2nd International Workshop on Artificial Intelligence Applications in Internet of Things & 1st International Workshop on Ubiquitous Electric Internet of Things

Session AI2OT-S1

AI2OT & UEIoT Session 1

10:00 AM — 11:40 AM JST
Dec 16 Wed, 8:00 PM — 9:40 PM EST

ECDT: Exploiting Correlation Diversity for Knowledge Transfer in Partial Domain Adaptation

Shichang He (Hunan University, China); Xuan Liu (Hunan University and Tsinghua University, China); Xinning Chen, Ying Huang (Hunan University, China)

Domain adaptation aims to transfer knowledge
across different domains and bridge the gap between them.
While traditional knowledge transfer considers identical domain,
a more realistic scenario is to transfer from a larger and
more diverse source domain to a smaller target domain, which
is referred to as partial domain adaptation (PDA). However,
matching the whole source domain to the target domain for
PDA might produce negative transfer. Samples in the shared
classes should be carefully selected to mitigate negative transfer
in PDA. We observe that the correlations between different
target domain samples and source domain samples are diverse:
classes are not equally correlated and moreover, different samples
have different correlation strengthes even when they are in the
same class. In this study, we propose ECDT, a novel PDA
method that Exploits the Correlation Diversity for knowledge
Transfer between different domains. We propose a novel method
to estimate target domain label space that utilizes the label
distribution and feature distribution of target samples, based
on which outlier source classes can be filtered out and their
negative effects on transfer can be mitigated. Moreover, ECDT
combines class-level correlation and instance-level correlation
to quantify sample-level transferability in domain adversarial
network. Experimental results on three commonly used crossdomain
object data sets show that ECDT is superior to previous
partial domain adaptation methods.

Study on Location and Sizing Programming of Regional Substation

Xiaolin Tan, Shiyao Hu, Chunguang He, Pengfei Sun (State Grid Hebei Electric Power Co.,Ltd., Institute of Economics and Technology, China); Jing Zhang (State Grid Jinzhou Power Supply Company, China); Ying Ma (Xiamen University of Technology, China)

This paper proposes a research method for the location
and capacity planning of regional substations. This method
mainly studies and analyzes the active distribution network space
based on load forecasting to complete the location and capacity
analysis of regional substations. Combining the GIS information
system and the power sensor network, based on the spatial load
prediction results, and combined with the regional distributed
power planning results, the location and capacity planning of
the regional substations are carried out, and finally based on
the location selection and capacity results, the power supply
range of the substation and Economic calculation indicators
have formed a set of technologically advanced, comprehensive
and practical planning schemes, which can not only meet the
needs of the distribution network at all levels in Xiongan New
District for substation location and capacity, but also can be
extended to urban areas of six cities, such as A, It is used
in Class B areas to provide data support and scientific basis
for the location and capacity of substations in the power grid,
realize accurate planning, and assist relevant technical personnel
in making decisions.

A Method to Construct Vulnerability Knowledge Graph based on Heterogeneous Data

Yizhen Sun (State Grid Information & Communication Company of Hunan Electric Power Corporation, China); Dandan Lin, Hong Song (Central South University, China); Minjia Yan, Linjing Cao (State Grid Information & Communication Company of Hunan Electric Power Corporation, China)

In recent years, there are more and more attacks and exploitation aiming at network security vulnerabilities. It is effective for us to prevent criminals from exploiting vulnerabilities for attacks and help security analysts maintain equipment security that knows vulnerabilities and threats on time. With the knowledge graph, we can organize, manage, and utilize the massive information effectively in cyberspace. In this paper we construct the vulnerability ontology after analyzing multi-source heterogeneous databases. And the vulnerability knowledge graph is established. Experimental results show that the accuracy of entity recognition for extracting vendor names reaches 89.76%. The more rules used in entity recognition, the higher the accuracy and the lower the error rate.

WSAD: An Unsupervised Web Session Anomaly Detection Method

Yizhen Sun (State Grid Information & Communication Company of Hunan Electric Power Corporation, China); Yiman Xie, Weiping Wang, Shigeng Zhang (Central South University, China); Jun Gao, Yating Chen (State Grid Information & Communication Company of Hunan Electric Power Corporation, China)

Web servers in the Internet are vulnerable to Web
attacks, to detect Web attacks, a commonly used method is to
detect anomalies in the request parameters by making regularexpression-
based matching rules for the parameters based on
known security threats. However, such methods cannot detect
unknown anomalies well and they can also be easily bypassed
by using techniques like transcoding. Moreover, existing anomaly
detection methods are usually based on a single HTTP request,
which is easy to ignore the attack behavior within a period of
time, such as brute-force password cracking attack. In this paper,
we propose an unsupervised Web Session Anomaly Detection
method called WSAD. WSAD uses ten features of web session
to perform anomaly detection. After extracting the ten features,
WSAD uses the DBSCAN algorithm to cluster the features of
each session and outputs the outliers found in the clustering
process as anomalies. We evaluate the performance of WSAD on
several datasets from multiple real websites of a company. The
results indicate that WSAD could detect malicious behaviors that
could not be detected by Web Application Firewall, and it almost
has no false positives.

Researches on Intelligent Traffic Signal Control Based on Deep Reinforcement Learning

Juan Luo, Xinyu Li, Yanliu Zheng (Hunan University, China)

The rapidly growing traffic flow exceeds the capa-city of the existing infrastructure. It will cause traffic congestion and increase travel time and carbon emissions. Intelligent traffic signal control is a significant element in intelligent transportation system. In order to improve the efficiency of intelligent traffic signal control, the traffic information needs to be collected and processed in real-time. In this paper, we propose a deep reinforcement learning model for traffic signal control. In this model, intersections are divided into several grids of different sizes, which represents the complex traffic state. The switching of traffic signals are defined as actions, and the weighted sum of various indicators reflecting traffic conditions is defined as rewards. The whole process is modeled as Markov Decision Process (MDP), and Convolutional Neural Network (CNN) is used to map the states to rewards. We evaluated the efficiency of the model through Simulation of Urban Mobility (SUMO), and the simulation results proved the efficiency of the model.

Session Chair

Shigeng Zhang (Central South University, China)

Enter Zoom
Session AI2OT-S2

AI2OT & UEIoT Session 2

1:00 PM — 2:40 PM JST
Dec 16 Wed, 11:00 PM — 12:40 AM EST

Research on load forecasting model on power sensor net

Kai Huang (State Grid Hebei Electric Power Co.,Ltd., Institute of Economics and Technology, China), Jing Zhang (State Grid Jinzhou Power Supply Company, China), Jiakun An, Jing Zhang, Jinglin Han (State Grid Hebei Electric Power Co.,Ltd., Institute of Economics and Technology, China); Yunjie Lei ( Xiamen University of Technology, China)

The business process of load forecasting algorithm
for distribution network planning is studied in depth, and the
work steps of load forecasting in different places are discussed
according to different planning objectives. Then, based on power
sensor net, we systematically describes various power demand
forecasting models and related theories, as well as their respective
application scenarios. Finally, on the basis of theoretical research,
relevant experiments are carried out, and the economic benefits
of load forecasting are analyzed and discussed by using reliability
evaluation method.

Privacy-Preserving Techniques for Protecting Large-Scale Data of Cyber-Physical Systems

Marwa Keshk (University of New South Wales, Canberra and Data61-CSIRO, Australia); Nour Moustafa, Elena Sitnikova, Benjamin Turnbull (University of New South Wales, Canberra, Australia); Dinusha Vatsalan (Data61-CSIRO, Australia)

As Cyber-Physical Systems (CPSs), such as power
and gas networks, generate heterogeneous and large-scale data
sources from devices and networks, they need efficient privacypreserving
techniques to protect data and systems from cyber
attacks. To safeguard CPSs from potential cyber threats, it is
vital to identify vulnerabilities of CPSs’ components to prevent
Advanced Persistent Threats (APTs) and protect their generated
data using privacy-preserving techniques. This paper aims to
review the current state of privacy-preserving techniques for
protecting CPSs and their networks against cyber attacks.
Concepts of Privacy preservation and CPSs are discussed, illustrating
CPSs’ components and how they could be hacked using
cyber and physical hacking scenarios. Then, types of privacy
preservation, including perturbation, authentication, machine
learning (ML), cryptography and blockchain, are discussed to
demonstrate how they would be applied to protect the original
data in CPSs and their networks. Finally, we explain existing
challenges, solutions and future research directions of privacy
preservation in CPSs.

Improving Analysis of Automatic Distribution Changes for Power Grid

Meile Shi, Zhen Wang, Pengfei Yu (Xiamen Great Power GeoInformation Technology Co., Ltd, China); Qi Du (Xiamen University of Technology, China)

In view of the actual demand of power supply enterprises
for the construction of distribution network, it is necessary
to integrate the two kinds of business, namely the abnormal
operation of distribution network equipment and the operation
and monitoring of distribution network, through the integration
of power network sensor network and other technologies, the
operation and distribution data and the integration of “big
data” technology to carry out integrated management of the
entire distribution network dispatching and production business.
Based on PMS2.5 and GIS2.0, we propose a new scheme to
analyse distribution changes for power grid, with the help of
the parameter comparison analysis, the mutual authentication
between the two systems construction of distribution network
equipment move detection function. It can realize electricity
information area over, demolition, shut down the usage scenarios
and system parameter changes between the data management, at
the same time auxiliary by automatic matching method, improved
the camp with penetration data accuracy.

Coding based Distributed Data Shuffling for Low Communication Cost in Data Center Networks

Junpeng Liang, Lei Yang, Zhenyu Wang, Xuxun Liu (South China University of Technology, China); Weigang Wu (Sun Yat-sen University, China)

Data shuffling can improve the statistical performance
of distributed machine learning. However, the obstruction
of applying data shuffling is the high communication
cost. Existing works use coding technology to reduce communication
cost. These works assume a master-worker based
storage architecture. However, due to the demand for unlimited
storage on the master, the master-worker storage architecture
is not always practical in common data centers. In this paper,
we propose a new coding method for data shuffling in the
decentralized storage architecture, which is built on a fat-tree
based data center network. The method determines which data
samples should be encoded together and from which the encoded
package should be sent to minimize the communication
cost. We develop a real-world test-bed to evaluate our method.
The results show that our method can reduce the transmission
time by 6.4% over the state-of-art coding method, and by
27.8% over Unicasting.

Research on visualization planning method of distribution network based on graphical model integration

He Huang (State Grid Jiangsu Electric Power Co., Ltd., China); Xian Zhou, Liang Guo, Hao Chang, Ning Ma (State Grid Taizhou Power Supply Company, China)

High efficient video coding (HEVC) is a new video
coding compression standard. HEVC adopts context-based adaptive
binary arithmetic coding (CABAC) as the entropy coding
scheme.In this paper, the overall architecture and efficiency
of the main frequency are improved by the optimization of
the input and output modules and the module optimization of
the arithmetic coding CABAC hardware structure. In terms of
input module optimization, four-level buffer input and residual
coefficient transmission optimization are adopted; in terms of
arithmetic coding module optimization, context model index
pre-reading, pre-normalization look-up table and in-line serial
stream output design are adopted so as to improve the overall
efficiency of the architecture and the main frequency, reduce
resource consumption, and achieve a high-frequency hardware
architecture of the efficient coding pipeline. The combined results
show that the pipeline can operate at 370MHz with 43.49K gates
aiming at 90nm process. The processing rate and throughput can
support real-time encoding of 1080P video under the general test
conditions of the HEVC standard of 30 frames per second.

Session Chair

Ying Ma (Xiamen University of Technology, China)

Enter Zoom

Made with in Toronto · Privacy Policy · © 2020 Duetone Corp.