Federated Learning based Energy Demand Prediction with Clustered Aggregation

To reduce negative environmental impacts, power stations and energy grids need to optimize the resources required for power production. Thus, predicting the energy consumption of clients is becoming an important part of every energy management system. Energy usage information collected by the client...

Full description

Saved in:
Bibliographic Details
Published in:International Conference on Big Data and Smart Computing pp. 164 - 167
Main Authors: Tun, Ye Lin, Thar, Kyi, Thwal, Chu Myaet, Hong, Choong Seon
Format: Conference Proceeding
Language:English
Published: IEEE 01.01.2021
Subjects:
clustering
Collaborative work
Computational modeling
Convergence
Data models
Distributed databases
energy
federated learning
long short-term memory
recurrent neural network
Servers
Training
ISSN:2375-9356
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To reduce negative environmental impacts, power stations and energy grids need to optimize the resources required for power production. Thus, predicting the energy consumption of clients is becoming an important part of every energy management system. Energy usage information collected by the clients' smart homes can be used to train a deep neural network to predict the future energy demand. Collecting data from a large number of distributed clients for centralized model training is expensive in terms of communication resources. To take advantage of distributed data in edge systems, centralized training can be replaced by federated learning where each client only needs to upload model updates produced by training on its local data. These model updates are aggregated into a single global model by the server. But since different clients can have different attributes, model updates can have diverse weights and as a result, it can take a long time for the aggregated global model to converge. To speed up the convergence process, we can apply clustering to group clients based on their properties and aggregate model updates from the same cluster together to produce a cluster specific global model. In this paper, we propose a recurrent neural network based energy demand predictor, trained with federated learning on clustered clients to take advantage of distributed data and speed up the convergence process.
ISSN:2375-9356
DOI:10.1109/BigComp51126.2021.00039