Around 3.15% of the total world energy consumption accounts for Information and Com-
munication Technology (ICT) sector. ICT's contribution to global greenhouse gas emission is expected to double in the coming five years.
Base transceiver station (BTS), an important but energy hungry component of access network in a cellular communication system, is usually resourced to serve busy hour traffic but remains under-utilized for most of the 24-hour period irrespective of the traffic load.
Hence, self organizing networks (SON) that react to the variable traffic load are being studied to minimize energy consumption without compromising the QoS of the network.
Discrete time Markov decision process (DTMDP) as an optimization tool to manage the operation of BTS is investigated in this thesis. MDP _nds an optimal policy that takes state specific optimal decisions, i.e. actions, and gets immediate rewards which maximizes the long term expected reward. The rewards obtained are the power savings when BTS operates as a SON by means of dynamic sectorization against the operation of BTS in uppermost mode irrespective of the traffic load. Further, transition cost to address mode switching cost and delay cost to address QoS are also discussed and elaborated through appropriate simulation to realize the actual energy savings.