An Approach to Optimize Device Power Performance Towards Energy Efficient Next Generation 5G Networks

A Thermal Aware Approach to Enhance 5G Device Performance and Reliability in mmWave Networks

If you use this dataset and code or any herein modified part of it in any publication, please cite the papers:

A. Thantharate, C. Beard and S. Marupaduga, "An Approach to Optimize Device Power Performance Towards Energy Efficient Next Generation 5G Networks," 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2019, pp. 0749-0754, doi: 10.1109/UEMCON47517.2019.8993067.

A. Thantharate, C. Beard and S. Marupaduga, "A Thermal Aware Approach to Enhance 5G Device Performance and Reliability in mmWave Networks," 2020 International Symposium on Networks, Computers and Communications (ISNCC), 2020, pp. 1-5, doi: 10.1109/ISNCC49221.2020.9297313.

Please reach out adtmv7@umkc.edu if you have any additional questions.

An Approach to Optimize Device Power Performance Towards Energy Efficient Next Generation 5G Networks https://ieeexplore.ieee.org/abstract/document/8993067/

In Fifth Generation (5G), wireless cellular networks, smartphone battery efficiency, and optimal utilization of power have become a matter of utmost importance. Battery and power are an area of significant challenges considering smartphones these days are equipped with advanced technological network features and systems. These features require much simultaneous power to make decisions and to transfer information between devices and network to provide best the user experience. Furthermore, to meet the demands of increased data capacity, data rate, and to provide the best quality of service, there is a need to adopt energy-efficient architectures. This paper presents system-level architectural changes on both User Equipment (UE) and Network elements along with a proposal to modify control signaling as part of Radio Resource Control messages using smartphone battery level. Additionally, we presented real-world 5G mmWave field results, showing impacts on device battery life in varying RF conditions and proposed methods to allocate optimal network resources and improve the energy efficiency by modifying radio layer parameters between devices and base stations. Without these proposed architecture level and system-level algorithm changes, realizing optimal and consistent 5G speeds will be near impossible.

**A Thermal Aware Approach to Enhance 5G Device Performance and Reliability in mmWave Networks https://ieeexplore.ieee.org/abstract/document/9297313 ** 5G NR (New Radio) mmWave networks are creating novel avenues of numerous possibilities and improving mobile broadband in terms of capacity, throughput, and performance, driven by the insatiable demand for faster and better user experience. However, one of the critical problem areas for User Equipment (UE) in mmWave networks is the fast depletion of UE battery power, increase in thermal levels caused by limited coverage and lot of overhead signaling due to rapid radio frequency (RF) and environment changes. With the growing inclusion of advanced functionality on mobile devices, power consumption is growing in parallel, which causes devices to increase thermal temperature, causing an impact on overall system performance. This paper presents system-level change proposal on control signaling between UE and network elements along with changes in UE thermal algorithms based on device battery levels and the coverage of the 5G mmWave networks to deliver the best device performance and user experience. Furthermore, we present real-world field results captured on mmWave networks showing impacts on UE performance with respect to thermal generation in different RF conditions. Our proposal will allocate optimal network resources by modifying the system selection on both UE and base stations. Without the proposed model, realizing the benefits of the 5G NR system along with achieving seamless cellular user experience would be near impossible.

5G , NR , LTE , mmWave , Smartphone , Battery , Power Optimization , Energy Efficiency , Network Efficiency, 5G NR , mmWave , Smartphone , Thermal , Device Temperature , User Equipment , Battery , Network Efficiency , Load Balancing , 3GPP , Power Efficiency , Green Energy

This dataset, provides realistic signal metrics for 3G, 4G, 5G, and LTE network analysis using DragonOS, Spike, and SDR devices. The dataset aims to provide a representative sample of signal measurements for various network types and locations in Bihar, India. The dataset also replicates the hardware setup involving the Spike software, DragonOS running on the Valve Steam Deck gaming system, BB60C spectrum analyzer powered by an external USB3 hub connected to the Steam Deck's USB C port, srsRan running on a separate laptop for creating the base station using the bladeRFxA9 device.

Features: The dataset includes the following features:

1. Timestamp: The timestamps represent the time at which the signal metrics were recorded, with a 10-minute interval between each timestamp.

2. Latitude and Longitude: The latitude and longitude coordinates indicate the location of the measurement in Bihar. The dataset covers 20 specified localities in Bihar, including Kankarbagh, Rajendra Nagar, Boring Road, Ashok Rajpath, Danapur, Anandpuri, Bailey Road, Gardanibagh, Patliputra Colony, Phulwari Sharif, Exhibition Road, Pataliputra, Fraser Road, Kidwaipuri, Gandhi Maidan, S.K. Puri, Anisabad, Boring Canal Road, Bankipore, and Kumhrar.

3. Signal Strength (dBm): The signal strength represents the received signal power in decibels (dBm) for different network types (3G, 4G, 5G, and LTE).

4. Signal Quality (%): The signal quality represents the percentage of signal strength relative to the maximum possible signal strength. It is calculated based on the signal strength values and is applicable for 3G, 4G, 5G, and LTE networks. Unfortunately, Signal Quality percentage yielded some error so it's 0.0 in all.

5. Data Throughput (Mbps): The data throughput represents the network's capacity to transmit data, measured in megabits per second (Mbps). Different network types have varying data throughput values.

6. Latency (ms): Latency refers to the time delay between the transmission and reception of data packets, measured in milliseconds (ms). Different network types have different latency values, generated using a random uniform distribution within appropriate ranges.

7. Network Type: The network type indicates the technology used for data transmission, such as 3G, 4G, 5G, or LTE.

8. BB60C Measurement (dBm): The BB60C measurement represents the signal strength measured using the BB60C spectrum analyzer device. The values are generated based on the signal strength values with added random uniform noise specific to 4G, 5G, and LTE networks.

9. srsRAN Measurement (dBm): The srsRAN measurement represents the signal strength measured using the srsRAN software-defined radio device.

10. BladeRFxA9 Measurement (dBm): The BladeRFxA9 measurement represents the signal strength measured using the BladeRFxA9 software-defined radio device.

The dataset is generated with a total of 1926 time periods and covers 20 localities in Bihar. It can be used for various purposes, including network optimization, coverage analysis, and performance evaluation.

Hardware Setup: The dataset replicates the hardware setup using the following components:

• Valve Steam Deck gaming system running DragonOS Focal
• BB60C spectrum analyzer powered by an external USB3 hub
• srsRan software-defined radio (SDR) device
• BladeRFxA9 software-defined radio (SDR) device

The BB60C spectrum analyzer is connected to the Steam Deck's USB C port via an external USB3 hub. The srsRan and BladeRFxA9 devices are connected to a separate laptop, which is running the srsenb software to create the base station.

Additionally, the Spike LTE Analysis tools are utilized to decode the LTE information in real-time. The dataset demonstrates how the Spike software, DragonOS, and SDR devices can be integrated to perform LTE analysis, and the results can be combined with a working GPS for mapping purposes within the Spike software.

Atlast, We'd like to extend credits to our volunteers in these localities who helped in logging the data after replicating the setup.

Let us know what you build out of this dataset. It's a subset of data that's being analysed for bio weapon usage in the Bihar area which's controlled via wireless signals to report to international delegates for expedited action against these.

The features used in the dataset are: Cell Identity: Cell identity in the Internet of Things (IoT) is a unique number that identifies a cell in a network. Downlink Traffic: The transmission of traffic from a service provider network to a customer network. Location Area Code (LAC): A unique number that identifies a location area within a cellular network. Duration: Time duration of data transfer. Radio Access Type (RAT): The physical connection method for a radio communication network. Uplink Traffic: The traffic transmitted from a customer network to a service provider network. Latency: Latency is the time it takes for data to travel from its source to its destination. In the context of the Internet of Things (IoT), latency is the time between when a request is sent and when a response is received. Throughput: It is the amount of data that can be transmitted and received in a given time period.

DeepSlice: A Deep Learning Approach towards an Efficient and Reliable Network Slicing in 5G Networks

Secure5G: A Deep Learning Framework Towards a Secure Network Slicing in 5G and Beyond

If you use this dataset and code or any herein modified part of it in any publication, please cite the papers:

A. Thantharate, R. Paropkari, V. Walunj and C. Beard, "DeepSlice: A Deep Learning Approach towards an Efficient and Reliable Network Slicing in 5G Networks," 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York City, NY, USA, 2019, pp. 0762-0767, doi: 10.1109/UEMCON47517.2019.8993066.

A. Thantharate, R. Paropkari, V. Walunj, C. Beard and P. Kankariya, "Secure5G: A Deep Learning Framework Towards a Secure Network Slicing in 5G and Beyond," 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 2020, pp. 0852-0857, doi: 10.1109/CCWC47524.2020.9031158.

DeepSlice: Existing cellular communications and the upcoming 5G mobile network requires meeting high-reliability standards, very low latency, higher capacity, more security, and high-speed user connectivity. Mobile operators are looking for a programmable solution that will allow them to accommodate multiple independent tenants on the same physical infrastructure and 5G networks allow for this end-to-end network resource allocation using the concept of Network Slicing (NS). Data-driven decision making will be vital in future communication networks due to the traffic explosion and Artificial Intelligence (AI) will accelerate the 5G network performance. In this paper, we implement Machine Learning (ML) and Deep Learning (DL) Neural Network models to manage network load efficiency and network availability, utilizing in-network deep learning and prediction. We use available network Key Performance Indicators (KPIs) to train our system to analyze incoming traffic and predict the network slice for an unknown device type. Intelligent resource allocation allows us to use the available resources on existing network slices efficiently and offer load balancing. Our proposed model will be able to make smart decisions and select the most appropriate network slice, even in case of a network failure.

Secure5G: Network Slicing will play a vital role in enabling a multitude of 5G applications, use cases, and services. Network slicing functions will provide an end-to-end isolation between slices with an ability to customize each slice based on the service demands (bandwidth, coverage, security, latency, reliability, etc.). Maintaining isolation of resources, traffic flow, and network functions between the slices is critical in protecting the network infrastructure system from Distributed Denial of Service (DDoS) attack. The 5G network demands and new feature sets to support ever-growing and complex business requirements have made existing approaches to network security inadequate. In this paper, we have developed a Neural Network based Secure5G' Network Slicing model to proactively detect and eliminate threats based on incoming connections before they infest the 5G core network.Secure5G' is a resilient model that quarantines the threats ensuring end-to-end security from device(s) to the core network, and to any of the external networks. Our designed model will enable the network operators to sell network slicing as-a-service to serve diverse services efficiently over a single infrastructure with high security and reliability.

Tags: 5G Cellular Networks , Network Slicing , Machine Learning , Deep Learning Neural Networks , Network Slicing Optimization , Survivability of Network Functions, 5G mobile communication , cellular radio , cloud computing , decision making , learning (artificial intelligence) , mobile computing , quality of service , resource allocation , telecommunication network reliability , telecommunication traffic , virtualization, 5G NR , Network Slicing , 5G Security , Deep Learning , Neural Networks , DDoS , IoT , Flooding , Internet Security , Network Security , Botnets , Malware , mm-Wave , Cyber-attack, 5G mobile communication , computer network security , learning (artificial intelligence) , neural nets , telecommunication network reliability , telecommunication traffic