Electricity-Price-Forecasting-using-Hybrid-Model

Introduction

In Competitive electricity markets, Electricity price forecasting is very valuable for all participants. Good forecasting plays a very important role in power investment decision and transmission expansion.

Why Electricity price forecasting is difficult?

High volatility
High frequency
Nonlinearity
Mean-reversion
Non-stationarity
Calendar-effect
Price spikes

Extreme learning machine (ELM)

● Extreme learning machines are feedforward neural networks for classification, regression and clustering with a single layer or multiple layers of hidden nodes, where the parameters of hidden nodes need not be tuned.
● These hidden nodes can be randomly assigned and never updated.
● The output weights of hidden nodes are usually learned in a single step, which essentially amounts to learning a linear model.

Particle Swarm Optimization (PSO)

● PSO was first intended for simulating social behaviour, as a stylized representation of the movement of organisms in a bird flock or fish school.
● PSO is a metaheuristic as it makes few or no assumptions about the problem being optimized and can search very large spaces of candidate solutions

How PSO works?

Initially we have set of Candidate solutions (called Particles).
These particles are moved around in the search-space
Every Particle have three direction to move
3.1. Its current direction
3.2. Particle’s best direction
3.3. Swarm’s best direction

Time Series

Time Series is a set of observations on the values that a variable takes at different time.
Ex.Sales trend, Stock market prices, weather forecasts etc.

Reference

1.Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods - ZhangYangabLiCeaLiLiana https://doi.org/10.1016/j.apenergy.2016.12.130

Prady029/Electricity-Price-Forecasting-using-Hybrid-Model