Samsung Project – Big Data Based Remaining Driving Range Estimation


The amount of data collected in Electric Vehicles has been growing fast because we have many more sensors, higher bandwidth communication systems, and cheaper memory to monitor and measure real-time driving range related data and store the data on the vehicles, in connected clouds, etc. This massive amount of data can have different levels of accuracy, resolutions, and relevance in unstructured ways. Big Data technologies have been emerging to address huge, diverse and unstructured data to substantially improve the overall system performance. With proper use of Big Data concepts and techniques, the remaining driving range estimation of the vehicle can be substantially improved.

The range estimation needs the incorporation and synchronization of all standard, real-time and historical data. Usually, the standard and historical data provides an initial prediction of the driving range; and the real-time data updates the estimation during the driving. However, under different conditions, some data are more relevant than others for the range estimation. This data can be historical, standard, or real-time depending on different situations. The big data analytics helps us identify the relevant data and discover its correlation to the remaining driving range estimation.



[1] H. Rahimi-Eichi and M.-Y. Chow, “Big-Data Framework for Electric Vehicle Range Estimation,”  presented at the 40th Annual Conference of the IEEE Industrial Electronics Society (IECON2014), IEEE, Dallas, TX , 2014.

[2] Z. Cheng, M. Chow, D. Jung and J. Jeon, “A big data based deep learning approach for vehicle speed prediction,” 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE), Edinburgh, 2017, pp. 389-394, doi: 10.1109/ISIE.2017.8001278.

[3] D. Jung, M. Chow, Z. Cheng, and J. Jeon, “Method and apparatus for estimating driving information,“US10215579B2, 2019.


First Principle Based Four Dimensional Battery Degradation Model (4DM)

The First Principle Based Four Dimensional Battery Degradation Model (4DM) is computer simulation model for battery dynamics studies under different degradation and operating conditions. The 4DM is designed based on the physics of operation of the battery, i.e., the actual components such as anode, cathode, electrolyte, separator and current collector, are used to construct the model. This particular approach is used to bridge the gap between material science, electrochemical and electrical engineering.

The 4DM, because of the design, is capable of simulating:

  • different battery chemistries,
  • batteries of different capacities,
  • progressive component degradation,
  • different operating conditions – C-rates, temperatures, depth of discharge, partial charging and discharging effects,
  • component degradation over time.

The 4DM provides a platform to study the sensitivity of the battery’s rate of change of voltage and capacity with respect to the degradation of different physical and electrochemical components. This feature/capability of the 4DM enables users to better understand the impact of different operating conditions on the degradation of their battery and determine appropriate use cases for their batteries to prolong the remaining useful life.

The 4DM has an intuitive user-interface that assists the user to perform different tests on the model under different operating conditions. The user interface is designed to be simple, yet intuitive and capable of providing the user with sufficient options to understand the working of the 4DM with access to the core back-end tool with all the features.


Co-Estimation Algorithm



Real-time estimation of the state of charge (SOC) of the battery is a crucial need in the growing fields of plug-in hybrid electric vehicles and smart grid applications. The SOC estimation accuracy depends on the accuracy of the model used to describe the characteristics of the battery. To accurately estimate the SOC of the battery, a Co-Estimation algorithm is proposed. The Co-Estimation algorithm is developed based on a resistance–capacitance (RC)-equivalent circuit model to model the battery dynamics. Considering the parameters of the battery model are functions of the SOC, C-rate, temperature, and aging, the Co-Estimation algorithm adopts an adaptive online parameter-identification algorithm to identify and update the model’s parameters as they change. We also deployed a piecewise linearized mapping of the VOC–SOC curve along with continuously updating the parameters to accurately represent all of the battery’s static and dynamic characteristics. Using this adaptive structure, we design an observer based on the updating model to estimate the SOC as one of the states of the battery model.