Energy-efficient client selection in federated learning with heterogeneous data on edge

2022 ◽  
Author(s):  
Jianxin Zhao ◽  
Yanhao Feng ◽  
Xinyu Chang ◽  
Chi Harold Liu
Keyword(s):  
Energy Efficient ◽  
Heterogeneous Data

Energy-efficient Collaborative Sensing: Learning the Latent Correlations of Heterogeneous Sensors

2021 ◽  
Vol 17 (3) ◽  
pp. 1-28
Author(s):  
Yunji Liang ◽  
Xin Wang ◽  
Zhiwen Yu ◽  
Bin Guo ◽  
Xiaolong Zheng ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Low Power ◽  
Energy Efficient ◽  
Learning Strategy ◽  
Heterogeneous Data ◽  
Convolutional Network ◽  
Heterogeneous Sensors ◽  
Correlation Learning ◽  
Collaborative Sensing ◽  
Iot Devices

With the proliferation of Internet of Things (IoT) devices in the consumer market, the unprecedented sensing capability of IoT devices makes it possible to develop advanced sensing and complex inference tasks by leveraging heterogeneous sensors embedded in IoT devices. However, the limited power supply and the restricted computation capability make it challenging to conduct seamless sensing and continuous inference tasks on resource-constrained devices. How to conduct energy-efficient sensing and perform rich-sensor inference tasks on IoT devices is crucial for the success of IoT applications. Therefore, we propose a novel energy-efficient collaborative sensing framework to optimize the energy consumption of IoT devices. Specifically, we explore the latent correlations among heterogeneous sensors via an attention mechanism in temporal convolutional network to quantify the dependency among sensors, and characterize the heterogeneous sensors in terms of energy consumption to categorize them into low-power sensors and energy-intensive sensors . Finally, to decrease the sampling frequency of energy-intensive sensors , we propose a multi-task learning strategy to predict the statuses of energy-intensive sensors based on the low-power sensors . To evaluate the performance of the proposed collaborative sensing framework, we develop a mobile application to collect concurrent heterogeneous data streams from all sensors embedded in Huawei Mate 8. The experimental results show that latent correlation learning is greatly helpful to understand the latent correlations among heterogeneous streams, and it is feasible to predict the statuses of energy-intensive sensors by low-power sensors with high accuracy and fast convergence. In terms of energy consumption, the proposed collaborative sensing framework is able to preserve the energy consumption of IoT devices by nearly 50% for continuous data acquisition tasks.

Performance Evaluation of AFOD Protocol for Energy Efficient Routing

2011 ◽  
Author(s):  
B. Smitha Shekar ◽  
M. Sudhakar Pillai ◽  
G. Narendra Kumar
Keyword(s):  
Performance Evaluation ◽  
Energy Efficient ◽  
Energy Efficient Routing

Distributed Entropy Energy-Efficient Clustering algorithm for cluster head selection (DEEEC)

2020 ◽  
Vol 39 (6) ◽  
pp. 8139-8147
Author(s):  
Ranganathan Arun ◽  
Rangaswamy Balamurugan
Keyword(s):  
Energy Efficient ◽  
Clustering Algorithm ◽  
Cluster Head ◽  
Residual Energy ◽  
Energy Utilization ◽  
Sensor Nodes ◽  
Second Stage ◽  
Energy Efficient Clustering ◽  
Two Stages ◽  
Ch Selection

In Wireless Sensor Networks (WSN) the energy of Sensor nodes is not certainly sufficient. In order to optimize the endurance of WSN, it is essential to minimize the utilization of energy. Head of group or Cluster Head (CH) is an eminent method to develop the endurance of WSN that aggregates the WSN with higher energy. CH for intra-cluster and inter-cluster communication becomes dependent. For complete, in WSN, the Energy level of CH extends its life of cluster. While evolving cluster algorithms, the complicated job is to identify the energy utilization amount of heterogeneous WSNs. Based on Chaotic Firefly Algorithm CH (CFACH) selection, the formulated work is named “Novel Distributed Entropy Energy-Efficient Clustering Algorithm”, in short, DEEEC for HWSNs. The formulated DEEEC Algorithm, which is a CH, has two main stages. In the first stage, the identification of temporary CHs along with its entropy value is found using the correlative measure of residual and original energy. Along with this, in the clustering algorithm, the rotating epoch and its entropy value must be predicted automatically by its sensor nodes. In the second stage, if any member in the cluster having larger residual energy, shall modify the temporary CHs in the direction of the deciding set. The target of the nodes with large energy has the probability to be CHs which is determined by the above two stages meant for CH selection. The MATLAB is required to simulate the DEEEC Algorithm. The simulated results of the formulated DEEEC Algorithm produce good results with respect to the energy and increased lifetime when it is correlated with the current traditional clustering protocols being used in the Heterogeneous WSNs.

A Survey on Hierarchical Cluster Based Secure Routing Protocols and Key Management Schemes in Wireless Sensor Networks

2018 ◽  
pp. 18-26
Author(s):  
Yugashree Bhadane ◽  
Pooja Kadam
Keyword(s):  
Routing Protocol ◽  
Routing Protocols ◽  
Key Management ◽  
Energy Efficient ◽  
Base Station ◽  
Secure Routing ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Management Schemes ◽  
Cluster Based Routing

Now days, wireless technology is one of the center of attention for users and researchers. Wireless network is a network having large number of sensor nodes and hence called as “Wireless Sensor Network (WSN)”. WSN monitors and senses the environment of targeted area. The sensor nodes in WSN transmit data to the base station depending on the application. These sensor nodes communicate with each other and routing is selected on the basis of routing protocols which are application specific. Based on network structure, routing protocols in WSN can be divided into two categories: flat routing, hierarchical or cluster based routing, location based routing. Out of these, hierarchical or cluster based routing is becoming an active branch of routing technology in WSN. To allow base station to receive unaltered or original data, routing protocol should be energy-efficient and secure. To fulfill this, Hierarchical or Cluster base routing protocol for WSN is the most energy-efficient among other routing protocols. Hence, in this paper, we present a survey on different hierarchical clustered routing techniques for WSN. We also present the key management schemes to provide security in WSN. Further we study and compare secure hierarchical routing protocols based on various criteria.

CONCEPTUAL POSITIONS OF MODERNIZATION OF EXISTING INEFFICIENT DISTRICT HEATING SYSTEMS

2017 ◽  
pp. 11-21
Author(s):  
Ye.Ye. Nikitin
Keyword(s):  
Energy Efficient ◽  
Mutual Influence ◽  
District Heating ◽  
Current Status ◽  
Cognitive Approach ◽  
Heating Systems ◽  
Energy Management Systems ◽  
Current State ◽  
Self Sufficiency ◽  
District Heating Systems

The current situation in the sphere of district heating is analysed on the basis of use of the cognitive approach. The presence of closed chains of cause-effect relationships of negative factors and conflicts of target settings of the subjects in the field of district heating is shown. The conceptual model of energy efficient modernization of district heating systems is proposed. This model includes indicators of the current status of heat sources, networks and heat consumers, energetic and economic models, restrictions, procedure of forming and analysis of the mutual influence of the recommended projects. The quantitative data on indicators of the current state of district heating systems of the cities of Ukraine are presented. The interrelation between indicators of the current state and projects of energy efficient modernization of district heating systems is shown. Assessment of energy self-sufficiency of municipal district heating systems on condition of thermal modernization of buildings is carried out. The creation of energy management systems at the district heating enterprises is proposed. Bib. 6, Fig. 7, Tab. 5.

Analysis Criteria for Choosing Energy Efficient High-Quality Light Sources and Luminaires

2018 ◽  
pp. 113-119
Author(s):  
Gennady Ya. Vagin ◽  
Eugene B. Solntsev ◽  
Oleg Yu. Malafeev
Keyword(s):  
Energy Efficiency ◽  
Energy Efficient ◽  
National Standards ◽  
Light Sources ◽  
The European Union ◽  
High Quality ◽  
Eu Directive ◽  
The World ◽  
A New Technique ◽  
Energy Labelling

The article analyses critera applying to the choice of energy efficient high quality light sources and luminaires, which are used in Russian domestic and international practice. It is found that national standards GOST P 54993–2012 and GOST P 54992– 2012 contain outdated criteria for determining indices and classes of energy efficiency of light sources and luminaires. They are taken from the 1998 EU Directive #98/11/EU “Electric lamps”, in which LED light sources and discharge lamps of high intensity were not included. A new Regulation of the European Union #874/2012/EU on energy labelling of electric lamps and luminaires, in which these light sources are taken into consideration, contains a new technique of determining classes of energy efficiency and new, higher classes are added. The article has carried out a comparison of calculations of the energy efficiency classes in accordance with GOST P 54993 and with Regulation #874/2012/EU, and it is found out that a calculation using GOST P 54993 gives underrated energy efficiency classes. This can lead to interdiction of export for certain light sources and luminaires, can discredit Russian domestic manufacturer light sources and does not correspond to the rules of the World Trade Organization (WTO).

Sign in / Sign up

Export Citation Format

Share Document