Search

Anomaly detection (AD) is a solution for cellular operators to overcome the difficulty of quality control over the proliferation of cellular phone usage. The telecommunications network monitoring system with anomaly detection enables immediate discovery of problems before they become more complex. Monitoring activities produce logs, which are then analyzed according to the interest, often with the help of statistics and visualizations. Relying on humans for analysis is increasingly difficult due to the immense amount of logs in modern telecommunication networks. This work extends the monitoring to automated anomaly detection by using various ELK modules to form an intelligent monitoring system. A testbed based on OpenAirInterface (OAI) and USRP B210 radiohead is used, which includes the functionalities of HSS, MME, SGW, PGW, eNB, and UE. The proposed system has an average accuracy of 91.5%. This is supported by an average value of the proportion of normal conditions that are correctly predicted at 99.31%. On the other hand, the system can still maintain the functionality of the cellular telecommunications network with an excellent predicate on service quality.

The open radio access network (RAN) aims to bring openness and intelligence to the traditional closed and proprietary RAN technology and offer flexibility, performance improvement, and cost-efficiency in the RAN’s deployment and operation. This paper provides a comprehensive survey of the Open RAN development. We briefly summarize the RAN evolution history and the state-of-the-art technologies applied to Open RAN. The Open RAN-related projects, activities, and standardization is then discussed. We then summarize the challenges and future research directions required to support the Open RAN. Finally, we discuss some solutions to tackle these issues from the open source perspective.

IoT devices are deployed in a building to instantly collect electricity load usage for next hour load consumption forecasting so that the operation of the building can be properly managed. However, due to the hardware or system error, data missing or overflow might occur. Noise might also be added into the collected data. Under this circumstance, the accuracy of next hour load forecasting would degrade which in turn decreases the building operation performance. In this paper, we propose an hourly load forecasting framework combining Data Preparation and LSTM, namely LSTM-DP, by considering data pre-processing, feature engineering and Long Short-Term Memory (LSTM). In LSTM-DP, the collected data is firstly processed by interpolation and Savitzky Golay filter, therefore the pattern of load consumption can be properly extracted by LSTM for next hour load forecasting. Moreover, we adopt two-stack LSTM to better determine the relationships among the time series information. We study the real data collected from three buildings of a company in Asia to investigate the performance of next hour load forecasting, and the results show the proposed LSTM-DP outperforms others.

A cyber-physical system (CPS) requires a time-bounded communication process for real-time interaction between the digital world and the physical world so that they can form a tight loop. Using the machine-type communication (MTC) protocol for a large-scale CPS is a good solution. However, the MTC protocol uses a random access (RA) mechanism to solve the radio resource contention problem, but that inevitably causes access delays especially in scenarios when there is a large number of MTC devices. To meet CPS requirement and address this problem, we propose a dynamic backoff window adjustment (DBA) algorithm for a pull-based RA process that can appropriately distribute the failed MTC devices engaged in the backoff window, so as to expedite their contention retrial time interval and achieve increased success probability. Simulation results showed that the DBA algorithm significantly increases the success probability of MTC devices contending for RA, and as well, shortens the mean access delay of the MTC devices. In comparison to the standard RA backoff scheme and a novel dynamic backoff (DB) scheme, the DBA algorithm proved to be more effective and suitable for the CPS to the best of our knowledge.

Multicast and broadcast service (MBS) is a point-to-multipoint service where data packets are transmitted simultaneously from a single source to multiple destinations. In MBS, some base stations (BSs) may form an MBS zone and transmit identical MBS contents simultaneously using the same modulation and coding scheme. Hence, the network has to coordinate the transmission of BSs such that BSs belonging to multiple MBS zones may utilize non-conflict resources to transmit different MBS contents. This paper extends the work in [10] for accommodating MBS zones with different service presence probabilities and various bandwidth requirements. A continuous allocation algorithm and a non-continuous allocation algorithm are presented to allocate resource units for overlapping MBS zones. Simulations were conducted to verify the effectiveness of the proposed algorithms.