RAIK: Regional analysis with geodata and crowdsourcing to infer key performance indicators

Enami, Rita; Rajan, Dinesh; Camp, Joseph

doi:10.1109/wcnc.2018.8377405

Cited by 17 publications

(20 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors in [40] extend the work in [39] to include a more realistic coverage hole definition, where the coverage of neighboring pixels is also taken into account. A framework to establish a relationship between geographical data and user data using crowdsourced measurements in three region types: downtown, single-family residential, and multi-family residential is proposed in [41]. A neural network is trained to predict the key performance indicators in terms of RSRP and path loss estimation.…”

Section: ) Data Sparsity and Quantizationmentioning

confidence: 99%

“…The impact of choosing different sizes of subregions (called tile size) is evaluated for three different sizes: 100-m, 200-m and 300-m square. Authors in [41] observed that too large or too small tile sizes hinders the ability of the model to capture the correlation between geographical characteristic changes and the resulting channel propagation. Since the 200-m square tile size showed the best performance for dataset used, this size is used for the remainder of the paper to study other issues related to key performance indicator prediction.…”

Section: ) Data Sparsity and Quantizationmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced MDT-Based Performance Estimation for AI Driven Optimization in Future Cellular Networks

2020

View full text Add to dashboard Cite

Minimization of drive test (MDT) allows coverage estimation at a base station by leveraging measurement reports gathered at the user equipment (UE) without the need for drive tests. Therefore, MDT is a key enabling feature for data and artificial intelligence driven autonomous operation and optimization in future cellular networks. However, to date, the utility of MDT feature remains thwarted by issues such as sparsity of user reports and user positioning inaccuracy. We characterize three key types of errors in MDT-based coverage estimation that stem from inaccurate user positioning, scarcity of user reports and quantization. For the first time, the presented analysis shows existence of joint interplay between these errors on coverage estimation that result from inter-dependency between positioning error and bin width. The analysis also shows that there exists an optimal bin width for given user positioning inaccuracy and user density that minimizes the overall error in MDT-based estimated coverage. Utility of our framework is presented by addressing two applications from network optimization perspective: determining optimal bin width to maximize accuracy of MDT-based coverage estimation and its calibration to further improve its accuracy. INDEX TERMS Minimization of drive test, autonomous coverage estimation, optimal bin width, sparse data, coverage calibration, data driven optimization

show abstract

Section: ) Data Sparsity and Quantizationmentioning

confidence: 99%

Section: ) Data Sparsity and Quantizationmentioning

confidence: 99%

Enhanced MDT-Based Performance Estimation for AI Driven Optimization in Future Cellular Networks

2020

View full text Add to dashboard Cite

show abstract

“…The latter are then exploited to estimate the network quality at unobserved locations. In [34], Enami et al present Regional Analysis to Infer KPIs (RAIK) as a method to forecast the Reference Signal Received Power (RSRP), which exploits highly detailed Light Detection and Ranging (LIDAR) environment maps for achieving highly accurate estimations. Fig.…”

Section: Related Workmentioning

confidence: 99%

Data-Driven Network Simulation for Performance Analysis of Anticipatory Vehicular Communication Systems

Sliwa

Wietfeld

2019

IEEE Access

View full text Add to dashboard Cite

IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, including reprinting/republishing this material for advertising or promotional purposes, collecting new collected works for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Abstract-The provision of reliable connectivity is envisioned as a key enabler for future autonomous driving. Anticipatory communication techniques have been proposed for proactively considering the properties of the highly dynamic radio channel within the communication systems themselves. Since real world experiments are highly time-consuming and lack a controllable environment, performance evaluations and parameter studies for novel anticipatory vehicular communication systems are typically carried out based on network simulations. However, due to the required simplifications and the wide range of unknown parameters (e.g., Mobile Network Operator (MNO)-specific configurations of the network infrastructure), the achieved results often differ significantly from the behavior in real world evaluations. In this paper, we present Data-driven Network Simulation (DDNS) as a novel data-driven approach for analyzing and optimizing anticipatory vehicular communication systems. Different machine learning models are combined for achieving a close to reality representation of the analyzed system's behavior. In a proof of concept evaluation focusing on opportunistic vehicular data transfer, the proposed method is validated against field measurements and system-level network simulation. In contrast to the latter, DDNS does not only provide massively faster result generation, it also achieves a significantly better representation of the real world behavior due to implicit consideration of crosslayer dependencies by the machine learning approach.The authors are with Communication Networks Institute, TU Dortmund University, be brought to the next performance level. The exploitation of machine learning offers the potential to be the catalyst for this development [5], as its inherent strength is to leverage hidden interdependencies between measurable variables, which are mostly too complex to be covered in an analytical solution.The development process of these novel anticipatory vehicular communication systems confronts researchers and engineers with a methodological dilemma: While the most accurate estimations for the future real world performance can be achieved by performing real world experiments, this approach is highly time consuming and lacks a controllable environment. In fact, it is practically impossible to guarantee fairness by evaluating different methods under the exact same network conditions. System-level network simulation based on Discrete Event Simulation (DES) has emerged as the most commonly used scientific method to analyze mobile communication systems [6], due to its capability of solving both issues. However, the necessary model simplifications reduce the significance of...

show abstract

“…Interestingly, both the Pearson's correlations and the Spearman's correlations reveal that there is a not negligible correlation between the RSRP and the uplink throughput (see [27,). Enami et al [28] build a tool, called RAIK, which is able to predict Key Performance Indicators (KPIs) such the RSRP and the path loss by applying an approach based on neural networks. Their tool takes into account crowdsourced measurements and geographical data (e.g, elevation and buildings).…”

Section: ) Qos Characterizationmentioning

confidence: 99%

“…In particular, RAIK exploits the available measurements to infer the metrics in areas where measurements have not been performed. The measurements used as input to RAIK clearly show that, as the distance between the transmitter and the receiver is increased, the RSRP tends to be notably reduced (see [28,Fig. 5]).…”

Section: ) Qos Characterizationmentioning

confidence: 99%

Not in My Neighborhood: A User Equipment Perspective of Cellular Planning Under Restrictive EMF Limits

et al. 2019

View full text Add to dashboard Cite

The installation of base station (BS) sites is regulated by a variety of laws at international, national, and local levels. While international regulations are already severe, the national and local laws applied in many countries and regions follow precautionary principles and enforce electromagnetic field (EMF) constraints that are even more restrictive. This legal environment results in substantial constraints affecting the planning of cellular networks, as requests for new BS site installation are easily denied by national or local authorities. In this paper, we consider the problem of cellular planning under restrictive EMF limits from the user equipment (UE) viewpoint. We focus on outdoor urban areas and first evaluate the impact of the current, non-optimal network planning at the UE side through a quantitative measurement-driven analysis of the quality of service (QoS) observed by users in heterogeneous, large-scale urban scenarios. We then perform a qualitative assessment of the perceived QoS and generated EMF levels at one UE transferring data from/to a BS based on its position with respect to the serving BS. Finally, we run a what-if analysis by comparing the existing planning with the one where new BS sites can be installed, thanks to a relaxation of the restrictive EMF constraints. Our results clearly show that a cellular planning driven by restrictive EMF constraints forces UE to experience large distances from the serving BS, frequent non-lineof-sight conditions, and poor received signal. In turn, this entails a very negative combination of high electric field activity (EFA) levels generated by the UE and low QoS perceived by the user. We show that, by relaxing the restrictive EMF constraints, the problem could be sensibly mitigated with a positive impact on the UE channel conditions and consequently on the perceived QoS and the UE EFA. INDEX TERMS Cellular network planning, EMF limits, impact on QoS, user equipment measurements.

show abstract

RAIK: Regional analysis with geodata and crowdsourcing to infer key performance indicators

Cited by 17 publications

References 19 publications

Enhanced MDT-Based Performance Estimation for AI Driven Optimization in Future Cellular Networks

Enhanced MDT-Based Performance Estimation for AI Driven Optimization in Future Cellular Networks

Data-Driven Network Simulation for Performance Analysis of Anticipatory Vehicular Communication Systems

Not in My Neighborhood: A User Equipment Perspective of Cellular Planning Under Restrictive EMF Limits

Contact Info

Product

Resources

About