Zhejiang Tower & Huawei's Smart Peak Shifting Practice Selected as GSMA's Global Excellent Case

With the deployment of 5G, the power consumption and number of base stations have increased significantly, and the OPEX of operators has increased significantly. In order to help operators reduce the OPEX of base stations, Zhejiang Tower and Huawei have jointly innovated and introduced AI technology to achieve intelligent peak shifting of base stations. Under the premise of ensuring reliable backup power, each station saves 17.1% of electricity costs each year. Due to the significant effect of saving electricity costs, on July 26, 2021, this innovative practice was successfully selected as a 2021 global boutique case by GSMA (Global System for Mobile Communications Association).

In order to improve the efficiency of power resource utilization, the current power sector has formulated peak-valley time-of-use electricity prices (i.e., different electricity prices in different time periods) based on the changes in grid load to encourage users to reasonably arrange their electricity usage time and fill the valley with peaks. Traditional base station batteries are only used for emergency backup power during power outages and have not become a production tool for base station operations, resulting in a waste of silent energy storage assets. In response to the peak-valley electricity price scenario, Zhejiang Tower and Huawei have launched base station intelligent peak shifting technology to improve battery utilization and save electricity costs. The specific principle is to charge the battery during the valley electricity price period and discharge the battery during the peak electricity price period instead of supplying electricity from the mains. Intelligent peak shifting can reduce electricity costs and balance the grid load, which has significant economic and social benefits.

                                                                                      Peak and valley electricity price data in Zhejiang Province

Challenges in applying peak-load electricity consumption technology

The primary function of base station batteries is to provide backup power. Therefore, the battery still needs to meet the backup power requirements after peak load shifting. The peak load strategy needs to be accurately calculated to ensure the reliability of backup power and maximize benefits. The battery backup time is affected by multiple factors such as load power, battery SOC, and battery age. The load power, battery capacity, and health status of different sites vary greatly and are constantly changing. Manual analysis and calculation cannot formulate an accurate peak load shifting strategy (battery charging and discharging time and discharge depth). If a fixed peak load shifting model is used, some sites will have insufficient backup power due to over-discharge of the battery, and some sites will have limited benefits due to too low a battery discharge depth.

Intelligent peak shifting principle

To solve the above problems, Huawei applies AI technology to peak-shifting electricity consumption to formulate the optimal peak-shifting strategy. Huawei's energy management system uses AI to build a mains model, load power model, and battery capacity model. AI predicts load power, calculates the required backup capacity based on the backup time requirements of each station, and reserves the required backup capacity. It uses redundant battery capacity to shift the peak, and implements dynamic peak shifting with one strategy for each station and one strategy for each time. Huawei's intelligent peak shifting reserves sufficient backup capacity, so reliability is fully guaranteed, and it can maximize the peak shifting depth of each station to maximize benefits.

Value analysis: Intelligent peak shifting saves 17.1% of base station electricity costs per station per year

Zhejiang Tower has used intelligent peak shifting for one year, with an average annual income of 1,784 yuan per station, and a 17.1% electricity bill saving per station, with significant economic benefits. Intelligent peak shifting helps Zhejiang Tower activate the value of silent battery assets, using backup batteries to discharge during peak electricity price periods to save electricity bills. During the use of intelligent peak shifting, there is no risk of station downtime, and the reliability of backup power is effectively guaranteed.

                                                                                         Management system intelligent peak shifting interface

According to the analysis of load power data, the AI ​​load power prediction accuracy is very high, thus ensuring the reliability of backup power. At sites with small load fluctuations such as welfare homes, the average error of AI load power prediction is 1.1%. At the same time, the balance between energy-saving benefits and reliability is achieved through optimal charging and discharging strategies, and intermittent discharge is automatically selected to control battery temperature rise and extend battery life. At sites with large load power fluctuations at highway intersections, a high dynamic prediction accuracy can be achieved, with an average error of 5.7%.

Intelligent peak shifting achieves optimal dispatching of comprehensive energy for base stations by integrating digital technology and power electronics technology, optimizing energy utilization and saving electricity costs. Against the backdrop of the dual carbon goals, this innovative practice provides an important technical and commercial demonstration for cost reduction, efficiency improvement and energy transformation in the communications industry, which is of great significance.

Note: GSMA, the full name of the Global System for Mobile Communications Association, is an industry organization in the global mobile communications field. It brings together more than 750 operators and nearly 400 companies around the world. It is also the organizer of the Mobile World Congress and the Mobile Asia Expo.