Virtual power plants: an in-depth analysis of their advancements and importance as crucial players in modern power systems

Table 2 Forecasting techniques

Refs.	Objective	Forecasting method used	Practical implications	Time scale	Software used
[82]	Probabilistic multi-period forecasting of DERs	CNN	Generate probabilistic forecasts	24 h	N/A
[83]	Forecast DER production and consumption	ARIMA, Gradient boosting, random forest	Method can be used by TSOs and DSOs	7 days ahead	N/A
[84]	Stochastic load and intermittency forecasting		Optimizing the scheduling of DERs	N/A	MATLAB,
[85]	Focus on growth, development, and future of RESs	ANN, SVR	Power system planning	Real-time (15min)	N/A
[86]	Forecasting framework to predict electrical, thermal net load	Deep belief network-based	Design and develop efficient forecasting model	Day-ahead	N/A
[87]	Predicting wind power	Fuzzy logic, MPC	SG applications	Monthly	MATLAB,
[88]	Short-term load forecasting	Genetic algorithm	Future planning of the power system network	24 h, 48 h	N/A
[89]	Wind speed forecasting	Neural network	Proper planning and operation	24 h	MATLAB
[90]	To deal with the challenges of increased penetration of PV into the electric grid	Multi-layer perceptron	Smart grid and microgrid applications	24 h	MATLAB
[91]	To predict accurate power generation from multiple RESs	CNN, LSTM, Auto regression	Power system planning	24 h	N/A

CNN Convolutional Neural Network, ARIMA autoregressive integrated moving average, ANN Artificial Neural Network, SVR support vector regression, MPC model predictive control, LSTM long short-term memory

ISSN: 2192-0567