Front End | News
Infovista unveils AI model for accelerated 5G roll-out
I
nfovista announced the availability of its Artificial Intelligence Model (AIM), a commercially available AI-based propagation model that changes the way wireless networks can be planned and optimised. “Operators are at different stages within the 5G rollout, but the majority are still faced with the massive task of selecting, testing and commissioning new sites,” said Régis Lerbour, VP product & R&D, RAN Engineering at Infovista. “Our
AI-based propagation model, successfully introduced to our customers at Infovista RAN Summit, is, by design, cloud-ready and scalable to increase agility and the ability to adapt the network more dynamically, thus offering a way to automate and accelerate the planning and roll-out of 5G networks.”
Infovista’s AIM has been built around state-
of-the-art machine learning frameworks such as TensorFlow to focus on training and inference of deep neural networks. The project utilised over 10 million data points collected by the company during the last 15 years and spans multiple sub- 6 GHz and millimetre wave bands, geographic locations, antenna heights, weather conditions, seasonal foliage variations and hundreds of additional variables – across urban, mixed and rural environments. The AI-model predictions have been extensively validated against real- world measurement sampling data and are proven to deliver network plans that are 25 per cent more accurate compared to those delivered using traditional propagation models. The initial
testing shows that this improved accuracy translates into up to 20 per cent CAPEX savings when it comes to radio site investments. AIM avoids labour-intensive and repetitive calibration and parameter manipulation. It fully fits with the Network Lifecycle Automation
Power Integrations incorporates lossless zero-cross detection and X-capacitor discharge
P
vision of Infovista that aims to expand the reach of automation beyond network and service operations, into planning, testing and deployment, and reporting and monetisation.
AIM is embedded into Infovista’s award-winning Planet software, which also includes an integrated feed of crowdsourced subscriber-centric data available in all geographies. Combining both provides mobile operators with higher accuracy and more efficient network planning workflows. “Over time the combination of AIM with crowdsourced data will mean the new platform will enable operators to fully automate network planning thus allowing them to deploy in new frequency bands faster than ever,” Régis Lerbour added. “Automated data collection and processing contribute to significantly reducing the cost of propagation model calibration and optimising drive testing, helping accelerate 5G deployments to new levels.”
ower Integrations announced LinkSwitch- TNZ, a new switching power supply IC that combines offline power
conversion, lossless zero-cross detection and, optionally, X-capacitor discharge functions in a compact SO-8C package. The highly efficient LinkSwitch-TNZ IC can be used for non-isolated buck and buck-boost power supplies up to 575 mA output current and provides up to 12 W output for universal-input isolated flyback designs. Adnaan Lokhandwala, product marketing manager at Power Integrations said: “The new LinkSwitch-TNZ ICs provide an accurate signal indicating that the sinusoidal AC line is at zero volts. This signal is used by smart home and building automation (HBA) products and appliances to control the switching of relays, IGBTs and TRIACs to minimize switching stress and system in-rush current. LinkSwitch-TNZ’s detection of the zero-cross point consumes less than 5 mW, allowing systems to reduce standby power losses versus alternative approaches that require ten or more discrete components and burn 50 to 100 mW of continuous power.”
Devices such as light switches, dimmers, sensors, and plugs connect and disconnect the AC line periodically using a relay or TRIAC. A discrete circuit is typically implemented to detect the AC line zero-crossing to control the turn-on transition of the main power device while reducing switching losses and in-rush current. This approach requires many components and is very lossy, consuming
Joint efforts for another leap in autonomous driving technology
E
ager to take self-driving reliability and accuracy to the next level, Sensible 4 and Panasonic Industry Europe announced a joint test project levering the synergies between Sensible 4’s proven self-driving software and the benefits of Panasonic Industry’s Inertial Measurement Unit (IMU).
The IMU plays an essential role in the sensor fusion process, which is more or less the fundament for driving autonomy by merging/synchronising the data with other sensors - such as, for instance, odometry, GNSS and lidar. “The IMU is employed to rectify the point cloud and thus impacts the accuracy of lidar data”, explained Fredrik Forssell
www.cieonline.co.uk
from Sensible 4. “Our software is expected to be ideally flexible and reliable to next-gen sensor hardware – and of course we are utterly excited to now commence this in depth- testing period with the 6 axis sensor from Panasonic Industry. We are curious about the outcomes, but strongly believe in groundbreaking insights on the alignment of soft- and hardware for autonomous driving.”
Specialists of both companies shortly will kick-off an extensive evaluation period with plenty of tests and analyses. “This project is a special one to all of us,” said Ryosuke Toda from product marketing at Panasonic Industry in Munich. “We are deeply interested in sending out our new sensor to
this freezing baptism by fire to Finland and learn more on its readiness to contribute to that new level of mobility that we all eagerly waiting for.”
Components in Electronics June 2021 7
almost half of the standby power budget in some cases. Similarly, appliances often use a discrete zero-cross detection circuit to control motor and MCU timing. These applications also require an auxiliary power supply for functions such as wireless connectivity, gate drivers, sensors and displays.
LinkSwitch-TNZ ICs provide best-in-class light-load efficiencies, enabling more system features to be powered while meeting stringent standby regulations such as: the European Commission (EC) standard for home appliances (1275), which requires equipment to consume no more than 0.5 W in standby or in off mode; ENERGY STAR’s version 1.1 for Smart Home Energy Management Systems (SHEMS), which limits standby consumption of smart lighting control devices to 0.5 W; and China’s GB24849, which limits the off-mode power consumption in microwave ovens to 0.5 W. LinkSwitch-TNZ ICs also reduce component count by 40 per cent or more when compared to discrete designs.
Optionally, an X-capacitor discharge function can also be included in the package for high power applications, leading to greater PCB space reduction, low BOM count and increased reliability (LNK331x).
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54
