With the advent of small cells like Femto cells which may be randomly placed, go on and off, and usually not accessible to phone companies, it became necessary that these cells coordinate among each other to prevent harmful interference to each other and to maximize some network parameters in what is called SON or self organizing networks. What are the different approaches/ techniques to SONs and how they act?
Several dynamic Interference management algorithm have been proposed so far to address this problem. Read following reference papers
S. Das, H. Viswanathan, and G. Rittenhouse, “Dynamic load balancing
through coordinated scheduling in packet data systems,” in Proc. IEEE
INFOCOM, San Francisco, CA, Mar. 2003, pp. 786–796.
K. Son, Y. Yi, and S. Chong, “Adaptive multi-pattern reuse in multi-cell
networks,” in Proc. WiOpt, Seoul, Korea, June 2009, pp. 1–10.
A. Gjendemsj, D. Gesbert, G. E. Øien, and S. G. Kiani, “Binary power
control for sum rate maximization over multiple interfering links,” IEEE
Trans. Wireless Commun., vol. 7, no. 8, pp. 3164–3173, Aug. 2008.
L. Venturino, N. Prasad, and X. Wang, “Coordinated scheduling and
power allocation in downlink multicell OFDMA networks,” IEEE Trans.
Veh. Technol., vol. 58, no. 6, pp. 2835–2848, July 2009.
A. L. Stolyar and H. Viswanathan, “Self-organizing dynamic fractional
frequency reuse for best-effort traffic through distributed inter-cell
coordination,” in Proc. IEEE INFOCOM, Rio de Janeiro, Brazil, Apr.
2009, pp. 1–9.
Home NodeB Output Power, 3GPP TSG Working Group 4 meeting
TSG-RAN WG1 Contribution R4-070 969, June 2007. [Online].
Available: http://www.3gpp.org/ftp/tsg ran/WG4 Radio/TSGR4 43bis/
Docs/.
V. Chandrasekhar and J. G. Andrews, “Uplink capacity and interference
avoidance for two-tier femtocell networks,” IEEE Trans. Wireless
Commun., vol. 8, no. 7, pp. 3498–3509, July 2009.
Thanks Muhammad, valuable references. I also prefer if you or some one else introduces any of the methods, i.e. giving a small description or so. This can enhance discussion and is much valuable. Thanks again. @AlDmour.
Self organizing networks are begning with only input neurons. During the training process, neurons are selected from a pool of candidates and added to the hidden layers. .
In Develop self organization network the connections between neurons in the network are not fixed but rather are selected during training to optimize the network. The number of layers in the network also is selected automatically to produce maximum accuracy without over fitting.
To get more detail about this network see the following paper [IEEE2013] "Design and Implementation Meta Knowledge System (MKS) "
where, this paper presents the develop of that network.
the following is abstract of that paper
Design and Implementation Meta Knowledge System (MKS)
Abstract: this work attention of develop self organizing networks. The network begins with only input neurons. During the training process, neurons are selected from a pool of candidates and added to the hidden layers. The develop of network focus on using different types of polynomial and hyperbolic functions to trained the network including eleven polynomial function (i.e., Linear of one, two and three variables, Quadratic of one and two variables, Cubic of one variable, Product of two variables, Logistic of one variable, Log of one variable, Exponential of one variable and Asymptotic of one variable ) and six hyperbolic function (i.e., Sinh, Cosh, Tanh, Sinh-1, Cosh-1 and Tanh-1) as describe in Table 1. In final stage, the propose system performs analysis for each type of the models generation by it base on five error predicate measures including Maximum error, RMSE, MSE, MAE and MAPE. In addition, the system determined the best and the worst model from the polynomial and hyperbolic models. By experiments we found all the huge databases have the fix behavior, the best model of their generated by linear of three variables function and worst model of their generated by cubic of one variable or quadratic function related to polynomial models. Add to that, the best model of their generated by tanh of one variable function and worst model of their generated by more than of one other functions related to hyperbolic models. While all the small databases have the not stabile behavior, the best model of their generated by linear of three and two variables or quadratic of two variables function and the worst model of their generated by cubic of one variable or quadratic function related to polynomial models. Add to that, the best model of their generated by inverse of tanh of one variable function and the worst model of their generated by sinh or cosh functions related to hyperbolic models.
Key words: Knowledge management applications, Meta knowledge, Self organization network, Hyperbolic Functions, Polynomial Functions.
- Badges
- Science topic