A Pyramid-CNN Based Deep Learning Model for Power Load Forecasting of Similar-Profile Energy Customers Based on Clustering

Khursheed Aurangzeb,Musaed Alhussein,Kumail Javaid,Syed Irtaza Haider

doi:10.1109/access.2021.3053069

Abstract

With rapid advancements in renewable energy sources, billing mechanism (AMI), and latest communication technologies, the traditional control networks are evolving towards wise, versatile and collaborative Smart Grids (SG). The short term power load forecasting of individual as well as group of similar energy customers is critical for effective operation and management of SG. Forecasting power load of individual as well as group of similar energy customers is challenging compared to aggregate load forecasting of a residential community. The main reason is the high volatility and uncertainty involved for the case of individual and group of similar energy customers. Several machine/deep learning models have been developed in the recent past for forecasting load of individual energy customers, but such explorations are ineffective due to the requirement of one trained model for every energy customer, which is practically not feasible. We plan to build a deep learning model using convolutional neural network (CNN) layers in pyramidal architecture for effective load forecasting for a group of similar energy-profile customers. Initially, we grouped a subset of energy customers from database of Smart Grid Smart City (SGSC) into clusters using DBSCAN approach. The CNN layers are used for extracting feature from historical load of each cluster. The extracted feature of similar energy-profile customers (grouped based on clustering) is combined to make training-databases for each cluster. We have used the power load data from SGSC project, which contain thousands of individual household energy customers data. The developed Pyramid-CNN model is trained based on these sets of databases. The trained model is evaluated on randomly selected customers from few clusters. We obtained significantly improved forecasting results for randomly selected user from different clusters. Our adapted strategy of clustering based model training resulted in upto 10 percent MAPE improvement for the energy customers. The essence of our work is that energy customers can be grouped into clusters and then representative model could be developed/trained, which can accurately forecast power load for individual energy-customer. This approach is highly feasible, as we do not need to train a model per energy customer and still achieve competitive forecasting results.

Highlights

The forecasting of short-term electricity loads is an important part of the energy market
Accurate load forecasting of individual and group of similar-profile energy user is highly important for successful operation of Smart Grids (SG)
Power load forecasting of individual energy customers has been studied by some researchers but it is unfeasible practically due to requirement of trained-model per energy user

Summary

INTRODUCTION

The forecasting of short-term electricity loads is an important part of the energy market. Accurate load forecasting based on deep learning models provides an opportunity for energy users to relate their current energy costs to their future usage patterns. As a result, these customers can take benefit from predictive algorithms by being aware of their energy usage and future estimates, and they can manage their energy consumption costs more efficiently. The aim in current work is to group the energy customers in a residential community based on their load pattern using DBSCAN clustering. 5) The trained models are used for forecasting power load of few individual customers from each category It helped in proving usefulness of the group based training strategy for effective power load forecasting of similar-profile energy customers.

LITERATURE REVIEW

DATA ANALYSIS

RESULTS AND DISCUSSIONS

CONCLUSION