IP Library › Granted Patent US 12,488,257
Granted Patent B2
US 12,488,257 · App. 17/726,182 · Granted Dec 2, 2025

System and method for reduction of data transmission in dynamic systems

Inventors: Ofir Ezrielev (Be'er Sheva, IL); Jehuda Shemer (Kfar Saba, IL)
Assignee: Dell Products L.P.
G06N5/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,488,257
App. No.
17/726,182
Granted
Dec 2, 2025
Kind
B2
Abstract

Methods and systems for managing data collection in a distributed system are disclosed. To manage data collection, the system may include a data aggregator and a data collector. The data aggregator and may utilize an inference model to predict data based on future measurements performed by data collectors throughout a distributed system without having access to the measurements. The data collectors may be mobile, and the data aggregator may direct the data collectors to various locations. To select paths for the data collectors to follow, the aggregator may utilize the level of uncertainty in predictions, the sensitivities in ranges of data to downstream consumers of the data collected by the data collectors, and/or other types of information. The data aggregator may select the paths for varying goals over time.

Claims (65)

1 . A method for managing data collection in a distributed system where data is collected in a data aggregator of the distributed system and from a data collector of the distributed system that is operably connected to the data aggregator via a communication system, the method comprising:

identifying, by the data aggregator, a path selection event for the data collector;

obtaining, by the data aggregator and in response to the path selection event, prediction uncertainty levels for multiple paths available to the data collector;

selecting, by the data aggregator, a path of the multiple paths based on the prediction uncertainty levels for the multiple paths;

directing, by the data aggregator, the data collector along the path;

obtaining, by the data aggregator and using an inference model, predictions of data obtained by the data as the data collector traverses the path;

obtaining, by the data aggregator, a portion of the data from the data collector as it traverses the path;

aggregating, by the data aggregator, the portion of the data and a portion of the predictions to obtain validated data; and

initiating, by the data aggregator and based on the validated data, performance of one or more actions to manage operation of the distributed system.

2 . The method of claim 1 , wherein obtaining the portion of the data comprises:

obtaining, by the data aggregator and from the data collector, a reduced size representation of a sub-portion of the portion of the data; and

reconstructing, by the data aggregator, the sub-portion of the portion of the data using the reduced size representation and a prediction of the predictions corresponding to the sub-portion of the portion of the data.

3 . The method of claim 2 , wherein the reduced size representation comprises a difference between a collector prediction that is identical to the prediction and the sub-portion of the portion of the data.

4 . The method of claim 2 , wherein the reduced size representation comprises a statistic derived from a plurality of the sub-portion of the portion of the data obtained by the data collector.

5 . The method of claim 1 , wherein obtaining the prediction uncertainty levels for the multiple paths comprises:

for the path of the multiple paths:

obtaining prediction uncertainties from the inference model for points along the path; and

using, at least in part, the prediction uncertainties associated with the points to obtain a prediction uncertainty level of the prediction uncertainty levels for the path.

6 . The method of claim 5 , wherein selecting the path comprises:

making a determination that the prediction uncertainty level is a highest prediction uncertainty level of the prediction uncertainty levels; and

selecting the path of the multiple paths based on the determination.

7 . The method of claim 6 , wherein each of the multiple paths is a possible path between a start location and a goal location for the data collector, and a duration of time for traversing each of the multiple paths is substantially similar.

8 . The method of claim 5 , wherein selecting the path comprises:

making a determination that the prediction uncertainty level is a lowest prediction uncertainty level of the prediction uncertainty levels; and

selecting the path of the multiple paths based on the determination.

9 . The method of claim 5 , wherein the prediction uncertainties for the points are used in a weighted average to obtain the prediction uncertainty level.

10 . The method of claim 1 , wherein a path of the multiple paths is selected additionally based on a sensitivity level of a consumer of the validated data.

11 . A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for managing data collection in a distributed system where data is collected in a data aggregator of the distributed system and from a data collector of the distributed system that is operably connected to the data aggregator via a communication system, the operations comprising:

identifying, by the data aggregator, a path selection event for the data collector;

obtaining, by the data aggregator and in response to the path selection event, prediction uncertainty levels for multiple paths available to the data collector;

selecting, by the data aggregator, a path of the multiple paths based on the prediction uncertainty levels for the multiple paths;

directing, by the data aggregator, the data collector along the path;

obtaining, by the data aggregator and using an inference model, predictions of data obtained by the data as the data collector traverses the path;

obtaining, by the data aggregator, a portion of the data from the data collector as it traverses the path;

aggregating, by the data aggregator, the portion of the data and a portion of the predictions to obtain validated data; and

initiating, by the data aggregator and based on the validated data, performance of one or more actions to manage operation of the distributed system.

12 . The non-transitory machine-readable medium of claim 11 , wherein obtaining the portion of the data comprises:

obtaining, by the data aggregator and from the data collector, a reduced size representation of a sub-portion of the portion of the data; and

reconstructing, by the data aggregator, the sub-portion of the portion of the data using the reduced size representation and a prediction of the predictions corresponding to the sub-portion of the portion of the data.

13 . The non-transitory machine-readable medium of claim 12 , wherein the reduced size representation comprises a difference between a collector prediction that is identical to the prediction and the sub-portion of the portion of the data.

14 . The non-transitory machine-readable medium of claim 12 , wherein the reduced size representation comprises a statistic derived from a plurality of the sub-portion of the portion of the data obtained by the data collector.

15 . The non-transitory machine-readable medium of claim 11 , wherein obtaining the prediction uncertainty levels for the multiple paths comprises:

for the path of the multiple paths:

obtaining prediction uncertainties from the inference model for points along the path; and

using, at least in part, the prediction uncertainties associated with the points to obtain a prediction uncertainty level of the prediction uncertainty levels for the path.

16 . A data aggregator, comprising:

a processor; and

a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations for managing data collection in a distributed system where data is collected in a data aggregator of the distributed system and from a data collector of the distributed system that is operably connected to the data aggregator via a communication system, the operations comprising:

identifying a path selection event for the data collector;

obtaining, in response to the path selection event, prediction uncertainty levels for multiple paths available to the data collector;

selecting a path of the multiple paths based on the prediction uncertainty levels for the multiple paths;

directing the data collector along the path;

obtaining, using an inference model, predictions of data obtained by the data as the data collector traverses the path;

obtaining a portion of the data from the data collector as it traverses the path;

aggregating the portion of the data and a portion of the predictions to obtain validated data; and

initiating, based on the validated data, performance of one or more actions to manage operation of the distributed system.

17 . The data aggregator of claim 16 , wherein obtaining the portion of the data comprises:

obtaining, by the data aggregator and from the data collector, a reduced size representation of a sub-portion of the portion of the data; and

reconstructing, by the data aggregator, the sub-portion of the portion of the data using the reduced size representation and a prediction of the predictions corresponding to the sub-portion of the portion of the data.

18 . The data aggregator of claim 17 , wherein the reduced size representation comprises a difference between a collector prediction that is identical to the prediction and the sub-portion of the portion of the data.

19 . The data aggregator of claim 17 , wherein the reduced size representation comprises a statistic derived from a plurality of the sub-portion of the portion of the data obtained by the data collector.

20 . The data aggregator of claim 16 , wherein obtaining the prediction uncertainty levels for the multiple paths comprises:

for the path of the multiple paths:

obtaining prediction uncertainties from the inference model for points along the path; and

using, at least in part, the prediction uncertainties associated with the points to obtain a prediction uncertainty level of the prediction uncertainty levels for the path.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 21, 2022
From: EZRIELEV, OFIR; SHEMER, JEHUDA
To: DELL PRODUCTS L.P.
Reel/Frame 059669/0758 →
Continuity (1)
Related Publication 20230342638A1 · Oct 26, 2023
References Cited (22)
US 11961598B1 · Finley · 2024 [cited by examiner]
US 20060167917A1 · Solomon · 2006 [cited by examiner]
US 20160026520A1 · Bouta et al. · 2016 [cited by applicant]
US 20190044786A1 · Wouhaybi et al. · 2019 [cited by applicant]
US 20210376853A1 · De et al. · 2021 [cited by applicant]
US 20220197306A1 · Cella · 2022 [cited by examiner]
Lewandowski, M.; Płaczek, B.; Bernas, M.; Classifier-Based Data Transmission Reduction in Wearable Sensor Network for Human Activity Monitoring. Sensors 2021, 21, 85. https://doi.org/10.3390/s21010085. [cited by applicant]
Le Borgne, Yann-Aäl & Santini, Silvia & Bontempi, Gianluca. (2007). Adaptive model selection for time series prediction in wireless sensor networks. Signal Processing. 87. 3010-3020. 10.1016/j.sigpro.2007.05.015. [cited by applicant]
Ankur Jain, Edward Y. Chang, Yuan-Fang Wang; Adaptive stream resource management using Kalman Filters. SIGMOD '04: Proceedings of the 2004 ACM SIGMOD international conference on Management of data Jun. 2004 pp. 11-22 ht… [cited by applicant]
X. Feng, X. Zhenzhen, Y. Lin, S. Weifeng and L. Mingchu, “Prediction-based data transmission for energy conservation in wireless body sensors,” 2010 The 5th Annual ICST Wireless Internet Conference (WICON), 2010, pp. 1-… [cited by applicant]
Tulone, Daniela & Madden, Samuel. (2006). An energy-efficient querying framework in sensor networks for detecting node similarities. 191-300. 10.1145/1164717.1164768. [cited by applicant]
Lu, Qing & Jiang, Weiwen & Xu, Xiaowei & Shi, Yiyu & Hu, Jingtong. (2019). On Neural Architecture Search for Resource-Constrained Hardware Platforms. [cited by applicant]
“Detecting data drift on data sets,” Web page <https://docs.microsoft.com/en-us/azure/machine-learning/how-to-monitor-datasets?tabs=python>, Nov. 10, 2021, retrieved from Internet Archive Wayback Machine <https://web.ar… [cited by applicant]
Pearl, Judea. “Causal inference in statistics: An overview.” Statistics surveys 3 (2009): 96-146. https://projecteuclid.org/journals/statistics-surveys/volume-3/issue-none/Causal-inference-in-statistics-An-overview/10.1… [cited by applicant]
Xie, Yaochen, et al. “Self-supervised learning of graph neural networks: A unified review.” IEEE Transactions on Pattern Analysis and Machine Intelligence (2022). https://ieeexplore.ieee.org/abstract/document/9764632/. [cited by applicant]
Kumar, Manoj, et al. “Genetic algorithm: Review and application.” Available at SSRN 3529843 (2010). https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3529843. [cited by applicant]
Lewandowski et al., “Classifier-Based Data Transmission Reduction in Wearable Sensor Network for Human Activity Monitoring”, Sensors 2021, 21, 85. <https://dx.doi.org/10.3390/s21010085>, Dec. 25, 2020, 22 pages (Year: 2… [cited by applicant]
Cui et al., “Classification of data aggregation functions in wireless sensor networks”, Computer Networks, vol. 178, 107342, <https://doi.org/10.1016/j.comnet.2020.107342>, 13 pages (Year: 2020). [cited by applicant]
Liazid et al., “An improved adaptive dual prediction scheme for reducing data transmission in wireless sensor networks”, Wireless Networks, 25:3545-3555, <https://doi.org/10.1007 /s11276-019-01950-7>, Feb. 2, 2019, 11 p… [cited by applicant]
Chen et al., “Online Model-Driven Data Acquisition for Wireless Sensor Networks”, 2015 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 2015, 6 pages (Year: 2015). [cited by applicant]
Zhang et al., “Lightweight Self-Adapting Linear Prediction Algorithms for Wireless Sensor Networks”, IEEE Sensors Journal, vol. 15, No. 5, May 2015, pp. 3050-3058 (Year: 2014). [cited by applicant]
Jain et al., “A Novel Data Prediction Technique Based on Correlation for Data Reduction in Sensor Networks”, Proceedings of International Conference on Artificial Intelligence and Applications: ICAIA 2020. Springer Sing… [cited by applicant]