Reduced complexity algorithms for cognitive packet network routers

Hey, Laurence

doi:10.1016/j.comcom.2008.04.026

Cited by 13 publications

(4 citation statements)

References 16 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The investigation showed RNNs 226-300 times more efficiency in terms of energy performance product as compared to ANNs. Furthermore, authors in [24] introduced a simplified RNN with 2N weights instead of 2N 2 weights for the implementation of smart packet processing.…”

Section: Random Neural Network Distinguished Featuresmentioning

confidence: 99%

Random neural network based cognitive engines for adaptive modulation and coding in LTE downlink systems

Adeel

Larijani

Ahmadinia

2017

Computers & Electrical Engineering

View full text Add to dashboard Cite

This paper presents two random neural network (RNN) based context-aware decision making frameworks to improve adaptive modulation and coding (AMC) in long-term evolution (LTE) downlink systems. In the first framework, AMC is modelled as a traditional classification problem with the aim to maximize the probability of correct classification. The second framework seeks to optimize the throughput as opposed to simply maximizing the probability of the correct classification. To model the second framework, we developed a hybrid cognitive engine (CE) architecture by integrating an RNN based learning algorithm with genetic algorithm (GA) based reasoning. RNN features help CE to concurrently acquire long-term-learning, fast decision making, and less computational complexity, which are essential for the development of any real-time cognitive communication system. The performance of RNN is compared with artificial neural networks (ANN) and state-of-the-art effective exponential SINR mapping (EESM) algorithm. A comprehensive analysis of the proposed RNN based AMC scheme is presented by jointly incorporating the effect of different schedulers, feedback delays, and multi-antenna diversity on the throughput of an orthogonal frequencydivision multiple access (OFDMA) system. The critical analysis of the first framework revealed that RNN based CE can achieve comparable results with faster adaptation, even in severe environment changes without the need of retraining compared to ANN. The analysis of the second approach demonstrated RNNs faster adaptation as compared to ANN with up-to 100% improvement in both system capacity and fairness as compared to EESM algorithm.

show abstract

Section: Random Neural Network Distinguished Featuresmentioning

confidence: 99%

Random neural network based cognitive engines for adaptive modulation and coding in LTE downlink systems

Adeel

Larijani

Ahmadinia

2017

Computers & Electrical Engineering

View full text Add to dashboard Cite

show abstract

Section: Hardware Implementation Of Cpnmentioning

confidence: 99%

“…Alternative algorithms to the RNN were also proposed in [47,48] in order to keep the benefits of the RNN while being less complex and less resource demanding, and therefore, more suitable for implementation in hardware. The approximated RNN (aRNN) [48] is not a neural network model, but attempts to approximate properties of the RNN while using only simple arithmetic operators such as addition and subtraction, and bitwise shifts. A sensible routing (SR) policy (also called 1-SR), introduced in [49], bases its routing decisions on the expected QoS of a possible outcome and selects a path with a probability that is inversely proportional to the expected QoS metric of that path.…”

Section: Hardware Implementation Of Cpnmentioning

confidence: 99%

“…This is beneficial as it makes the CPN suitable for implementation in dedicated hardware for high-speed routers, and also enables it to be used in software-driven devices that lack powerful processors and large memories, such as PDAs or wireless sensor network devices. The authors in [47,48] also propose an architecture for a field programmable gate arraybased hardware CPN router. This design demonstrates that the traditional architectural approaches used in high-speed IP routers are applicable to CPN routers, and thus demonstrates the possibility for hybrid IP/CPN routers in hardware.…”

Section: Hardware Implementation Of Cpnmentioning

confidence: 99%

See 1 more Smart Citation

The Cognitive Packet Network: A Survey

Sakellari

2009

The Computer Journal

View full text Add to dashboard Cite

Current and future multimedia networks require connections under specific quality of service (QoS) constraints which can no longer be provided by the best-effort Internet. Therefore, 'smarter'networks have been proposed in order to cover this need. The cognitive packet network (CPN) is a routing protocol that provides QoS-driven routing and performs self-improvement in a distributed manner, by learning from the experience of special packets, which gather on-line QoS measurements and discover new routes. The CPN was first introduced in 1999 and has been used in several applications since then. Here we provide a comprehensive survey of its variations, applications and experimental performance evaluations.

show abstract

The Random Neural Network and Web Search: Survey Paper

Serrano

2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Reduced complexity algorithms for cognitive packet network routers

Cited by 13 publications

References 16 publications

Random neural network based cognitive engines for adaptive modulation and coding in LTE downlink systems

Random neural network based cognitive engines for adaptive modulation and coding in LTE downlink systems

The Cognitive Packet Network: A Survey

The Random Neural Network and Web Search: Survey Paper

Contact Info

Product

Resources

About