To reduce the emission of greenhouse gas, the automotive industry has been turning to electric vehicles (EVs), and governments around the world are also planning to ban the sales of gasoline cars to speed up the switch to electric vehicles. With the increasing number of electric vehicles, the need for EV charging stations is going to rise. As recently at the Detroit Auto show, United States President Biden announced the approval of the first $900 million in funds for electric vehicle charging stations in 35 states in the country.
As electric vehicles hold the key to clean transport and low-carbon electricity, the EV charging stations must be smart to optimize energy consumption and increase charging efficiencies. With the IoT and AI implementations, the electric vehicles, the charger, the charge point operator’s cloud-based management platform, and the grid are connected. Every aspect of charging station usage such as charging volume, speed, peak time, energy costs, etc. can be tracked and furtherly analyzed to optimize the whole efficiency and management.
To manage the charging and optimize energy efficiency, the deployment of AI and collecting data are to raise the demand for the gateway to a much higher level. The powerful gateway collecting the data not only allows the operators to monitor and manage the overall usage, but it can also run artificial inference (AI) to optimize this energy revolution.
Keeping the battery healthy and having a longer life cycle
The battery life span is one of the most important concerns of electric vehicle drivers and potential owners. Just like cell phones, the state of the health of batteries dies out over time. And it is very costly to replace a new battery. Thus, keeping the battery healthy and prolonging the life cycle as much as possible are crucial tasks. In this case, AI can give a hand.
Deploying a gateway at the edge can collect the charging pattern data of drivers via charging stations and it can be uploaded to the cloud for further AI-driven analysis and diagnosis. As the AI algorithm perceives the charging history of the car and the status of the battery from the Battery Management System (BMS), smart charging can show a reminder and suggestion for drivers to choose a suitable charging speed or set it to stop charging at a certain power percentage to protect the battery life. Moreover, getting insight into the weekly or monthly driving distance can lead to suggested charging volume to avoid overcharging.
To aggregate, process, and filter the data from various sources for faster analysis in the next phase, Axiomtek recommends the gateway, ICO330. To monitor the status of the energy storage systems, charging stations, and smart meter, the ICO330 with Intel Atom® x6212RE or x6414RE processor (Elkhart Lake) possesses the advantage of abundant I/O including six isolated COM ports and three isolated 2.5G LAN ports. The isolation design protects the gateway from electromagnetic interference to secure the data transmission.
Floating price according to time and location
By obtaining insight into the charging patterns such as the charging duration of countless drivers, accordingly, the charging service provider can set floating prices based on the number of vehicles, locations, and times by the AI algorithm. In hot spots and hours, the increase in price can decrease the coming drivers and lessen the power load; in other words, it encourages drivers to go charging at the time that is best for their schedule on the day.
To deploy AI for advanced AI analysis of large amounts of data received from charging stations, Axiomtek recommends the high-performance DIN-rail embedded system, the upcoming ICO520. The system features the 12th Gen Intel® Core™ i7-1265UE processor (Alder Lake-P) with integrated Intel® Iris® Xe Graphics which features low-power architecture for multitasking and the Intel® Deep Learning Boost-powered AI engine means less waiting. To smoothly transfer data to the cloud and control center, it provides five antenna holes and a full-size PCI Express Mini Card slot for Wi-Fi or 4G LTE module. Plus, the M.2 slot can enable a faster 5G connection for data transmission.
However, considering cyberattack is a threat to the application domain, users can add one more cybersecurity gateway to ensure safety. The iNA100 featuring Intel Atom® x5-E3930/E3940 processor (Apollo Lake) can be deployed as a firewall. It provides four GbE LAN ports for connection to other gateways and one pair of LAN bypass is built-in to prevent a single point of failure and traffic overloading It also supports Wi-Fi, 3G and 4G/LTE.
DIN-rail Fanless Embedded System with Intel Atom® x6212RE or x6414RE Processor, 3 LAN, Isolated COM and DIO
DIN-rail Fanless Embedded System with 12th Gen Intel® Core™ i7/i5/i3 & Celeron® Processor, 4 LAN, 1 HDMI, 1 DisplayPort, Isolated COM and DIO
DIN-rail Fanless Embedded System with Intel® Celeron® Processor N3350, COM/CAN/DIO, 2 LAN, and 2 USB
Plate identification for charging space whitelist and payment
With the increase in electric vehicles and charging stations, in urban areas, parking lot spaces are still limited. Lamentably, some spaces with chargers sometimes get occupied by gasoline cars that do not need charging. Nevertheless, with AI deep learning to denoise the images, charging stations will be able to identify the plate numbers precisely under any weather conditions in the whitelist. Therefore, as the registered electric vehicles arrive, the ground barrier will unlock automatically to allow the vehicles to enter the charging space. What’s more, now that cashless payment becomes more common than ever, the payment can bind with the plate number to make the whole charging process more convenient and faster.
In this application, Axiomtek recommends the super lightweight, cost-effective, fanless DIN-Rail gateway, the ICO120-E3350. Based on Intel® Celeron® processor N3350, as a low-power system that is lighter than 500 grams, it provides just enough I/O like two GbE LAN ports and two USB 2.0 for cameras to identify the plate numbers. Besides, users can choose from COM, CAN, and DIO for other peripherals and controlling ground barriers. To be installed outdoors, its operation temperature ranges from -40°C to +70°C. An extension module that provides COM, CAN, LAN, and DIO can be added to the ICO120-E3350 to maximize its workloads and connectivity. The ICO120-E3550 is certified by Microsoft Azure, which ensures its cloud compatibility and is open to more analytical services.
Considering the remote deployment location of the system, Axiomtek’s Out-of-band (OOB) module allows operators to monitor the status of the system to save labor force and time for on-site maintenance; if the system freezes, it can be remotely turned on through OOB. Since the system deployed in the field rely on solar power, power saving is another crucial issue. The system can turn to sleep mode via OOB to minimize power consumption and turns on again when it is necessary. In terms of software, with the services from our Cloud Service Partner, Allxon, the software of the system can be updated remotely, accomplishing predictive maintenance and remote management.