Browsing by Author "Tirkkonen, Olav"

Filter results by typing the first few letters
Now showing 1 - 20 of 147
  • 10 Gigabit-capable Passive Optical Network Transmission Convergence kerroksen suunnittelu
    (2010) Leino, Dmitri
     Elektroniikan, tietoliikenteen ja automaation tiedekunta | Master's thesis
    Uusien laajakaistaisten tietoliikennepalvelujen ja kasvavan tiedonsiirtokapasiteetin tarpeen myötä kiinteiden liityntäverkkojen infrastruktuuri on muuttumassa sähköisestä optiseksi. Euroopan komission rahoittamassa Scalable Advanced Ring-based passive Dense Access Network Architecture (SARDANA)-tutkimusprojektissa tutkitaan seuraavan sukupolven passiivisten optisten liityntäverkojen teknologioita. Projektin päätavoitteena on pienentää passiivisiin optisiin liityntäverkkoihin liittyviä kustannuksia. Tämä diplomityö käsittelee SARDANA-testiverkon standardoimattoman 10 Gigabit-capable Passive Optical Network (XGPON) Transmission Convergence (TC)-kerroksen suunnittelua ja ensimmäistä toteutusta optisessa verkkopäätteessä (ONU:ssa). TC-kerros toteuttaa Medium Access Control (MAC)-protokollan. SARDANA XGPON TC (SXGTC)-kerros perustuu standardoituun ITU-T G.984.3 Gigabit-capable Passive Optical Network (GPON) TC (GTC)-kerroksen [ITU08] tarjoamaan ratkaisuun mutta eroaa tästä yksityiskohdiltaan. Kaikki SXGTC-kerroksen oleelliset yksityiskohdat peilataan GTC-kerrokseen. Suunniteltu SXGTC-protokolla tukee maksimissaan 9.95328 Gbps:n symmetrisiä tiedonsiirtonopeuksia. SXGTC-protokolla on optimoitu käsittelemään dataa 8 tavun sanoissa. Ensimmäinen ONU SXGTC-kerroksen toteutus ohjelmoitavassa Field Programmable Gate Array (FPGA)-piirissä esitellään funktionaalisten lohkojen avulla. Tämän implementaation tiedonsiirtonopeus alasuunnassa on 9.95328 Gbps 98 %:n kaistatehokkuudella ja yläsuunnassa 2.48832 Gbps 94.5 %:n kaistatehokkuudella SARDANA-testiverkkokonfiguraation tapauksessa.
  • Adaptive Cache Policy Optimization Through Deep Reinforcement Learning in Dynamic Cellular Networks
    (2024) Srinivasan, Ashvin; Amidzade, Mohsen; Zhang, Junshan; Tirkkonen, Olav
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    We explore the use of caching both at the network edge and within User Equipment (UE) to alleviate traffic load of wireless networks. We develop a joint cache placement and delivery policy that maximizes the Quality of Service (QoS) while simultaneously minimizing backhaul load and UE power consumption, in the presence of an unknown time-variant file popularity. With file requests in a time slot being affected by download success in the previous slot, the caching system becomes a non-stationary Partial Observable Markov Decision Process (POMDP). We solve the problem in a deep reinforcement learning framework based on the Advantageous Actor-Critic (A2C) algorithm, comparing Feed Forward Neural Networks (FFNN) with a Long Short-Term Memory (LSTM) approach specifically designed to exploit the correlation of file popularity distribution across time slots. Simulation results show that using LSTM-based A2C outperforms FFNN-based A2C in terms of sample efficiency and optimality, demonstrating superior performance for the non-stationary POMDP problem. For caching at the UEs, we provide a distributed algorithm that reaches the objectives dictated by the agent controlling the network, with minimum energy consumption at the UEs, and minimum communication overhead.
  • Adaptive Sector Splitting based on Channel Charting in Massive MIMO Cellular Systems
    (2021-06-15) Al-Tous, Hanan; Tirkkonen, Olav; Liang, Jing
     A4 Artikkeli konferenssijulkaisussa
    We consider a downlink scenario where a multiantenna base station in a sectorized cellular system creates multiple logical cells in each sector, applying Adaptive Sector Splitting (ASS). In ASS, a population of User Equipments (UEs) is grouped based on radio Channel State Information (CSI), groups are assigned to cells, and the virtual antennas serving the cells are optimized based on CSI. Grouping UEs based on covariance matrix similarity may result in considerable spatial overlap of the UE groups, and a need for frequent handovers for mobile UEs. To reduce handovers, an improved grouping strategy that takes into account UE physical locations is needed. We use Channel Charting (CC) to learn the radio map of the cell from uplink CSI, and consider UE grouping based on CC locations aiming to maximize the mean distance of UEs to virtual cell borders without the need to know the physical locations of the UEs. Simulation results show that ASS groups based on CC are more compact than angle-of-arrival and covariance matrix based groupings from the literature.
  • Analysis of Energy Efficiency in IEEE 802.11ah
    (2015-06-10) Zhao, Yue
     Sähkötekniikan korkeakoulu | Master's thesis
    Recently, machine to machine (M2M) communication has been considerably evolved and occupied a large proportion of the wireless markets. The distinct feature of M2M applications brings new challenges to the design of the wireless systems. In order to increase the competence for M2M markets, several enhancements have been proposed accordingly in different wireless technologies. The thesis introduces these M2M enhancements with a focus on the Wi-Fi solution - 802.11ah technology. 802.11ah is a new amendment of Wi-Fi technology for M2M applications. In 802.11ah, a new mechanism named TIM segmentation has been introduced to provide scalable operation for a large number of devices as well as reduce the energy consumption. The scope of the thesis is to evaluate the energy efficiency of TIM segmentation in uplink traffic assuming Poisson process. To thoughtfully understand the principle of this mechanism, the fundamental MAC layer functions in Wi-Fi technologies have also been introduced. In addition, the thesis also proposed an energy-saving solution called additional sleeping (AS) cycles. The performance evaluation is based on a Matlab system-level simulator. The simulations are carried out for various TIM segmentation deployments for a selected M2M use case, the agriculture scenario. The results show that the TIM segmentation can deteriorate the performance for uplink transmission. This is because that in sporadic traffic, restricting the uplink access causes the increase in packet buffering and these packets leads to simultaneous transmission. This can be a serious issue especially for the network with a large number of devices. The random backoff procedure in Wi-Fi cannot efficiently solve this collision problem. In addition, results shows that the AS cycles can reduce the energy consumption in busy-channel sensing and also decrease the collision probability by adding extra randomness.
  • Angle-Delay Features and Distances for Channel Charting
    (2024) Uykan, Zekeriya; Al-Tous, Hanan; Yiğitler, Hüseyin; Jäntti, Riku; Tirkkonen, Olav
     A4 Artikkeli konferenssijulkaisussa
    Channel charting (CC) is an unsupervised machine learning framework for learning a lower-dimensional representation of Channel State Information (CSI), while preserving spatial relations between CSI samples. In this paper, we consider super-resolution features in the angle-delay domain in massive Multiple-Input Multiple-Output (MIMO) systems. We i) treat the angle and delay separately, ii) present the so-called 'Normalized Polar Feature' utilizing the channel statistics of the CSI samples, iii) use the Euclidean distance to compute the dissimilarity matrix, and create the channel chart. Simulation results based on the DeepMIMO data-set show that the proposed super-resolution representation with the Euclidean distance leads to the state-of-the-art quality CC as compared to other CSI features and distances from the literature such as angle-delay-power features with earth mover distance.
  • Anomaly Detection in Radio Access Network Performance Data
    (2024-06-17) Asikainen, Eero
     Perustieteiden korkeakoulu | Master's thesis
    Mobile network operators deploy, configure, and maintain mobile networks, which play an important role in providing ubiquitous communication services to their customers. A key component of these networks are the base stations, whose performance is actively monitored by gathering performance data. Anomalies in this data may be indicative of malfunctions, which can originate from various reasons. Due to the immense volume of the data, automatic solutions are needed to be able to detect such anomalies. This thesis explores the design of an automatic anomaly detection method for the performance data of 4G base stations. The dataset that is used in the work includes 13 mobile network key performance indicators across 500 base stations gathered from a large Finnish network operator. The dataset is unlabeled, so a small scale test dataset is created, which includes manually selected examples of anomalies out of the whole dataset. Multiple existing anomaly detection methods are compared. The methods are evaluated based on their ability to detect relevant anomalies while minimizing the amount of false positives generated. The anomalies they find on the whole dataset are visually inspected, and the methods are analyzed against design requirements. The best performing methods are selected to be joined into one combined method, which is shown to be able to rank base stations based on how anomalous their behavior is across all the key performance indicators.
  • Antenna tuning for WCDMA RF front end
    (2012) Sidhwani, Reema
     Sähkötekniikan korkeakoulu | Master's thesis
    Modern mobile handsets or so called Smart-phones are not just capable of communicating over a wide range of radio frequencies and of supporting various wireless technologies. They also include a range of peripheral devices like camera, keyboard, larger display, ash-light etc. The provision to support such a large feature set in a limited size, constraints the designers of RF front ends to make compromises in the design and placement of the antenna which deteriorates its performance. The surroundings of the antenna especially when it comes in contact with human body, adds to the degradation in its performance. The main reason for the degraded performance is the mismatch of impedance between the antenna and the radio transceiver which causes part of the transmitted power to be reflected back. The loss of power reduces the power amplifier efficiency and leads to shorter battery life. Moreover the reflected power increases the noise floor of the receiver and reduces its sensitivity. Hence the over performance of the radio module in terms of Total Radiated Power and Total Isotropic Sensitivity, gets substantially degraded in the face of these losses. This thesis attempts to solve the issue of impedance mismatch in RF front-ends by introducing an adaptive antenna tuning system between the radio module and the antenna. Using tunable reactive components and by intelligently controlling them through a tuning algorithm, this system is able to compensate the impedance mismatch to a large extent. The improvement in the output power and the reduction in the Return Loss observed in the measurements carried out for WCDMA, as part of this thesis work, confirm this. However, the antenna tuner introduces an insertion loss and hence degrades the performance in perfect match conditions. The overall conclusion is that the adaptive antenna tuner system improves the performance much more than it degrades it. Hence it is an attractive solution to be included in mobile terminals on a commercial scale.
  • Automated Analysis of Antenna Data in 5G New Radio Uplink
    (2020-05-18) Pulkkinen, Joel
     Sähkötekniikan korkeakoulu | Master's thesis
    The transition to the next generation of mobile communications has begun as the fifth generation mobile communication (5G) networks are being deployed worldwide. The need for 5G keeps growing, as the number of connected devices and the amount of traffic continue to increase. Furthermore, 5G is expected to have a large impact on our society and industry. Consequently, the deployment schedule is strict and the requirements set for 5G mobile networks are notably higher than for previous mobile communication systems. Tight schedule, high requirements and fierce competition make the software and hardware development for 5G challenging. The scope of this thesis is in the uplink physical layer software development for 5G base station (BS) units. The first 5G BS products are already being delivered to customers globally. In order to keep customers satisfied, it is important to have efficient troubleshooting methods when possible issues arise in the field. The current troubleshooting process involves the analysis of captured antenna data. The analysis includes an initial evaluation stage, where the captured data has to be processed manually. This manual processing includes repetitive work and consumes time that is removed from actual troubleshooting. If the problem is not found in the initial evaluation stage, more extensive analysis is needed with internal tools. Currently, there is a risk of performing unnecessary analysis if a simple failure is missed in the initial evaluation. The goal of this thesis is to partially automate the uplink reception troubleshooting process by implementing a tool that can perform some of the initial analysis work on behalf of the troubleshooter. The components to be automatised were analysed and based on multiple requirements the chosen implementation method for the tool was programming language Python. It is shown that the implemented tool can improve the uplink troubleshooting process by helping in the detection of some of the most common problems. Typically, the most common problems are issues related to synchronisation and used hardware. These problems cause clear anomalies to the received signal that the implemented tool can detect. By detecting these anomalies, it is possible to narrow down the possible causes of a decoding failure. Therefore, the manual workload for antenna data processing is moved to the actual troubleshooting itself. In addition, time and resources are saved as the risk of performing unnecessary analysis work is mitigated.
  • Average Downlink SINR Modeling in 5G with Analog Beamforming using an Emulated Multi-Beam Scheduler Model
    (2018-12-10) Ali, Amaanat
     Sähkötekniikan korkeakoulu | Master's thesis
  • Beam SNR Prediction Using Channel Charting
    (2023-10-01) Kazemi, Parham; Al-Tous, Hanan; Ponnada, Tushara; Studer, Christoph; Tirkkonen, Olav
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    We consider a machine learning approach for beam handover in mmWave 5G New Radio systems, in which User Equipments (UEs) perform autonomous beam selection, conditioned on a used Base Station (BS) beam. We develop a network-centric approach for predicting beam Signal-to-Noise Ratio (SNR) from Channel State Information (CSI) features measured at the BS, which consists of two phases; offline and online. In the offline training phase, we construct CSI features and dimensionality-reduced Channel Charts (CCs). We annotate the CCs with per-beam SNRs for different combinations of a BS beam and the corresponding best UE beam, and train models to predict SNR from CSI features for different BS/UE beam combinations. In the online phase, we predict SNRs of beam combinations not being used at the moment. We develop a low complexity out-of-sample algorithm for dimensionality reduction in the online phase. We consider K-nearest neighbors, Gaussian process regression, and neural network-based predictions. To evaluate the efficacy of the proposed framework, we perform simulations for a street segment with synthetically generated CSI. We investigate the complexity-accuracy trade-off for different dimensionality reduction techniques and different predictors. Our results reveal that nonlinear dimensionality reduction of CSI features with neural network prediction shows the best performance, and the performance of the best CSI-based prediction method is comparable to prediction based on using known physical location.
  • Best Beam Prediction in Non-Standalone mm Wave Systems
    (2021-07-28) Ponnada, Tushara; Kazemi, Parham; Al-Tous, Hanan; Liang, Ying-Chang; Tirkkonen, Olav
     A4 Artikkeli konferenssijulkaisussa
    We consider a machine learning approach to perform best beam prediction in Non-Standalone Millimeter Wave (mmWave) Systems utilizing Channel Charting (CC). The approach reduces communication overheads and delays associated with initial access and beam tracking in 5G New Radio (NR) systems. The network has a mmWave and a sub-6 GHz component. We devise a Base Station (BS) centric approach for best mmWave beam prediction, based on Channel State Information (CSI) measured at the sub-6 GHz BS, with no need to exchange information with UEs. In a training phase, we collect CSI at the sub-6 GHz BS from sample UEs, and construct a dimensional reduction of the sample CSI, called a CC. We annotate the CC with best beam information measured at a mmWave BS for the sample UEs, assuming autonomous beamformer at the UE side. A beam predictor is trained based on this information, connecting any sub-6 GHz CSI with a predicted best mmWave beam. To evaluate the efficiency of the proposed framework, we perform simulations for a street segment with synthetic spatially consistent CSI. With a neural network predictor, we obtain 91% accuracy for predicting best beam and 99% accuracy for predicting one of two best beams. The accuracy of CC based beam prediction is indistinguishable from true location based beam prediction.
  • A Big Data Enabled Channel Model for 5G Wireless Communication Systems
    (2020-06-01) Huang, Jie; Wang, Cheng-Xiang; Bai, Lu; Sun, Jian; Yang, Yang; Li, Jie; Tirkkonen, Olav; Zhou, Ming-Tuo
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    The standardization process of the fifth generation (5G) wireless communications has recently been accelerated and the first commercial 5G services would be provided as early as in 2018. The increasing of enormous smartphones, new complex scenarios, large frequency bands, massive antenna elements, and dense small cells will generate big datasets and bring 5G communications to the era of big data. This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling. We propose a big data and machine learning enabled wireless channel model framework. The proposed channel model is based on artificial neural networks (ANNs), including feed-forward neural network (FNN) and radial basis function neural network (RBF-NN). The input parameters are transmitter (Tx) and receiver (Rx) coordinates, Tx-Rx distance, and carrier frequency, while the output parameters are channel statistical properties, including the received power, root mean square (RMS) delay spread (DS), and RMS angle spreads (ASs). Datasets used to train and test the ANNs are collected from both real channel measurements and a geometry based stochastic model (GBSM). Simulation results show good performance and indicate that machine learning algorithms can be powerful analytical tools for future measurement-based wireless channel modeling.
  • Cache Policy Design via Reinforcement Learning for Cellular Networks in Non-Stationary Environment
    (2023-10-23) Srinivasan, Ashvin; Amidzade, Mohsen; Zhang, Junshan; Tirkkonen, Olav
     A4 Artikkeli konferenssijulkaisussa
    We consider wireless caching both at the network edge and at User Equipment (UE) to alleviate traffic congestion, aiming to find a joint cache placement and delivery policy by maximizing the Quality of Service (QoS) while minimizing backhaul load and User Equipment (UE) power consumption. We assume unknown and time-variant file popularities which are affected by the UE cache content, leading to a non-stationary Partial Observable Markov Decision Process (POMDP). We address this problem in a deep reinforcement learning framework, employing Feed Forward Neural Network (FFNN) and Long Short Term Memory (LSTM) networks in conjunction with Advantageous Actor Critic (A2C) algorithm. LSTM exploits the correlation of the file popularity distribution across time slots to learn information of the dynamics of the environment and A2C algorithm is used due to its ability of handling continuous and high dimensional spaces. We leverage LSTM and A2C tools based on its virtue to find an optimal solution for the POMDP environment. Simulation results show that using LSTM-based A2C outperforms a FFNN-based A2C in terms of sample efficiency and optimality. An LSTM-based A2C gives a superior performance under the non-stationary POMDP paradigm.
  • Caching in Cellular Networks Based on Multipoint Multicast Transmissions
    (2023-04-01) Amidzade, Mohsen; Al-Tous, Hanan; Tirkkonen, Olav; Caire, Giuseppe
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    We consider cellular network caching with network-wide Orthogonal Multipoint Multicast (OMPMC) delivery. We apply a probabilistic model for content placement at the Base Stations (BSs). Content is delivered with multipoint multicast operating in file-specific orthogonal resources: all BSs caching a distinct file synchronously multicast it to requesting users in a dedicated resource. For a network modeled as a Poisson Point Process (PPP), an expression for the outage probability is derived. The outage-minimizing cache policy is found from a joint constrained optimization problem over cache placement and resource allocation. We devise principles by which the solution in one propagation environment can be generalized to another. To reduce computational complexity, we obtain a sub-optimal solution based on convex relaxation. We obtain an upper bound of the gap between the optimal and sub-optimal solutions. We compare the outage performance of OMPMC with delivery polices from the literature. Simulation results show that exploiting OMPMC with optimal cache placement and resource allocation outperforms single point cache delivery policies with a wide margin.
  • Cellular network caching based on multipoint multicast transmissions
    (2020-12) Amidzadeh, Mohsen; Al-Tous, Hanan; Tirkkonen, Olav; Caire, Giuseppe
     A4 Artikkeli konferenssijulkaisussa
    We consider an optimal cache-placement-and-delivery-policy using Network-level Orthogonal Multipoint Multicasting (OMPMC) for wireless networks. The placement of files in caches of Base Station (BS) is based on a probabilistic model, with controlled cache placement probabilities. File delivery is based on multipoint multicast and network-based orthogonal transmission; all BSs in the network caching a file transmit it synchronously in dedicated radio resources. If the average signal-to-noise ratio associated to a file at a requesting user is less than a threshold, the request is in outage. We derive a closed-form expression for the outage probability for a network modeled as a Poisson Point Process. An optimal caching policy is solved from an optimization problem, and compared to a threshold-based policy, suboptimal partial solutions, and single-point cache delivery. Simulation results show that exploiting OMPMC with optimal cache and bandwidth allocation significantly improves the overall outage probability as compared to single point delivery.
  • Cellular Traffic Offloading with Optimized Compound Single-point Unicast and Cache-based Multipoint Multicast
    (2022-05-16) Amidzade, Mohsen; Al-Tous, Hanan; Tirkkonen, Olav; Caire, Giuseppe
     A4 Artikkeli konferenssijulkaisussa
    We consider an optimal cache-placement-and-delivery-policy where traffic is offloaded from Single-Point Unicast (SPUC) service by using network-level Orthogonal Multipoint Multicast (OMPMC) scheme. The files are classified into two sets. The most popular files are cached at the BSs using a probabilistic approach and are served by OMPMC. The remaining files are fetched from the core network on demand and served by SPUC. Optimal compound scheme is analyzed, based on resource allocation between OMPMC and multi-antenna SPUC schemes. If a user is not able to successfully receive the requested file due to its experienced signal-to-interference-plus-noise ratio, its request is in outage. A closed-form expression is derived for the total outage probability based on stochastic geometry for the compound scheme. An optimization problem is formulated to design the caching policy for the compound scheme. The optimal solution to this problem is obtained by finding optimal cache placement, bandwidth allocation, and file classification. Simulation results show that the compound scheme outperforms other caching schemes in terms of the total outage probability.
  • Channel Charting Aided Pilot Reuse for Massive MIMO Systems with Spatially Correlated Channels
    (2022-12-01) Ribeiro, Lucas; Leinonen, Markus; Al-Tous, Hanan; Tirkkonen, Olav; Juntti, Markku
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    Massive multiple-input multiple-output (mMIMO) technology is a way to increase spectral efficiency and provide access to the Internet of things (IoT) and machine-type communication (MTC) devices. To exploit the benefits of large antenna arrays, accurate channel estimation through pilot signals is needed. Massive IoT and MTC systems cannot avoid pilot reuse because of the enormous numbers of connected devices. We propose a pilot reuse algorithm based on channel charting (CC) to mitigate pilot contamination in a multi-sector single-cell mMIMO system having spatially correlated channels. We show that after creating an interference map via CC, a simple strategy to allocate the pilot sequences can be implemented. The simulation results show that the CC-based pilot reuse strategy improves channel estimation accuracy, which subsequently improves the symbol detection performance and increases the spectral efficiency compared to other existing schemes. Moreover, the performance of the CC pilot assignment method approaches that of exhaustive search pilot assignment for small network setups.
  • Channel Charting Assisted Beam Tracking
    (2022) Kazemi, Parham; Al-Tous, Hanan; Studer, Christoph; Tirkkonen, Olav
     A4 Artikkeli konferenssijulkaisussa
    We propose a novel beam-tracking algorithm based on channel charting (CC) which maintains the communication link between a base station (BS) and a mobile user equipment (UE) in a millimeter wave (mmWave) mobile communications system. Our method first uses large-scale channel state information at the BS in order to learn a CC. The points in the channel chart are then annotated with the signal-to-noise ratio (SNR) of best beams. One can then leverage this CC-to-SNR mapping in order to track strong beams between UEs and BS efficiently and robustly at very low beam-search overhead. Simulation results in a mmWave scenario show that the performance of the CC-assisted beam tracking method approaches that of an exhaustive beam-search approach while requiring significantly lower beam-search overhead than conventional tracking methods.
  • Channel Charting Based Beam SNR Prediction
    (2021-07-28) Kazemi, Parham; Ponnada, Tushara; Al-Tous, Hanan; Liang, Ying-Chang; Tirkkonen, Olav
     A4 Artikkeli konferenssijulkaisussa
    We consider machine learning for intra cell beam handovers in mmWave 5GNR systems by leveraging Channel Charting (CC). We develop a base station centric approach for predicting the Signal-to-Noise-Ratio (SNR) of beams. Beam SNRs are predicted based on measured signal at the BS without the need to exchange information with UEs. In an offline training phase, we construct a beam-specific dimensionality reduction of Channel State Information (CSI) to a low-dimensional CC, annotate the CC with beam-wise SNRs and then train SNR predictors for different target beams. In the online phase, we predict target beam SNRs. K-nearest neighbors, Gaussian Process Regression and Neural Network based prediction are considered. Based on SNR difference between the serving and target beams a handover can be decided. To evaluate the efficiency of the proposed framework, we perform simulations for a street segment with synthetically generated CSI. SNR prediction accuracy of average root mean square error less than 0.3 dB is achieved.
  • Channel Charting with Angle-Delay-Power-Profile Features and Earth-Mover Distance
    (2023-03-07) Al-Tous, Hanan; Kazemi, Parham; Studer, Christoph; Tirkkonen, Olav
     A4 Artikkeli konferenssijulkaisussa
    We are interested in deducing whether two user equipments (UEs) in a cellular system are at nearby physical locations from measuring similarity of their channel state information (CSI). This becomes essential for fingerprinting localization as well as for channel charting. A channel chart is a low dimensional (e.g., 2-dimensional) radio map based on CSI measurements only, which is created using self-supervised machine learning techniques. Analyzing CSI in terms of the angle-delay power profile (ADPP) takes advantage of the uniqueness of the multipath channel between the base station and the UE over the geographical region of interest. We consider super-resolution features in the angle and delay domains in massive multiple-input multiple-output (MIMO) systems and consider the earth-mover distance (EMD) to measure the distance between two features. Simulation results based on the DeepMIMO data set show that the super-resolution ADPP features with EMD leads to a better quality channel chart as compared to other CSI features and distances from the literature.