Load-Aware Cell Switching in Ultra-Dense Networks: An Artificial Neural Network Approach
Summary (3 min read)
Introduction
- Base station (BS) switching is one of the most generally accepted techniques for energy saving in mobile cellular networks (MCNs) [1].
- In addition, machine learning models can be trained offline and then plugged into the network in order to enhance realtime decision making by reducing the network delays [7].
- The previously mentioned solutions only consider simplistic network scenarios where very few small cells (SCs) are deployed, hence, such solutions will not be suitable when network dimensions becomes very large and complexity increases.
- Specifically, the authors develop an ANN-based cell switching framework, which is referred to as offline-trained online cell switching , to learn the optimal switching strategy for the SCs in a UDN.
A. Network model
- A heterogeneous UDN, with separate control and data plane, comprising both MC and SCs is considered.
- Four types of SCs (RRH, micro, pico, and femto cell) are considered in the work.
- The MC—which encompasses the footprints of the SCs—is constantly kept on, and also orchestrates the switching operation of the SCs via its backhaul connection to them.
- The SCs, on the other hand, can be turned ON/OFF based on their traffic load and are responsible for handling high data traffic demands.
- Vertical traffic offloading is considered, such that the traffic load of the SCs that are switched OFF are offloaded to the MC to ensure that the quality-of-service (QoS) of the offloaded users are maintained.
B. Power Consumption model
- Ptx and Pm denote the instantaneous and maximum BS transmission power, respectively.
- The total power consumption of the UDN comprises the power consumption of the MC and that of all the SCs deployed under its coverage.
C. Problem Formulation
- The aim of this research is to select the optimal combination of SCs to switch OFF, during periods of low or no traffic in order to minimize the total power consumption of a UDN while ensuring that the QoS of the users originally connected to the switched OFF SCs are maintained by the MC.
- PT (φ) is the expected power consumption of the network with φ switching policy.
- N∑ n=1 τSC,nΓn, (5) where τMC and τSC,n are the original traffic demands (i.e., before offloading) of MC and n-th SC, respectively, and N is the total number of SCs in the network.
- The constraint in (4) is to ensure that there must be sufficient capacity in the MC to accommodate both the original traffic demand of the MC, τMC, and the total traffic demand of all the SCs that are switched OFF in order to maintain the QoS.
III. OTOCELL FRAMEWORK
- Most of the cell switching solutions developed using heuristic approaches, such as exhaustive search (ES) or genetic algorithm, are not suitable for real-time implementation, particularly in networks with large dimensions because they are usually computationally demanding.
- The ES algorithm uses the optimization function in (4) to decide the optimal set of SCs to switch ON/OFF per time while the Input/Output Mapper prepares the training data set—which includes the traffic loads, and optimal switching combinations.
- The activation function for the HL neurons is ReLU while that of the output neurons is softmax (since the cell switching problem is a multi-classification problem).
- The training process involves adjusting the ANN parameters, using gradient-descent algorithms, such that the difference between the expected output (i.e., predicted output) and the actual output is as close to zero as possible.
A. Simulation Scenario and data-set generation
- Two simulation scenarios, Scenario-A and Scenario-B, with different number of SCs are considered to test the performance of the proposed model on varying network sizes.
- The traffic load of both MC and SCs are generated using uniform random distribution model, such that τMC ∈ [0,mMC] and τSC ∈ [0,mSC] where mMC,mSC are the maximum normalized loads of the MC and SCs, respectively.
- In Scenario-A, BS switching pattern were generated for 7 days with one-minute resolution using ES amounting to about 10,000 observations, while Scenario-B was for 35 days2 resulting in about 50,000 observations.
- For the remaining simulation parameters, the authors adopted values in [11].
- 2More data set is generated in Scenario-B because the increase in network dimension and complexity makes the training process more difficult.
B. ANN Training and Testing
- For Scenario-A, two data sets—each comprising about 10,000 traffic load samples of the BSs and their corresponding optimal switching patterns—were used for training and testing the proposed model.
- For Scenario-B, one data set comprising about 50,000 traffic load samples and their corresponding optimal switching patterns was utilized, out of which 80% was used for training and 20% for testing.
- The training of the model in both scenarios is carried out using the Adam optimization algorithm [12].
- Table I summarizes the parameters of both models.
- Upon successful training of both models in each scenario, the trained models are then applied to the test data set in order to evaluate the performance of the trained models.
C. Results and discussion
- Compared to the All-ON, it can be observed that the OTOcell shows a reduction in power consumption, however, the authors notice that due to the few number of SCs, the reduction in power consumption is not significant most of the time as the SCs have fewer opportunities to sleep.
- This can be traced to the fact that the network dimensions and complexity is increased in Scenario-B compared to Scenario-A, and as a result the OTOcell is prone to more prediction errors.
- The QoS evaluation of the proposed framework is also carried out using the throughput metric to ascertain the impact of the OTOcell framework on QoS of the network.
- The throughput per time slot is the total network throughput for a given time slot, i.e., every hour and TP avg.
V. CONCLUSION
- A UDN with four types of SCs and two deployment scenarios is considered.
- A cell switching mechanism based on ANN is proposed to determine the optimal cell switching pattern per time instance based on the traffic loads of both the MC and SCs.
- The simulation results reveals that a significant amount of power savings can be achieved with the proposed model.
- In addition, the performance of the proposed OTOcell framework is very close to the optimal ES-based solution in terms of power consumption minimization with very minimal effect on the QoS.
Did you find this useful? Give us your feedback
Citations
4 citations
References
111,197 citations
"Load-Aware Cell Switching in Ultra-..." refers methods in this paper
...The training of the model in both scenarios is carried out using the Adam optimization algorithm [12]....
[...]
1,462 citations
195 citations
169 citations
120 citations
"Load-Aware Cell Switching in Ultra-..." refers background in this paper
...One of such machine learning algorithms is the artificial neural networks (ANN), which are known as universal approximators because they are able to find the relationships between complex non-linear functions and are also known for their excellent generalization ability [8], hence they have found numerous applications in the field of wireless communications [7]....
[...]
...In addition, machine learning models can be trained offline and then plugged into the network in order to enhance realtime decision making by reducing the network delays [7]....
[...]
Related Papers (5)
Frequently Asked Questions (17)
Q2. How many observations were generated in Scenario-A?
In Scenario-A, BS switching pattern were generated for 7 days with one-minute resolution using ES amounting to about 10,000 observations, while Scenario-B was for 35 days2 resulting in about 50,000 observations.
Q3. How many data sets were used for training and testing?
For Scenario-B, one data set comprising about 50,000 traffic load samples and their corresponding optimal switching patterns was utilized, out of which 80% was used for training and 20% for testing.
Q4. What is the rationale for using the proposed framework?
The justification for using the proposed framework is twofold: 1) once the ANN model is fully trained, the optimal cell switching pattern can be obtained in real-time, that is, whenever the network status changes, without resorting to computing the optimization objective afresh; 2) both training data set generation and the ANN training stage, which are the computationally intensive processes, can be done offline, thus enabling the trained model to be implemented for real-time cell switching without additional computational overhead and delays to the network.
Q5. What is the traffic load of the MC and all the SCs associated with it?
The traffic loads are then passed to the Training Data Set Generator which consists of the ES algorithm, and Input/Output Mapper.
Q6. What is the purpose of this paper?
Future work will consider using more realistic traffic model, carry out complexity, and error probability analysis on the proposed model in order to further ascertain its suitability for UDNs.
Q7. How is the performance of the proposed OTOcell framework?
In addition, the performance of the proposed OTOcell framework is very close to the optimal ES-based solution in terms of power consumption minimization withvery minimal effect on the QoS.
Q8. How many neurons are in the input layer?
The number of neurons in the input layer is determined by the input features of the training data set (number of SCs and MC), the number of neurons in the HL are selected empirically by trying different combinations, and the OL neurons is given by 2N , where N is the number of SCs.
Q9. What is the way to determine the optimal cell switching pattern?
A cell switching mechanism based on ANN is proposed to determine the optimal cell switching pattern per time instance based on the traffic loads of both the MC and SCs.
Q10. What is the power consumption of a BS?
2The power consumption model of a BS proposed in [11] is adopted and is expressed as:PBS = { Pc + σyPtx, if 0 < Ptx < Pm Ps, if Ptx = 0,(1)where PBS represents the BS total power consumption, σy denotes the slope of the load dependent components, Pc is the constant power consumption component of the BS, and Ps is the sleep mode power consumption.
Q11. What is the traffic load of the MC and SCs?
The traffic load of both MC and SCs are generated using uniform random distribution model, such that τMC ∈ [0,mMC] and τSC ∈ [0,mSC] where mMC,mSC are the maximum normalized loads of the MC and SCs, respectively.
Q12. What is the QoS evaluation of the proposed OTOcell framework?
The QoS evaluation of the proposed framework is also carried out using the throughput metric to ascertain the impact of the OTOcell framework on QoS of the network.
Q13. What is the procedure for training the OTOcell?
Upon successful training of both models in each scenario, the trained models are then applied to the test data set in order to evaluate the performance of the trained models.
Q14. What can be traced to the wrong predictions from the proposed framework?
This can be traced to inappropriate switch ON/OFF decisions due to wrong predictions from the proposed framework occasioned by the increase in network dimension and complexity which makes it more difficult to accurately train the ANN model.
Q15. Why is the training process more difficult in Scenario-B?
2More data set is generated in Scenario-B because the increase in networkdimension and complexity makes the training process more difficult.
Q16. What is the traffic demand of the MC and the total number of SCs?
As a result, before these algorithms decide which set of SCs to switch ON/OFF and execute the decision, the network state would have changed, thereby leading to sub-optimal switching decision and delays.
Q17. What is the definition of the network throughput?
the network throughput is considered to be the traffic demand that is supported by all the active BSs in a given time interval.