the server processing capacity. In particular, call establishment times increase due to overload, which triggers retransmissions and causes a further increase of the total incoming flow of requests. This paper proposes an overload control system for regulating both the queue length and the CPU load of the SIP server. The proposed control system is made of two PI controllers tuned by minimizing a proper cost function using the Extremum Seeking algorithm. A real working implementation of the SIP overload controller has been made in the open source SIP server Kamailio. A performance evaluation and comparison of the proposed controller with the main proposals existing in literature has been carried out. Results show that the proposed control system counteracts overload situations and provides a goodput close to the optimal while maintaining low call establishment delays and retransmission ratios.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Local SIP Overload Control: Controller Design and Optimization by Extremum Seeking

Cicco

Cofano

Mascolo

2015

IEEE Trans. Control Netw. Syst.

View full text Add to dashboard Cite

show abstract

“…Its direct upstream neighbors only follow the received restrictions to throttle traffic forwarded to the overloaded server. This type of overload control is adopted by Hilt and Widjaja (2008), Noel and Johnson (2007), Shen et al (2008), and Garroppo et al (2011). On the other hand, in sender-based control, the overloaded server only implements local overload control which rejects requests by using 503 responses.…”

Section: Related Workmentioning

confidence: 99%

“…The time series prediction is well investigated and many predictors have been proposed in control systems (Garroppo et al, 2011;Hayes, 1996;Haykin, 1991;Mishra et al, 1996;Adas, 1998;Garroppo et al, 2008). Among these predictors, the linear predictors can provide low complexity as well as high accuracy and responsiveness (Garroppo et al, 2008).…”

Section: Prediction Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Probe-based end-to-end overload control for networks of SIP servers

Wang

Liao

et al. 2014

Journal of Network and Computer Applications

View full text Add to dashboard Cite

The Session Initiation Protocol (SIP) has been adopted by the IETF as the control protocol for creating, modifying and terminating multimedia sessions. Overload occurs in SIP networks when SIP servers have insufficient resources to handle received messages. Under overload, SIP networks may suffer from congestion collapse due to current ineffective SIP overload control mechanisms. This paper introduces a probe-based end-to-end overload control (PEOC) mechanism, which is deployed at the edge servers of SIP networks and is easy to implement. By probing the SIP network with SIP messages, PEOC estimates the network load and controls the traffic admitted to the network according to the estimated load. Theoretic analysis and extensive simulations verify that PEOC can keep high throughput for SIP networks even when the offered load exceeds the capacity of the network. Besides, it can respond quickly to the sudden variations of the offered load and achieve good fairness.

show abstract

Optimizing VoIP server resources using linear programming model and autoscaling technique: An SDN approach

Montazerolghaem

2021

Concurrency and Computation

View full text Add to dashboard Cite

Summary Nowadays, the Voice Over IP (VoIP) technology is an important component of the communications industry as well as a low‐cost alternative to Public Switched Telephone Networks. Communication in VoIP networks consists of two main phases, for example, signaling and media exchange. VoIP servers are responsible for signaling exchange using the Session Initiation Protocol (SIP) as the signaling protocol. The saturation of SIP server resources is one of the issues with the VoIP network, which causes problems such as overload or loss of energy. Resource saturation occurs mainly due to a lack of integrated server resource management. In the traditional VoIP networks, management and routing are distributed among all equipment, including servers. These servers are overloaded during peak times and face energy loss during idle times. Given the importance of this issue, this paper introduces a framework based on Software‐Defined Networking technology for SIP server resource management. The advantage of this framework is to have a global view of all the server resources. In this framework, the resource allocation optimization problem and resource autoscaling are presented to deal with the problems posed. The goal is to maximize total throughput and minimize energy consumption. In this regard, we seek to strike a balance between efficiency and energy. The proposed framework is implemented in the actual testbed. The results show that the proposed framework has succeeded in achieving these goals.

show abstract

A Prediction-Based Overload Control Algorithm for SIP Servers

Cited by 28 publications

References 12 publications

Local SIP Overload Control: Controller Design and Optimization by Extremum Seeking

Local SIP Overload Control: Controller Design and Optimization by Extremum Seeking

Probe-based end-to-end overload control for networks of SIP servers

Optimizing VoIP server resources using linear programming model and autoscaling technique: An SDN approach

Contact Info

Product

Resources

About