Collaborative Computation Offloading for Photovoltaic Power Prediction in Energy Internet: A Similarity-Aware Stable Matching Approach

The advances of communication technology and edge intelligence are deriving new computation offloading modes in the energy Internet by integrating computing capabilities of cloud servers, edge gateways (EGs), and terminal nodes into forecasting the renewable energy generation. However, the largely dispersed data generated by abundant photovoltaic (PV) stations and limited transmission capacity will degrade the collaboration of clouds, edges, and end nodes and, as a result, fail to satisfy the delay requirements of tasks. Owing to the similarity of power data generated by PV stations with akin geographical positions and weather conditions, we can reuse and offload the selected and representative power data so as to reduce transmission costs and overloads. In this article, we propose a similarity-aware stable matching approach (SASMA) to efficiently offload prediction tasks to EGs or cloud platforms with reusing the computing results. Specifically, we analyze task similarity and build the reuse strategy for the power data, and propose a similarity graph algorithm (SGA) to select representative PV stations and derive reuse relations. We also propose a similarity-based Gale–Shapley algorithm to match reused PV stations, computing nodes with prediction models. The objective is to maximize the prediction accuracy with a stable match. Simulation results show the effectiveness of the proposed approach while examining the tradeoff between the prediction accuracy and the system delay.

I. Introduction

The inherent natural characteristics of distributed energy resources (DERs), such as violent fluctuations and strong uncertainties, bring considerable uncertainties into electricity networks [1]. Energy Internet (EI) can enhance the collaborative utilization of DERs, enabling a flexible, customer-engaged energy transaction network, which achieve real-time balancing of supply and demand [2]. The photovoltaic (PV) generator has been widely deployed in EI as it is easily accessible and cost effective [3]. The accurate prediction for PV power generation is essential for an efficient management and utilization of renewable energies in power grids [4]. The prediction task for PV power generation uses meteorological information such as temperature, solar radiation, humidity at different timescales [5]. Extensive research efforts have been devoted into developing effective machine learning algorithms to predict the PV power generation, such as the statistical-based approaches (e.g., autoregressive model [6] and moving average model [7]), the artificial neural networks (e.g., echo state network [8] and naive Bayes classification [9]). However, PV stations are always constrained by its computational capabilities which fails to undertake computing-expensive prediction tasks locally.