Accurate Base Station Placement in 4G LTE Networks Using Multiobjective Genetic Algorithm Optimization

Isabona, Joseph; Imoize, Agbotiname Lucky; Ojo, Stephen; Venkatareddy, Prashanth; Hinga, Simon Karanja; Sánchez-Chero, Manuel; Ancca, Sheda Méndez

doi:https://doi.org/10.1155/2023/7476736

Wireless Communications and Mobile Computing

On this page

Abstract Introduction Preliminaries Results and Discussion Conclusion Data Availability Conflicts of Interest Acknowledgments References Copyright Related Articles

Special Issue

Machine Learning Enabled Signal Processing Techniques for Large Scale 5G and 5G Networks

View this Special Issue

Research Article | Open Access

Volume 2023 | Article ID 7476736 | https://doi.org/10.1155/2023/7476736

Accurate Base Station Placement in 4G LTE Networks Using Multiobjective Genetic Algorithm Optimization

Joseph Isabona,¹Agbotiname Lucky Imoize,^2,3Stephen Ojo,⁴Prashanth Venkatareddy,⁵Simon Karanja Hinga,⁶Manuel Sánchez-Chero,⁷and Sheda Méndez Ancca⁸

Academic Editor: Mohammad Farukh Hashmi

Received20 Jul 2022

Revised07 Sept 2022

Accepted23 Jan 2023

Published11 Feb 2023

Abstract

Cellular mobile communication network planning and optimization involve a complex engineering process that deals with network fundamentals, radio resource elements, and critical decision variables. The continuous evolution of radio access technologies provides new challenges that necessitate efficient radio planning and optimization. Therefore, the planning and optimization algorithms should be highly efficient, advanced, and robust. An important component of 4G LTE network planning is the proper placement of evolved node base stations (eNodeBs) and the configuration of their antenna elements. This contribution proposes a multiobjective genetic algorithm that integrates network coverage, capacity, and power consumption for optimal eNodeB placement in an operational 4G LTE network. The multi-objective-based genetic algorithm optimization has been achieved using the optimization toolbox in MATLAB. By leveraging the proposed method, the effect of different population sizes on the cost of placing the eNodeBs and the percentage coverage of the eNodeBs in a given cell is determined. As a result, the optimal selection technique that minimizes the total network cost without compromising the desired coverage and capacity benchmarks is achieved. The proposed automatic eNodeB antenna placement method can be explored to optimize 4G LTE cellular network planning in related wireless propagation environments.

1. Introduction

The evolved node base station (eNodeB) placement and configuration in cellular radio networks is critical to delivering efficient wireless network services and guaranteeing the quality of service for mobile subscribers [1–3]. The performance of a cellular network is mainly characterized by the received signal strength and signal quality at the subscriber equipment terminal. In practice, the service coverage is primarily affected by radio propagation and transmit power and depends on the propagation environment of the wireless network [4–9]. Thus, attaining excellent cellular network coverage and improved signal coverage around the subscribers by deploying the minimum required number of BSs with configurations is one of the leading objectives of the mobile networking industry [10–13]. This objective can only be achieved if a good evolved node base station (eNodeB) placement and configuration method considers the propagation environment in place [14–16].

The traditional method of eNodeB placement and configurations depends mainly on the imported propagation models such as the Hata and COST 231 Hata that do not capture the actual characteristics of the radio signal propagation environment [17–20]. The limitations posed by these models used to characterize the environment often lead to unreliable network planning, resulting in poor quality of service at the subscribers’ equipment terminals. To this end, this study focuses on investigating and developing a robust eNodeB placement and configuration algorithm that considers the investigated radio signal propagation environment.

The genetic algorithm (GA) is preferred to other heuristic optimization algorithms and deterministic approaches owing to its capability to handle continuous and discrete parameters, insensibility to local minima, model generality, and robustness of the GA program code [21–24]. These characteristics presents the genetic algorithm (GA) as the natural choice for optimization in this investigation. In particular, the optimization problem is quantitatively described as a maximization or minimization of the function , where indicates the number of parameters. The minimization and maximization can be replaced by each other if the function is multiplied by a minus sign.

The cellular network infrastructure comprises several eNodeBs deployed over the service coverage area. Each eNodeB creates or produces a coverage area referred to as a cell [25, 26]. The users geographically located inside the cell are provided with the different network services by the associated eNodeB. The optimal placement of the eNodeB to varying locations over the tested geographical area to meet the desired service coverage quality and satisfy the diverse subscribers’ multifarious demands poses a challenge due to several dynamic factors and steps involved, leading to an eNodeB placement problem worthy of investigation. The eNodeB placement problems deal with determining the type of eNodeB antennas, the number of eNodeBs, the configuration of the eNodeB antennas (tilt, sectors, and azimuth), and the positioning of the eNodeBs on potential cell sites to meet the coverage, capacity, and service quality demands [12, 27–31].

There exist several methods of handling automatic base station placement problems. In the existing literature, Císcar and Pino [32] presented a solution-based technique that employs a heuristic search algorithm that combines ray tracing and direct ray methods to determine the received signal power level at a given location. In the works of [33–37], pattern search algorithms were explored to determine the antenna location placement considering bit error rate and power coverage constraints. In the pattern search algorithm, the coverage area is separated into different receiver location grids, followed by an iterative search initiated until some enhanced and workable solutions are attained. In [10], a robust method similar to the current study is proposed. Base stations are automatically determined and distributed over an area to meet the coverage constraint and traffic capacity demands.

In [38], a nonlinear programming problem with constrained multivariables is formulated to determine the location of nodes and their data transmission patterns. The constraints were targeted at minimizing the total cost and maximizing the network lifetime. Furthermore, the authors assumed that all nodes possess the same energy, making them suitable for only first-round wireless network deployment. A related study [39] proposed a multiobjective metric method to handle base station placement in WSNs. The metrics are coverage, fault tolerance, energy consumption, and average delay. Their results showed optimal base station performance.

From the preceding literature, it is apparent that there is a need to investigate the coverage, capacity, and power consumption of eNodeBs as a combined multiobjective problem employing a genetic algorithm. Thus, this paper proposes a multiobjective genetic algorithm that integrates coverage, capacity, and power consumption for optimal eNodeB placement in a typical 4G LTE network. The main contributions of this paper are outlined as follows: (i)A multiobjective optimization method is proposed for evaluating the combined coverage, capacity, and power consumption problem for optimal eNodeB placement in a typical 4G LTE network(ii)The effect of different population sizes on the cost of placing the eNodeBs and the percentage coverage of the eNodeBs in a given cell is investigated(iii)The optimal selection technique minimizes the total network cost without compromising the desired coverage and capacity benchmarks determined

The remaining part of this paper is given as follows: Section 2 presents the preliminaries. Section 3 captures the experimental measurements, and Section 4 presents the results and discussions. Finally, Section 5 gives a brief conclusion to the paper.

2. Preliminaries

This section presents the design of the base station placement model, maximization of service coverage areas, maximization of the covered user capacity, minimization of cost of power consumption, and model formulation.

2.1. Base Station Placement Model

The core aim is to find a BS placement procedure that maximizes the coverage and user capacity, whose power radiation is equal to or below maximum transmit power, . In order to provide a mathematical depiction of this model, it is essential to introduce a set of variables. Mainly each is linked to a binary variable with the following meaning: is equal to 1 if an eNB is selected and placed in the intended location equal to 0, or otherwise. Figure 1 shows the setup created for the eNodeB placement and evaluation method with the randomly distributed user traffic. The design is as follows: the total area of interest and the BS transceiver is km², and the eNodeB can be placed at any location in this area. Eleven base stations with three sectored directional antennas are intended to be distributed randomly in the investigated area. All base stations are assumed to possess the same transmission power (20 W) and are of the same height (30 m).

2.2. Maximization of Service Coverage Areas

The first objective is to minimize the network dead zones/coverage hole areas. Dead zones/coverage holes are the areas of interest close to the cell edges where the network services are very poor or unavailable. This first objective is geared toward maximizing the network coverage area. Thus, this fitness function , in equation (1), has been formally evaluated by [40, 41]. where the coverage rate expresses the coverage percentage value of the measurement test points.

2.3. Maximization of the Covered User Capacity

The second objective is targeted at minimizing the uncovered user capacity. In other words, the objective is directed at maximizing the system capacity in the network area of interest [42, 43]. This objective can be expressed by

2.4. Minimization of Cost of Power Consumption

Cellular network planners are always interested in reducing users’ exposure to electromagnetic radiation emanating from the BSs and the cost of energy consumption to maximize revenue. Thus, the key objective is to minimize network energy consumption and reduce users’ exposure to electromagnetic radiation emanating from the eNodeBs [44]. This objective can be formulated as follows: where indicate the BS transmit power, is the number of eNodeBs, and is the maximum BS transmit power given in equation (4), and it can be determined by [24].

2.5. Model Formulation

The optimal placement of no more than some BSs attains a suitable trade-off among

Subject to the constraints given, where indicates the channel capacity for user , considering a channel . indicates the maximum BS transmit power. A receiver is said to be properly covered by a base station if the RSRP is greater than the threshold, which is given by

A binary decision vector , satisfying equations (8)–(11), is termed a feasible solution.

3. Proposed Multiobjective Optimization Method

There exist several GA stochastic optimization methods. This work engages the nondominated sorting genetic algorithm-II (NSGA-II) optimization method. The NSGA-II is a fast elitist multiobjective optimization algorithm [45, 46] resolving problems by converging to a Pareto front. The NSGA-II is utilized to select the optimal BS locations from a subset of the predefined candidate sites and guide an evolutionary procedure toward attaining feasible solutions with better service coverage, desired user capacity, and lower cost function. At the same time, it retains a population of the best-fit solutions. The adopted NSGA-II pseudocode is given in Algorithm 1. The key GA parameters include the following: (a)Population size: this expresses the number of individuals (chromosomes) that are available in a population for each generation(b)Crossover fraction: this defines the population fraction at the succeeding (next) generation(c)Selection function: a key evolutionary process operator that assists individuals to undergo better variation and produce offspring in the succeeding generation employing their fitness scores(d)Pareto function: this regulates the elite population members at each generation to keep up the population diversity before converging to the optimal Pareto front(e)Generation: iteratively, the control of the number of chromosome evaluations during the optimization process (run)

Input: eNodeB placement model parameters
Input: GA control operators
Input: I (population size)
Output: O (Pareto front approximation)
Steps
i: Define fitness functions
ii: Create an initial random population,
iii: Compute fitness values of each chromosome in
iv: Rank the individuals in the population using a fast nondominated sort
v: Compute the crowding distance of each solution
vi: While the maximum iteration number is not reached yet, do
vii: Choose parents from through binary tournament selection with crowding distance
viii: Employ the GA operators (crossover and mutation) to create a set of new solutions,
ix: Evaluate fitness values of solutions in
x: Merge I ← [I, ]
xi: Rank each solution in using a fast nondominated sort
xii: Compute the crowding distance meant for each solution in
xiii: Change solutions in with the best solution in
xiv: End while

3.1. Representation and Encoding

In the proposed multiobjective GA, chromosomes represent the solution that designates the locations (positions) of the potential BS sites. A location is modeled as an coordinate point. Each chromosome is encoded in the GA algorithm using binary values (i.e., tilt strings of 1 s and 0 s), with one at each bit for a potential BS location; otherwise, it is 0. Thus, the coordinates represent the location of each BS in the optimization area such that is called the gene and are termed the chromosomes, where indicates the number of BSs. Table 1 gives the simulation parameters used in the proposed multiobjective genetic algorithm.

4. Results and Discussion

The GA simulations are performed using a PC/Intel Core i5-500 CPU at 2.5.00 GHz, 3 GB Memory (RAM), and Window 7 with 64-bit operating system in MATLAB 2018a environment. The GA embroils searching and tuning (optimizing) several key parameters to attain its desired optimal performance. The key parameters considered include population size, mutation, and crossover organizations. In order to obtain good results, several simulated tests were performed to ascertain the proper population size within the range of 10 to 100 individuals. In the simulation, two scenarios were considered. Scenario 1 considers optimal eNodeB placement with coverage and cost optimization, and scenario 2 considers optimal eNodeB placement with coverage plus user capacity and cost optimization. The key GA simulation parameters are provided in Table 1.

The first scenario considers optimal eNodeB placement with coverage and cost optimization. Here, the effect of different population sizes (10, 40, 70, and 100) on the cost of placing the eNodeBs (fun 2) and the percentage coverage of the eNodeBs (fun 1) are presented in Figures 2–5. Each figure’s upper and lower parts indicate the optimal Pareto front and the minimum/maximum scores achieved after the simulation. An inspection of the statistics reveals that the cost objective function (fun 2) reduces as the population sizes grow larger until 70. Then, a further increase in the population to 100 produced a reduced population size. Thus, the maximum population size of 70 is simulated using the GA simulation parameters in Table 1. The results in Table 2 show the respective optimal coverage plus capacity and cost performance over ten simulation runs. This result implies that a population size of 70 individuals produced the best coverage performances of 88.59 and 98.10%, but at the cost of 9.92 and 36.90, respectively.

The second scenario considers optimal eNodeB placement with coverage plus user capacity and cost optimization. Here, the effect of different population sizes (10, 40, 70, and 100) on the cost of placing the eNodeBs (fun 2) and the percentage coverage of the eNodeBs (fun 1) are presented in Figures 6–9. The upper and lower parts of each figure indicate the optimal Pareto front attained and the minimum/maximum scores achieved after the simulation. An inspection of the figures reveals that the cost objective function (fun 2) reduces as the population sizes grow larger until 70. Further, an increase in population size to 100 produced a better solution by using the 70 population size with other GA parameters (Table 1). The results in Table 2 show the respective optimal coverage plus capacity and cost performance over 10 simulation runs. Again, the results imply that with a population size of 70 individuals, the best coverage plus capacity performances of 81.42 and 96.07% were produced at the cost of 26.80 and 35.26, respectively. Lastly, the coverage plus capacity versus cost performance statistics is presented in Table 3.

5. Conclusion

This study has presented a multiobjective genetic algorithm that integrates network coverage, capacity, and power consumption for optimal eNodeB placement in a simulated 4G LTE network. Optimal minimization of the cost of planning cellular networks generally calls for the most favorable selection and positioning of the eNodeB transmitter stations to meet the required coverage and capacity quality under certain constraints. Capacity and coverage planning are interconnected in contextual broadband wireless networks like 4G LTE. However, the ever-growing nonuniform user capacity demands coupled with mixed cellular network settings make the selection and location of eNodeB transmitter stations a nontrivial task. In order to address this problem, this paper proposes a multiobjective genetic algorithm-based methodology that performs optimal selection and location of base stations robustly. The optimal selection process minimizes the total network cost without compromising the desired coverage and capacity benchmarks. The proposed method performed favorably and can be explored to optimize a cellular network planning process in a related wireless environment.

Data Availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Conflicts of Interest

The authors declare that they have no conflicts of interest.

Acknowledgments

The work of Agbotiname Lucky Imoize was supported in part by the Nigerian Petroleum Technology Development Fund (PTDF) and in part by the German Academic Exchange Service (DAAD) through the Nigerian-German Postgraduate Program under Grant 57473408.

References

U. D. Maiwada, K. U. Danyaro, and A. B. Sarlan, “An improved mobility state detection mechanism for femtocells in LTE networks,” in International Conference on Decision Aid Sciences and Applications (DASA), pp. 486–492, Chiangrai, Thailand, 2022.
View at: Google Scholar
D. Amzallag, M. Livschitz, J. Naor, and D. Raz, “Cell planning of 4G cellular networks: algorithmic techniques and results,” in 2005 6th IEE International Conference on 3G and Beyond, pp. 1–5, London, UK, 2005.
View at: Google Scholar
J. Košmerl and A. Vilhar, “Base stations placement optimization in wireless networks for emergency communications,” in 2014 Ieee International Conference On Communications Workshops (Icc), pp. 200–205, Sydney, NSW, Australia, 2014.
View at: Google Scholar
V. C. Ebhota, J. Isabona, and V. M. Srivastava, “Base line knowledge on propagation modelling and prediction techniques in wireless communication networks,” Journal of Engineering and Applied Science, vol. 13, no. 7, pp. 1919–1934, 2018.
View at: Google Scholar
J. Isabona and C. C. Konyeha, “Site-specific assessment of node B using key service quality indicators over 3G/UMTS networks from outdoor drive-test measurements,” Journal of Information Engineering and Applications, vol. 3, no. 9, pp. 48–56, 2013.
View at: Google Scholar
M. E. Ekpenyong, S. Robinson, and J. Isabona, “Macrocellular propagation prediction for wireless communications in urban environments,” Journal of Computer Science and Technology, vol. 10, 2010.
View at: Google Scholar
A. L. Imoize, S. O. Tofade, G. U. Ughegbe, F. I. Anyasi, and J. Isabona, “Updating analysis of key performance indicators of 4G LTE network with the prediction of missing values of critical network parameters based on experimental data from a dense urban environment,” Data in Brief, vol. 42, article 108240, 2022.
View at: Publisher Site | Google Scholar
C. Wechtaisong, P. Chamnanka, and C. Prommak, “Efficient placement of femtocell base stations for 4G-LTE networks in multi-floor buildings,” in Proceedings of the 3rd International Conference on Communication and Information Processing, pp. 320–325, New York, NY, USA, 2017.
View at: Google Scholar
M. Ekpenyong, J. Isabona, and E. Ekong, “Computational modeling of transmission capacity with outage constraints in ad-hoc networks,” Computer Science and Telecommunications, vol. 3, no. 3, 2010.
View at: Publisher Site | Google Scholar
I. Törős and P. Fazekas, “An algorithm for automatic base station placement in cellular network deployment,” in Lecture Notes in Computer Science, pp. 21–30, Springer, 2010.
View at: Google Scholar
J. Isabona, “Joint statistical and machine learning approach for practical data-driven assessment of user throughput quality in microcellular radio networks,” Wireless Personal Communications, vol. 119, no. 2, pp. 1661–1680, 2021.
View at: Google Scholar
J. Isabona, A. L. Imoize, S. Ojo et al., “Development of a multilayer perceptron neural network for optimal predictive modeling in urban microcellular radio environments,” Applied Sciences, vol. 12, no. 11, p. 5713, 2022.
View at: Publisher Site | Google Scholar
J. Isabona and V. M. Srivastava, “Coverage and link quality trends in suburban mobile broadband HSPA network environments,” Wireless Personal Communications, vol. 95, no. 4, pp. 3955–3968, 2017.
View at: Publisher Site | Google Scholar
X. Liang, H. Liu, and Q. Wang, “4G heterogeneous networks base station planning using evolutionary multi-objective algorithm,” in 2015 11th International Conference on Computational Intelligence and Security (CIS), pp. 248–252, Shenzhen, China, 2015.
View at: Google Scholar
M. Nivedita and G. Raja, “Efficient relay station placement strategy for broadband wireless networks-4G,” in 2012 International Conference on Recent Trends in Information Technology, pp. 282–286, Chennai, India, 2012.
View at: Google Scholar
C. O. Alenoghena and J. O. Emagbetere, “Base station placement challenges in cellular networks: The Nigerian experience,” in 2012 IEEE 4th International Conference on Adaptive Science & Technology (ICAST), pp. 7–11, Kumasi, Ghana, 2012.
View at: Google Scholar
S. O. Ajose and A. L. Imoize, “Propagation measurements and modelling at 1800 MHz in Lagos Nigeria,” International Journal of Wireless and Mobile Computing, vol. 6, no. 2, pp. 165–174, 2013.
View at: Publisher Site | Google Scholar
A. L. Imoize and A. I. Dosunmu, “Path loss characterization of long term evolution network for,” Jordan Journal of Electrical Engineering, vol. 4, no. 2, pp. 114–128, 2018.
View at: Google Scholar
A. L. Imoize and A. I. Oseni, “Investigation and pathloss modeling of fourth generation long term evolution network along major highways in Lagos Nigeria,” IFE Journal of Science, vol. 21, no. 1, pp. 39–60, 2019.
View at: Publisher Site | Google Scholar
Y. Wang, J. Han, Z. Liu, Y. Wang, and X. Feng, “Impact of 5G base station participating in grid interaction,” in 2022 7th Asia Conference on Power and Electrical Engineering (ACPEE), pp. 586–590, Hangzhou, China, 2022.
View at: Google Scholar
W. Deng, X. Zhang, Y. Zhou et al., “An enhanced fast non-dominated solution sorting genetic algorithm for multi- objective problems,” Information Sciences, vol. 585, pp. 441–453, 2022.
View at: Publisher Site | Google Scholar
S. Mirjalili and S. Mirjalili, “Genetic algorithm,” in Studies in Computational Intelligence, S. Mirjalili, Ed., vol. 780, pp. 43–55, Springer International Publishing, Cham, 2019.
View at: Publisher Site | Google Scholar
S. Katoch, S. S. Chauhan, and V. Kumar, “A review on genetic algorithm: past, present, and future,” Multimedia Tools and Applications, vol. 80, no. 5, pp. 8091–8126, 2021.
View at: Publisher Site | Google Scholar
I. K. Valavanis, G. E. Athanasiadou, D. Zarbouti, and G. V. Tsoulos, “Base-station location optimization for lte systems with genetic algorithms,” in 20th European Wireless Conference, pp. 1–6, Barcelona, Spain, 2014.
View at: Google Scholar
A. L. Imoize and O. D. Adegbite, “Measurements-based performance analysis of a 4G LTE network in and around shopping malls and campus environments in Lagos Nigeria,” Arid Zone Journal of Engineering, Technology and Environment, vol. 14, no. 2, pp. 208–225, 2018.
View at: Google Scholar
A. L. Imoize, A. E. Ibhaze, P. O. Nwosu, and S. O. Ajose, “Investigation and pathloss modeling of fourth generation long term evolution network along major highways in Lagos Nigeria,” Ife Journal of Science, vol. 21, no. 1, pp. 13–21, 2019.
View at: Publisher Site | Google Scholar
L. Raisanen and R. Whitaker, “Multi-Objective Optimization in the Area Coverage Problems for Cellular Communication Networks: Evaluation of an Elitist Evolutionary Strategy,” in In Proceedings of the 2003 ACM symposium on applied computing, pp. 714–720, March 2003.
View at: Publisher Site | Google Scholar
S. Ben Jemaa, Z. Altman, J. M. Picard, and B. Fourestie, “Combined Coverage and Capacity Optimisation for UMTS Networks,” in 11th International Telecommunications Network Strategy and Planning Symposium, Vienna, Austria, 2004.
View at: Google Scholar
S. Ojo, A. Imoize, and D. Alienyi, “Radial basis function neural network path loss prediction model for LTE networks in multitransmitter signal propagation environments,” International Journal of Communication Systems, vol. 34, no. 3, pp. 1–26, 2021.
View at: Publisher Site | Google Scholar
J. Isabona and A. L. Imoize, “Terrain-based adaption of propagation model loss parameters using non-linear square regression,” Journal of Engineering and Applied Science, vol. 68, no. 1, pp. 1–19, 2021.
View at: Google Scholar
J. Isabona, R. Kehinde, A. L. Imoize, S. Ojo, and N. Faruk, “Large-scale signal attenuation and shadow fading measurement and modelling for efficient wireless network design and management,” in 2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON), pp. 1–5, Lagos, Nigeria, 2022.
View at: Publisher Site | Google Scholar
F. J. B. Císcar and M. M. Pino, “A method for the automatic selection of the radiated power and location of radio transmitters in indoor environments,” in 14th IEEE Proceedings on Personal, Indoor and Mobile Radio Communications, vol. 3, pp. 2307–2311, Beijing, China, 2003.
View at: Google Scholar
J. He, A. A. Verstak, L. T. Watson et al., “Globally optimal transmitter placement for indoor wireless communication systems,” IEEE Transactions on Wireless Communications, vol. 3, no. 6, pp. 1906–1911, 2004.
View at: Publisher Site | Google Scholar
H. D. Sherali, C. M. Pendyala, and T. S. Rappaport, “Optimal location of transmitters for micro-cellular radio communication system design,” IEEE Journal on Selected Areas in Communications, vol. 14, no. 4, pp. 662–673, 1996.
View at: Publisher Site | Google Scholar
M. H. Wright, “Optimization methods for base station placement in wireless applications,” in VTC’98. 48th IEEE Vehicular Technology Conference. Pathway to Global Wireless Revolution (Cat. No. 98CH36151), vol. 1, pp. 387–391, Ottawa, ON, Canada, 1998.
View at: Google Scholar
D. Stamatelos and A. Ephremides, “Spectral efficiency and optimal base placement for indoor wireless networks,” IEEE Journal on Selected Areas in Communications, vol. 14, no. 4, pp. 651–661, 1996.
View at: Publisher Site | Google Scholar
Y. Xu, M. Zhou, and L. Ma, “Optimization of WLAN indoor location network based on signal coverage requirement,” in 2010 First International Conference on Pervasive Computing, Signal Processing and Applications, pp. 162–166, Harbin, China, 2010.
View at: Google Scholar
P. Cheng, C.-N. Chuah, and X. Liu, “Energy-aware node placement in wireless sensor networks,” in IEEE Global Telecommunications Conference, GLOBECOM’04., vol. 5, pp. 3210–3214, Dallas, TX, 2004.
View at: Google Scholar
S. Kim, J.-G. Ko, J. Yoon, and H. Lee, “Multiple-objective metric for placing multiple base stations in wireless sensor networks,” in 2007 2nd International Symposium on Wireless Pervasive Computing, San Juan, PR, USA, 2007.
View at: Google Scholar
A. J. Nebro, J. J. Durillo, C. A. Coello Coello, F. Luna, and E. Alba, “A study of convergence speed in multi-objective metaheuristics,” in Parallel Problem Solving from Nature -- PPSN X, pp. 763–772, Springer, 2008.
View at: Google Scholar
A. Nebro, E. Alba, G. Molina, F. Chicano, F. Luna, and J. Durillo, “Optimal antenna placement using a new multi-objective chc algorithm,” in Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference, pp. 876–883, New York, NY, USA, 2007.
View at: Publisher Site | Google Scholar
S. Dahmani, M. Gabli, and A. Serghini, “A green fuzzy multi-objective approach to the RNP problem for LTE networks,” Progress in Artificial Intelligence, vol. 11, no. 1, pp. 29–41, 2022.
View at: Publisher Site | Google Scholar
M. Ying, J. Zhang, and Y. Qin, “Simulation and analysis of fractional frequency reuse power allocation for a 24-cell network,” in International Conference on Signal Processing and Communication Technology (SPCT 2021), vol. 12178, pp. 590–604, Tianjin, China, 2022.
View at: Google Scholar
M. S. Sadoon and S. A. Ayoob, “Modeling and evaluating performance for Long-Term Evaluation networks in a part of Mosul city,” in 2021 4th International Conference on Information and Communications Technology (ICOIACT), pp. 149–153, Yogyakarta, Indonesia, 2021.
View at: Publisher Site | Google Scholar
K. Deb, S. Agrawal, A. Pratap, and T. Meyarivan, “A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II,” in Parallel Problem Solving from Nature PPSN VI, pp. 849–858, Springer, Berlin, Heidelberg, 2000.
View at: Google Scholar
K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: NSGA-II,” IEEE Transactions on Evolutionary Computation, vol. 6, no. 2, pp. 182–197, 2002.
View at: Publisher Site | Google Scholar

Copyright

Copyright © 2023 Joseph Isabona et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PDF Download Citation

Download other formats

Order printed copies