Key Performance Indicator Data Research Articles

Creating a Data Cleaning and Pre-Processing Module for Generalisable Data Linkage

ObjectiveAcute renal replacement therapy (RRT) is an important life saving technology used in critical care. However, variation in clinical practice for initiation and maintenance of RRT can increase healthcare costs and worsen patient outcomes. In Alberta, Canada, a province-wide electronic health record provides a unique opportunity to measure and evaluate clinical practice. The present study aims to improve the quality of RRT delivery in Alberta critical care units by providing feedback on key performance indicators (KPIs) for RRT based on current evidence. ApproachKPIs for RRT included an initiation pathway based on threshold lab values, and measures of RRT quality such as the time from order to treatment initiation, the average life of dialysis filters, and the actual vs. prescribed fluid removal. Clinical KPI definitions were mapped to data available in the electronic health record to evaluate current practice and track changes in KPIs over time. ResultsMapping the clinical guidelines to the electronic health record took significant time and effort in a large team with expertise on both the data and clinical sides. Each KPI data definition went through several cycles of development, validation and refinement before being included in the dashboards and reports given to participating sites. ConclusionsProviding accurate data on RRT ordering and delivery practices is an important step in aligning acute RRT delivery with current best practice, ultimately improving the quality of care and reducing unnecessary costs. ImplicationsElectronic health records provide a powerful tool for evaluating clinical decisions and implementing best practice guidelines.

Hidden Markov models for predicting cell-level mobile networks performance degradation

The ubiquitous deployment of Fourth-generation (4G) and Fifth-generation (5G) networks, while expanding user connectivity over a larger geographic area, presents significant challenges for mobile network management. The surge in connected devices increase cell congestion, while user mobility, fading, and interference further deteriorate channel quality. The combined effect of these factors contribute to a gradual degradation in cell and network performance, straining the capabilities of Mobile Network Operators (MNOs) to maintain optimal service quality. The degradation progresses through distinct stages, and ultimately leading to cell outages. Existing cell degradation detection methods, such as key performance indicators (KPIs) monitoring and drive tests, rely on indicators such as signal strength (like reference signal received power (RSRP)), network measurements (like traffic volume and handover requests), and user complaints. However, these methods may not provide real-time insights, leading to delays in identifying and addressing performance issues. This paper proposes a Hidden Markov Model (HMM) approach for proactive cell degradation prediction using real-time time-series KPIs data collected from a telecom operator’s network management system. The NetMax system, a network management system specifically designed for ZTE networks, was used for KPIs data collection. RSRP, 3GPP-recommended signal strength metrics for degradation measure, defines hidden states, while traffic volume and handover requests represent the observable states. The HMM achieves an average prediction accuracy of 93.12%, F1 score of 91.81%, and precision of 92.82% with 23 observation lengths, demonstrating the models’s effectiveness in predicting mobile network’s cell degradation severity.

Swarm learning anomaly detection framework for cloud data center using multi-channel BiWGAN-GTN and CEEMDAN

Anomaly detection is an important task for maintaining the performance of cloud data center. Traditional anomaly detection primarily examines individual Virtual Machine (VM) behavior, neglecting the impact of interactions among multiple VMs on Key Performance Indicator (KPI) data,e.g., memory utilization. Furthermore, the non-stationarity, high complexity, and uncertain periodicity of KPI data in VM also bring difficulties to deep learning-based anomaly detection tasks. To settle these challenges, this paper proposes MCBiWGAN-GTN, a multi-channel semi-supervised time series anomaly detection algorithm based on the Bidirectional Wasserstein Generative Adversarial Network with Graph-Time Network (BiWGAN-GTN) and the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). (a)The BiWGAN-GTN algorithm is proposed to extract spatiotemporal information from data. (b) The loss function of BiWGAN-GTN is redesigned to solve the abnormal data intrusion problem during the training process. (c) MCBiWGAN-GTN is designed to reduce data complexity through CEEMDAN for time series decomposition and utilizes BiWGAN-GTN to train different components. (d) To adapt the proposed algorithm for the entire cloud data center, a cloud data center anomaly detection framework based on Swarm Learning (SL) is designed. The evaluation results on a real-world cloud data center dataset show that MCBiWGAN-GTN outperforms the baseline, with an F1-score of 0.96, an accuracy of 0.935, a precision of 0.954, a recall of 0.967, and an FPR of 0.203. The experiments also verify the stability of MCBiWGAN-GTN, the impact of parameter configurations, and the effectiveness of the proposed SL framework.

Anomaly detection for key performance indicators by fusing self-supervised spatio-temporal graph attention networks

With the development of Artificial Intelligence for IT Operations (AIOps), numerous software and services are monitored by Key Performance Indicators (KPIs) collection components. Multivariate KPIs, as a type of time series data, are essential for effective management of the entity's service quality. In recent years, deep learning methods have made great improvements in the anomaly detection of multivariate time series; however, existing methods have not fully considered how to explicitly capture the correlation between multivariate time series in the feature dimension and temporal dimension, resulting in inevitable abnormal false positives. Therefore, this paper proposes a self-supervised multivariate KPIs anomaly detection method MAD-STA that combines graph structure learning and spatio-temporal GAT (Graph Attention Network). In the feature dimension, MAD-STA introduces a node embedding mechanism for graph structure learning and then uses the feature-oriented GAT layer to compute the graph attention coefficient to obtain the correlation between different KPIs. In the temporal dimension, MAD-STA uses the time-oriented GAT layer to compute attention weights between correlated timestamps, and the GRU-based VAE encoder captures long-term dependence to extract more comprehensive temporal feature representations. Finally, MAD-STA uses GRU-based VAE decoder to reconstruct the captured high-level features and achieves efficient anomaly detection and localization by calculating the anomaly score of multiple KPIs. Compared with the baseline methods on multiple data sets, the experimental results show that the anomaly detection accuracy of MAD-STA is better than that of the baseline method. Especially on the KPI data sets of the two server clusters of SMD and CKM, MAD-STA improves the performance and the F1 comprehensive index compared with the best baseline method. In addition, MAD-STA performs well on anomaly false positive rate and has excellent interpretability, which can be used to assist anomaly diagnosis and root cause index analysis.

Quality and sustainability of Ethiopia's national surgical indicators.

In 2015, the Ethiopian Federal Ministry of Health (FMOH) developed the Saving Lives through Safe Surgery (SaLTS) initiative to improve national surgical care. Previous work led to development and implementation of 15 surgical key performance indicators (KPIs) to standardize surgical data practices. The objective of this project is to investigate current practices of KPI data collection and assess quality to improve data management and strengthen surgical systems. The first portion of the study documented the surgical data collection process including methods, instruments, and effectiveness at 10 hospitals across 2 regions in Ethiopia. Secondly, data for KPIs of focus [1. Surgical Volume, 2. Perioperative Mortality Rate (POMR), 3. Adverse Anesthetic Outcome (AAO), 4. Surgical Site Infection (SSI), and 5. Safe Surgery Checklist (SSC) Utilization] were compared between registries, KPI reporting forms, and the DHIS2 (district health information system) electronic database for a 6-month period (January-June 2022). Quality was assessed based on data completeness and consistency. The data collection process involved hospital staff recording data elements in registries, quality officers calculating KPIs, completing monthly KPI reporting forms, and submitting data into DHIS2 for the national and regional health bureaus. Data quality verifications revealed discrepancies in consistency at all hospitals, ranging from 1-3 indicators. For all hospitals, average monthly surgical volume was 57 cases, POMR was 0.38% (13/3399), inpatient SSI rate was 0.79% (27/3399), AAO rate was 0.15% (5/3399), and mean SSC utilization monthly was 93% (100% median). Half of the hospitals had incomplete data within the registries, ranging from 2-5 indicators. AAO, SSC, and SSI were commonly missing data in registries. Non-standardized KPI reporting forms contributed significantly to the findings. Facilitators to quality data collection included continued use of registries from previous interventions and use of a separate logbook to document specific KPIs. Delayed rollout of these indicators in each region contributed to issues in data quality. Barriers involved variable indicator recording from different personnel, data collection tools that generate false positives (i.e. completeness of SSC defined as paper form filled out prior to patient discharge) or missing data because of reporting time period (i.e. monthly SSI may miss infections outside of one month), inadequate data elements in registries, and lack of standardized monthly KPI reporting forms. As the FMOH introduces new indicators and changes, we recommend continuous and consistent quality checks and data capacity building, including the use of routinely generated health information for quality improvement projects at the department level.

Assessing Knowledge Performance for the Fast-Track Delivery of Sustainable Mobility Solutions

European cities are motivated to act towards the achievement of climate-neutral mobility solutions. Often, though, they are facing many challenges when bringing (innovative) sustainable mobility solutions forward. Capacity building that fills the skills gaps and/or enables the acquisition of new ones related to the planning and implementation of such solutions can empower local/regional authorities to identify them, adopt them and eventually deliver them properly. The aim of this paper is to present the Key Performance Indicator (KPI) framework that has been used for the assessment of the effectiveness of the Learning and Exchange Programme applied in an EU-funded project. It presents the methodological steps for the adoption of the KPIs, as well as the tools used for the selection of the KPI data and the KPI monitoring at the project level. It also presents the results from the application of the framework for assessing the knowledge performance towards the deployment of sustainable mobility solutions. It finally reflects on recommendations for applying the KPI framework to other cases and thematic contents.

LEAF: Navigating Concept Drift in Cellular Networks

Operational networks commonly rely on machine learning models for many tasks, including detecting anomalies, inferring application performance, and forecasting demand. Yet, model accuracy can degrade due to concept drift, whereby the relationship between the features and the target to be predicted changes. Mitigating concept drift is an essential part of operationalizing machine learning models in general, but is of particular importance in networking's highly dynamic deployment environments. In this paper, we first characterize concept drift in a large cellular network for a major metropolitan area in the United States. We find that concept drift occurs across many important key performance indicators (KPIs), independently of the model, training set size, and time interval---thus necessitating practical approaches to detect, explain, and mitigate it. We then show that frequent model retraining with newly available data is not sufficient to mitigate concept drift, and can even degrade model accuracy further. Finally, we develop a new methodology for concept drift mitigation, Local Error Approximation of Features (LEAF). LEAF works by detecting drift; explaining the features and time intervals that contribute the most to drift; and mitigates it using forgetting and over-sampling. We evaluate LEAF against industry-standard mitigation approaches (notably, periodic retraining) with more than four years of cellular KPI data. Our initial tests with a major cellular provider in the US show that LEAF consistently outperforms periodic and triggered retraining on complex, real-world data while reducing costly retraining operations.

Performance Assessment Method for Small- and Medium-Sized Urban Water Systems: Development and Implementation

ABSTRACT Performance assessment of Small and Medium-Sized Water Systems (SMWSs) is important for operational, tactical, and strategic decision-making. In this study, a performance assessment method has been developed and applied to five drinking water, three wastewater, and two stormwater utilities using 39, 30 and 27 Key Performance Indicators (KPIs) in a semi-arid region. The KPIs were aggregated to determine a performance index using a Technique for Order of Preference by Similarity to Ideal Solution method. K-nearest neighbors and penalty methods were used to estimate missing KPIs data. The results indicated that only two drinking water utilities and one wastewater utility had been rated as ‘high’ performance. None of the utilities in stormwater performance was rated as ‘high’. The developed method can assist decision-makers in evaluating SMWSs performance holistically, build operational management strategies, and identify necessary interventions in overcoming water systems challenges across each urban water system component.

Use of statistical process control charts to identify impactful implementation strategies for an ePRO-based symptom management program across the SIMPRO Consortium.

6579 Background: Collecting electronic patient reported outcomes (ePROs) reduces the burden of cancer and prevents acute care hospitalizations. However, broad implementation in the routine care setting remains challenging, partly because the optimal implementation strategies – actions that are most likely to encourage adoption and use – are not known. Since 2019, the SIMPRO Consortium has deployed an ePRO-based symptom management program (eSyM) across 6 community-based cancer centers. Methods: We used statistical process control (SPC) charts to identify variation due to special versus common causes (random variation) for one key performance indicator (KPI) – the weekly ePROs response rate. All 6 SIMPRO sites contributed data for this analysis: 3 for chemotherapy patients and 3 for surgery patients. Sites had to have at least 18 months of KPI data; information from the first 4 months after eSyM rollout were excluded to account for program ramp-up. The KPI was calculated as the number of patients who submitted an ePRO questionnaire divided by the number eligible to submit a questionnaire each week. The upper and lower confidence limits were set at +/- 2 sigma to allow for 95% of observations to fall within the limits. Three rules were applied to identify special cause variation: 1) astronomical points (outside sigma limits), 2) shifts (8 or more points above or below a center line), and 3) trends (6 or more points consecutively ascending or descending). Implementation strategies that mapped to special cause variations were selected as those most likely to impact the KPI. Results: Across the 6 sites that deployed eSyM, the mean KPI performance ranged from 19.7%-35.7%. SPC charts detected multiple special cause variations in the KPI at all 6 sites, though the patterns varied by site. All sites demonstrated positive and negative astronomical variations as well as positive and negative shifts. Three sites demonstrated negative trends; no sites demonstrated positive trends. Direct patient outreach was the implementation strategy most frequently associated with special cause variation, followed by changes in promoting the ePRO program to clinical staff. Positive changes were associated with strategy initiation; negative changes were associated with strategy discontinuation. Conclusions: Applying SPC charts to a KPI from the eSyM deployment highlighted the effect of personal communication with patients and providers, suggesting that these implementation strategies could offer value to other sites deploying eSyM. The absence of positive trends early in eSyM program deployment underscores the need to identify better implementation strategies and allocate more resources to foster program adoption and sustainability. Applying SPCs to other KPIs, such as symptom severity and healthcare utilization, could improve eSyM deployment and impact.

Evaluating key performance indicators of the process of care in juvenile idiopathic arthritis

ObjectiveTo determine whether and how often the information to measure a set of key performance indicators (KPIs) in juvenile idiopathic arthritis (JIA) is found in data collected routinely in a Pediatric Rheumatology Clinic.MethodsA retrospective electronic chart review and administrative data analysis was conducted for a cohort of 140 patients with JIA at a tertiary Pediatric Rheumatology Clinic between 2016–2020. The set of KPIs include measuring patient outcomes (joint assessment, physician’s global assessment of disease activity, assessment of functional ability, composite disease activity measurement), access to care (waiting time between referral and first visit, visit with the rheumatologist within the first year of diagnosis, annual follow-up visits with the rheumatologist), and safety (tuberculosis screening, and laboratory monitoring). Documentation was assessed as a binary variable indicating whether the required information was ever found. Documentation frequency for each KPI was assessed with counts and percentages of the number of times the required information was documented for each clinic visit. Compliance with the safety KPI definitions was assessed using administrative databases.ResultsData for each KPI were found at least once in the cohort and documentation varied in frequency and consistency. Access to care and safety KPIs were documented more frequently than patient outcome KPIs. A joint assessment was documented at every visit for 95% of patients, 46% for an assessment of pain, and none for a physician’s global assessment of disease activity, an assessment of functional ability, or a composite disease activity measurement.ConclusionAlthough feasible to measure, there is an opportunity for improving the consistency of documentation. Having an active system of monitoring KPIs and tools to simplify measurement is a key step in the process toward improved patient care outcomes. Streamlining the collection of KPI data can increase the likelihood of compliance. Next steps should involve replicating this study in various centres.

Rancang Bangun Sistem Informasi Konawe Elektronik Sistem Data (Koneksi Data) dengan Menggunakan Metode Waterfall Model

The purpose of this study was to design a data management information system at the Konawe District Bappeda Office and to provide convenience for Bappeda in providing a centralized online-based data and information system, so as to facilitate the process of analyzing policy making. The software development model used is the Waterfall Model which emphasizes sequential and systematic phases. The Waterfall model is used in the design of a Data Connection Information System. The research results show that the design of the Data Connection Information System consists of several stages, namely: needs analysis, application design, programming, testing and program installation that produces Village/Kelurahan Monographic Data, OPD Key Performance Indicator Data (IKU), and LPPD OPD Achievement Data. The system was developed using the PHP-based codeigniter framework which integrates all stages into a web-based application.

DA-LSTM-VAE: Dual-Stage Attention-Based LSTM-VAE for KPI Anomaly Detection.

To ensure the normal operation of the system, the enterprise's operations engineer will monitor the system through the KPI (key performance indicator). For example, web page visits, server memory utilization, etc. KPI anomaly detection is a core technology, which is of great significance for rapid fault detection and repair. This paper proposes a novel dual-stage attention-based LSTM-VAE (DA-LSTM-VAE) model for KPI anomaly detection. Firstly, in order to capture time correlation in KPI data, long-short-term memory (LSTM) units are used to replace traditional neurons in the variational autoencoder (VAE). Then, in order to improve the effect of KPI anomaly detection, an attention mechanism is introduced into the input stage of the encoder and decoder, respectively. During the input stage of the encoder, a time attention mechanism is adopted to assign different weights to different time points, which can adaptively select important input sequences to avoid the influence of noise in the data. During the input stage of the decoder, a feature attention mechanism is adopted to adaptively select important latent variable representations, which can capture the long-term dependence of time series better. In addition, this paper proposes an adaptive threshold method based on anomaly scores measured by reconstruction probability, which can minimize false positives and false negatives and avoid adjustment of the threshold manually. Experimental results in a public dataset show that the proposed method in this paper outperforms other baseline methods.

A KPI Anomaly Detection Method Based on Fast Clustering

In the Artificial Intelligence for IT Operations scenarios, KPI (Key Performance Indicator) is a very important operation and maintenance monitoring indicator, and research on KPI anomaly detection has also become a hot spot in recent years. Aiming at the problems of low detection efficiency and insufficient representation learning of existing methods, this paper proposes a fast clustering-based KPI anomaly detection method HCE-DWL. This paper firstly adopts the combination of hierarchical agglomerative clustering (HAC) and deep assignment based on CNN-Embedding (CE) to perform cluster analysis (that is HCE) on KPI data, so as to improve the clustering efficiency of KPI data, and then separately the centroid of each KPI cluster and its Transformed Outlier Scores (TOS) are given weights, and finally they are put into the LightGBM model for detection (the Double Weight LightGBM model, referred to as DWL). Through comparative experimental analysis, it is proved that the algorithm can effectively improve the efficiency and accuracy of KPI anomaly detection.

Simulating Behavior Pattern of Key Performance Indicators to Improve Organization’s Safety Performance in Maritime Transport

Safety performance management is at the core of safety management system (SMS) in any organization. Managing organization's safety performance in maritime transport is achieved through the identification of key performance indicators (KPIs), which are used to monitor and measure safety performance. Aim of this paper is to determine how behavior pattern of key performance indicators (KPIs) in the organization, can be simulated. Methods used for this research include methods of gathering, describing, and analyzing key performance indicators data of sample organization, as well as statistics, causal modeling, and simulation. Results show behavior pattern of key performance indicators (KPIs) in the organization due to causal impact of certain key performance indicator. In conclusion, the simulation showed how causal modeling techniques can be useful to simulate behavior pattern of key performance indicators (KPIs) in the organization in order to improve organization’s safety performance.

Efficient KPI Anomaly Detection Through Transfer Learning for Large-Scale Web Services

Timely anomaly detection of key performance indicators (KPIs), <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , service response time, error rate, is of utmost importance to Web services. Over the years, many unsupervised deep learning-based anomaly detection approaches have been proposed. To achieve good performance, they require a long period of KPI data for model training, which is not easy to guarantee with frequent service changes. Additionally, the training overhead is too significant for the vast number of KPIs in large-scale Web services. To address the problems, we propose an unsupervised KPI anomaly detection approach, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AnoTransfer</i> , by combining a novel Variational Auto-Encoder (VAE)-based KPI clustering algorithm with an adaptive transfer learning strategy. Extensive evaluation experiments using real-world data collected from several large-scale Web service providers demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AnoTransfer</i> reduces the average initialization time by 65.71% and improves the training efficiency by 50.62 times, without significantly degrading anomaly detection accuracy.

Including stochastics in metamodel-based DEM model calibration

In calibration of model parameters for discrete element method (DEM) based models the focus lies on matching the mean key performance indicator (KPI) values from laboratory experiments to those from simulation results. However, due to the stochastic nature of granular processes experimental results can show large variances. To include stochastic behaviour, interpolation-based and regression-based metamodels are trained with stochastic data. These metamodels are used in the standard mean calibration approach and newly introduced mean-variance calibration approach to predict the KPIs mean and variance. In addition, the effect of enriching data on the calibration is investigated up to 50 repetitions of experiments and simulations. Based on a hopper case study, use of regression-based metamodels trained with KPI data repeated at least 20 times is recommended. While differences between mean and mean-variance-based metamodels were minor in the considered case study, regression-based metamodeling clearly showed improved accuracy and stability over interpolation-based metamodels.

Structure learning‐based unsupervised root cause diagnosis for radio access networks

The next generation radio access networks (RAN) put forward higher requirements for the reliability of base stations. Telecom operators are facing a series of challenges such as network complexity and diversified user needs, which puts forward higher requirements for the performance of RAN. In order to provide users with high-quality experience, causes of performance problems must be quickly identified. Previous work on unsupervised RAN performance diagnosis mainly used correlation information of the data. This work introduces causality into performance diagnosis of RAN. A score-based directed acyclic graph (DAG) structure learning network is used to extract causal relations between key performance indicators (KPIs). In this study, an unsupervised root cause analysis (RCA) scheme, DAG-RCA, is proposed to achieve rapid diagnosis of abnormal performance on the edge nodes of the RAN. DAG-RCA decomposes the work into four phases: abnormal ranking, DAG generation, propagation graph construction and random walk diagnosis. Using the KPI data collected from China Mobile's RAN, DAG-RCA achieves 83.75 % $83.75\%$ top-1 precision on the RCA task.

TSAGen: Synthetic Time Series Generation for KPI Anomaly Detection

A key performance indicator (KPI) consists of critical time series data that reflect the runtime states of network systems (e.g., response time and available bandwidth). Despite the importance of KPI, datasets for KPI anomaly detection available to the public are very limited, due to privacy concerns and the high overhead in manually labelling the data. The insufficiency of public KPI data poses a great barrier for network researchers and practitioners to evaluate and test what-if scenarios in the development of artificial intelligence for IT operations (AIOps) and anomaly detection algorithms. To tackle the difficulty, we develop a univariate time series generation tool called TSAGen, which can generate KPI data with anomalies and controllable characteristics for KPI anomaly detection. Experiment results show that the data generated by TSAGen can be used for comprehensive evaluation of anomaly detection algorithms with diverse user-defined what-if scenarios.

Quality of Monitoring for Cellular Networks

5G networks and beyond introduce a larger number of Network Elements (NEs) and functions than former cellular generations. The increase in NEs will, thus, result in significantly increasing the Management-Plane (M-Plane) data collected from the NEs. Therefore, the conventional centralized Network Management Systems (NMSs) will face fundamental challenges in processing the M-Plane data. In this paper, we present the concept of Quality of Monitoring (QoM) as a solution, which is able to reduce the M-Plane data already at the NEs. First, QoM aggregates the raw M-Plane data into Key Performance Indicators (KPIs). To these KPIs, the QoM applies a data-driven algorithm to define information loss limits for QoM classes specific for each KPI time series. Then, the QoM applies the classes for compressing the KPI data utilizing a lossy-compression method, which is a derivative of the Piece-Wise Constant Approximation (PWCA) algorithm. To evaluate the performance of the QoM solution, we use M-Plane raw data from a live LTE network and calculate four KPIs, while each KPI has different statistical characteristics. We also define three QoM classes named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Exact</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Optimized</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sharp</i> . For all KPIs, the class <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Optimized</i> has a higher compression rate than the class <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Exact</i> , while the class <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sharp</i> has the highest compression rate. Assuming that, for example, NEs of a network produce 280 MB of raw data containing information that needs to be transferred to the network operations center; we use KPIs to represent the information contents of the data, and QoM solution to transfer the data over the network. As a result, the QoM solution achieves an estimated 95% compression gain from the raw data in transfer.

A novel multivariate statistical process monitoring algorithm: Orthonormal subspace analysis

Partial least squares (PLS) and canonical correlation analysis (CCA) are two most popular key performance indicators (KPI) monitoring algorithms, which have shortcomings in dealing with the KPI-related information leakage problem, the model identification problem, the component selection problem, and the process hypothesis problem. To overcome these shortcomings, this study proposes a new multivariate statistics-based process monitoring (MSPM) method called the orthonormal subspace analysis (OSA) method. OSA divides process data and KPI data into three orthonormal subspaces through an analytic solution. Hence, OSA not only can detect a fault but also can judge whether the fault is KPI-related or KPI-unrelated. OSA is always effective irrespective of the availability of the KPI variables in the online monitoring stage. In OSA, the cumulative percent variance (CPV) method is adopted for principal component selection. In brief, OSA is a more effective method than PLS and CCA, and it achieves superior performance in fault detection and classification.