Danyang Li

Dr. Danyang Li

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 July 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
DLDanyang Li
Danyang Li
YZYuqi Zhang
Yuqi Zhang
JSJie Song
Jie Song
HLHui Liu
Hui Liu
JJJingqing Jiang
Jingqing Jiang
Data centers with high energy consumption have become a threat to urban sustainability on electric energy. In contrast, hot spots in a data center are another threat to server stability, which leads to unsafe data storage and service provisioning to urban lives. However, state-of-the-art works cannot ensure sustainability and stability together because they fail to consider them holistically. For example, some existing works eliminate the hot spots by increasing cooling power, which results in lower sustainability. In contrast, others reduce energy consumption by saving the cooling power, which harms stability. Therefore, to balance the hot spot elimination and energy saving through power control remains challenging, this paper proposes a novel power control approach for energy saving with zero hot spots in data centers. Power control works when hot spots appear, or consumed energy is excess. Specifically, we formulated a total consumption minimization problem to characterize and analyze the optimal set points for power control, where the number of hot spots is zero and the energy consumption is low. Adding the interactional penalty models can determine the power control approach when the objective function obtains the optimal solution. We propose a Modified Differential Evolution algorithm (MDE) to solve the function quickly and accurately. It adopts adaptive parameters to reduce the computing time. Meanwhile, it avoids optimal local solutions by changing mutation operations. Further, simulation experiments using our optimal solution demonstrate that energy consumption saves about 13% on average with zero hot spots, compared with three typical approaches.

15 June 2023 in Symmetry
Verified
Journal Article
Open access
PDF file
CSChenxi Sun
Chenxi Sun
DLDanyang Li
Danyang Li
BWBeilei Wang
Beilei Wang
JSJie Song
Jie Song
With the enhanced interoperability of information among vehicles, the demand for collaborative sharing among vehicles increases. Based on blockchain, the classical consensus algorithms in collaborative IoV (Internet of Vehicle), such as PoW (Proof of Work), PoS (Proof of Stake), and DPoS (Delegated Proof of Stake), only consider the node features, which is hard to adapt to the immediacy and flexibility of vehicles. On the other hand, classical consensus algorithms often require mass computing, which undoubtedly increases the communication overhead, resulting in the inability to achieve collaborative IoV under asymmetric networks. Therefore, proposing a low failure rate consensus algorithm that takes into account running time and energy consumption becomes a major challenge in IoV applications. This paper proposes an AI-enabled consensus algorithm with vehicle features, combining vehicle-based metrics and neural networks. First, we introduce vehicle-based metrics such as vehicle online time, performance, and behavior. Then, we propose an integral model and a hierarchical classification method, which combine with a BP neural network to obtain the optimal solution for interconnection. Among them, we also use Informer to predict the future online duration of vehicles, which effectively solves the situation that the primary node vehicle drops off in collaborative IoV. Finally, the experimentations show that the vehicle-based metrics eliminate the problem of the primary node vehicle being offline, which realizes the collaborative IoV considering vehicle features. Meanwhile, it reduces the vehicle network system delay and energy consumption.

11 November 2024 in Energies
Verified
Journal Article
Open access
PDF file
DLDanyang Li
Danyang Li
JSJie Song
Jie Song
HLHui Liu
Hui Liu
JJJingqing Jiang
Jingqing Jiang
This paper aims to help data center administrators choose thermal simulation tools, which manage thermal conduction from power for energy savings. When evaluating and suggesting data center thermal simulators for users, questions such as “What are the simulator’s differences? Are they easy to use? Which is the best choice?” are frequently asked. To answer these questions, this paper reviews the thermal simulation works for data centers in the last ten years. After that, it proposes the versatility and dexterity metrics for these simulators and discovers that it is difficult to choose them despite their similar design purpose and functions. Empowered by the survey, we claim that the widespread practice simulators still need more enhancement in data center scenarios. We back up our claim by comparing typical simulators and propose improvements to thermal simulators for future studies.

13 April 2026 in Processes
Verified
Journal Article
Open access
PDF file
DLDanyang Li
Danyang Li
JSJie Song
Jie Song
HLHui Liu
Hui Liu
With the rise of computer-related fields, data centers have become essential infrastructure. Thermal analysis helps to improve data center performance and reduce data center energy consumption. Due to the variable load, the scheduling of the data center is frequent, and the thermal state also changes frequently. However, existing thermal analysis methods have a high cost regarding mesh division and thermal calculation and cannot provide dynamic thermal simulation for data centers. To address this challenge, this paper proposes a cost-compensated spatial–temporal meshing method for transient thermal simulation (TranSim) of the data center. TranSim adaptively adjusts the mesh boundaries according to the workload gradient of a location, and it can adaptively adjust the meshing step time according to the workload change frequency in order to achieve transient simulation. Cost-compensated thermal calculation replaces the CFD model, considering air flow, by adding the thermal source, thermal medium, thermal radiation and thermal lagging in order to gain a simple thermal calculation. This paper designs an experiment for comparing TranSim with several popular data center thermal simulation methods, such as a structured mesh with a CFD model, regarding their transient effect, time cost, and error cost. The results show that TranSim has a good transient effect, low error cost (the simulation error decreases by 13.5% compared with the average error) and low time cost (the simulation time is only about 7% that of the most accurate data center thermal simulation method).

14 May 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
DLDanyang Li
Danyang Li
JSJie Song
Jie Song
HLHui Liu
Hui Liu
JJJingqing Jiang
Jingqing Jiang
With the in-depth research of data centers, the task scheduling for sustainable data centers has garnered significant attention. Since thermal dissipation power occupies half of the energy consumption of a whole data center, a large number of sustainable data centers use Thermal-Aware Task Scheduling (TATS). However, existing approaches struggle to perform well in TATS, by ignoring the dynamic characteristics of the thermal in sustainable data centers, which is highly related to the temporal and spatial relationship between servers. It might cause inaccurate scheduling timing and poor scheduling locations, which will lead to additional scheduling costs and cooling costs. To address this problem, we propose a dynamic TATS with GNN-based deep reinforcement learning (DRLGTS) for sustainable data centers. Specifically, DRLGTS first evenly distributes the tasks according to the spatial positions of servers in data center, which is the preprocessing step of DRLGTS. Then, by calling the TranSimmethod, a dynamic thermal graph generation method based on thermal transient simulation in the entire task execution process is conducted. The thermal graph generated by TranSim represents the operating status of the servers and the temporal and spatial correlations between the servers as a graph layout. Finally, based on the feature extraction of thermal graphs using GNN, the proposed dynamic thermal-aware task scheduling using deep reinforcement learning (DRL) is executed. DRLGTS minimizes the energy consumption cost and time cost while scheduling task to adjacent servers as much as possible. Experimental results show that this architecture has good effectiveness and dynamic adaptability.