In this paper, a survey of the literature of the past 15 years involving machine learning (ML) algorithms applied to self-organizing cellular networks is performed. In order for future networks to overcome the current limitations and address the issues of current cellular systems, it is clear that more intelligence needs to be deployed so that a fully autonomous and flexible network can be enabled. This paper focuses on the learning perspective of self-organizing networks (SON) solutions and provides, not only an overview of the most common ML techniques encountered in cellular networks but also manages to classify each paper in terms of its learning solution, while also giving some examples. The authors also classify each paper in terms of its self-organizing use-case and discuss how each proposed solution performed. In addition, a comparison between the most commonly found ML algorithms in terms of certain SON metrics is performed and general guidelines on when to choose each ML algorithm for each SON function are proposed. Lastly, this paper also provides future research directions and new paradigms that the use of more robust and intelligent algorithms, together with data gathered by operators, can bring to the cellular networks domain and fully enable the concept of SON in the near future.

/pdf/a-survey-of-machine-learning-techniques-applied-to-self-5ggfpvrhwz.pdf

A Survey of Machine Learning Techniques Applied to Self-Organizing Cellular Networks

Plasmid-lipid particles which are useful for transfection of cells in vitro or in vivo are described. The particles can be formed using either detergent dialysis methods or methods which utilize organic solvents. The particles are typically 65-85 nm, fully encapsulate the plasmid and are serum-stable.

Methods for encapsulating plasmids in lipid bilayers

The spectrum congestion experienced in today's common cellular bands has led to research and measurements to explore the vast bandwidths available at millimeter waves (mmWaves). NYU WIRELESS conducted E-band propagation measurements for both mobile and backhaul scenarios in 2013 in the dense urban environment of New York City using a sliding correlator channel sounder, by transmitting a 400 Mega chip per second (Mcps) PN sequence with a power delay profile (PDP) multipath time resolution of 2.5 ns. Measurements were made for more than 30 transmitter-to-receiver location combinations for both mobile and backhaul scenarios with separation distances up to 200 m. This paper presents results that support the use of directional steerable antennas at mmWave bands in order to achieve comparable path loss models and channel statistics to today's current cellular systems and at 28 GHz. These early results reveal that the mmWave spectrum, specifically the E-band, could be used for future cellular communications by exploiting multipath in urban environments with the help of beam-steering and beam combining.

/pdf/73-ghz-millimeter-wave-propagation-measurements-for-outdoor-1ktk5v11dj.pdf

73 GHz millimeter wave propagation measurements for outdoor urban mobile and backhaul communications in New York City

A radio communication system includes a remote device radio, and a base station radio operable to communicate with the remote device radio at a first channel and at a second channel using non-simultaneous frequency diversity. The base station is operable to communicate with a device other than the remote device at the second channel while the remote device radio and the base station radio are communicating at the first channel. A radio using non-simultaneous frequency diversity includes an antenna, a radio frequency module coupled to the antenna such that the radio frequency module is operable to transmit or receive radio frequency signals at a first channel and signals at a second channel using the antenna, and a baseband module coupled to the radio frequency module. The baseband module operable to transmit or receive signals through the radio frequency module, such that signals transmitted or received by the radio employ non-simultaneous frequency diversity using the first channel and the second channel. Additional devices are operable to use the second channel while the radio is transmitting or receiving radio frequency signals at the first channel.

Multi-connection, non-simultaneous frequency diversity in radio communication systems

A method and apparatus for focused communication is disclosed. The method includes a base transmitter array in communication with at least one client device at the same frequency. The base transmitter array provides a focused data communication to the client device.

Method and apparatus for focused data communications

One of the primary aims of radio network planning is to configure the parameters of the base stations such that the deployment achieves the required quality of service. However, the adjustment of radio network parameters in a heterogeneous macro-only cellular network is a complex task, which involves a large number of configuration parameters with interactions among them. Existing commercial planning tools are based on local search methods, e.g., simulated annealing, that require problem-specific and heuristic definitions of the input parameters. The problem with local search methods is that their performance can significantly be degraded if the input parameters are misconfigured. To overcome these difficulties, an iterative optimization procedure based on Taguchi's method is proposed to find near-optimal settings. Taguchi's method was originally applied in manufacturing processes and has recently been used in several engineering fields. Unlike local search methods that heuristically discover the multidimensional parameter space of candidate solutions, Taguchi's method offers a scientifically disciplined methodology to explore the search space and select near-optimal values for the parameters. In this paper, the application of Taguchi's method in radio network optimization is illustrated by setting typical radio network parameters of the Long Term Evolution (LTE) system, i.e., the uplink power control parameters, antenna tilts, and azimuth orientations of trisectored macro base stations. Simulation results reveal that Taguchi's method is a promising approach for radio network optimization with respect to performance and computational complexity. It is shown that Taguchi's method has a comparable performance to simulated annealing in terms of power control and antenna azimuth optimizations; however, it performs better in terms of antenna tilt optimization. Moreover, it is presented that the performance of simulated annealing, as opposed to Taguchi's method, highly depends on the definition of the input parameters.

Optimizing the Radio Network Parameters of the Long Term Evolution System Using Taguchi's Method

Game theory provides an adequate methodology for analyzing topics in communication systems that include trade-offs such as the subject of load balancing. As a means of balancing the load in the network, users are handed over from highly loaded cells to lower loaded neighbors increasing the capacity usage and the Quality of Service (QoS). The algorithm that calculates the amount of the load that each cell should decide either to accept or to offload might differ if the base stations are from distinct vendors, which in-turn may have an impact on the performance of the network. In this paper, we study the load balancing problem using a game-theoretic approach where, in the worst case, each cell decides independently on the amount of load that maximizes its payoff in an uncoordinated way and investigate whether the resulting Nash equilibrium would exhaust the gains achieved. Moreover, we alter the behavior of the players using the linear pricing technique to have a more desirable equilibrium. The simulation results for the Long Term Evolution (LTE) network have shown that the Nash equilibrium point can still provide a remarkable increase in the capacity when compared to a system without load balancing and has a slight degradation in performance with respect to the equilibrium achieved by linear pricing.

A game-theoretic approach to load balancing in cellular radio networks

Mobility robustness is often understood as making the radio link Doppler-resistent. However, guaranteeing proper cell changes, e.g. handovers, is another, as important and at least as challenging aspect beyond Doppler and wide sense stationarity (WSS) assumption. This paper tries to describe the complex optimization problem with scientific methods, in order to catalyze future academic work in the interesting field of minimizing handover problems. Simulation results will be presented for intra-frequency mobility robustness optimization (MRO) distinguishing network-wide, cell-specific and cell-pair specific optimization.

Mobility robustness optimization beyond Doppler effect and WSS assumption

First, the deployment of the Long-Term Evolution (LTE) system will be concentrated on areas with high user traffic overlaying with the legacy second-generation (2G) or third-generation (3G) mobile system. Consequently, the limited LTE coverage will result in many inter-radio access technology (RAT) handovers from LTE to 3G systems and vice versa. Trouble-free operation of inter-RAT handovers requires the optimization of the handover parameters of each cell in both RATs. The current network planning and optimization methods provide a fixed network-wide setting for all the handover parameters of the cells. Cells that later show considerable mobility problems in operation mode are manually optimized with the aid of drive tests and expert knowledge. This manual optimization of the handover parameters requires permanent human intervention and increases the operational expenditure (OPEX) of the mobile operators. Moreover, the interoperability of several RATs increases further the parameter space of the handover parameters, which makes the manual optimization difficult and almost impracticable. To reduce OPEX and to achieve a better network performance, we propose in this paper a self-optimizing algorithm where each cell in a RAT updates its handover parameters in an autonomous and automated manner depending on its traffic and mobility conditions. The proposed algorithm uses a feedback controller to update the handover parameters as a means to providing a steady improvement in the network performance. In the context of control theory, the feedback controller consists of a proportional control block, which regulates the change in the magnitude of each handover parameter, and a gain scheduler, which modifies the parameters of the proportional control block depending on the mobility conditions in each cell. To benchmark the design of the proposed algorithm, we apply two general and nonself-optimization algorithms: Taguchi's method and simulated annealing to optimize the handover parameters. Simulation results show that the proposed self-optimizing algorithm reaches a stable optimized operation point with cell-specific handover parameter settings, which considerably reduce the number of mobility failure events in the network, compared with three fixed settings for the handover parameters. Moreover, it is presented that the proposed self-optimizing algorithm outperforms Taguchi's method and simulated annealing when applied to a mobility robustness optimization (MRO) problem.

A SON-Based Algorithm for the Optimization of Inter-RAT Handover Parameters

A method and a device for data processing in a wireless network including several base stations are provided, wherein a mobility information is conveyed between at least two base stations Furthermore, a communication system is suggested including at least one such device

Bernhard Wegmann

Papers

Optimizing the Radio Network Parameters of the Long Term Evolution System Using Taguchi's Method

A game-theoretic approach to load balancing in cellular radio networks

Mobility robustness optimization beyond Doppler effect and WSS assumption

A SON-Based Algorithm for the Optimization of Inter-RAT Handover Parameters

Method and device for data processing in a wireless network