The integration and management of distributed energy resources (DERs), including residential photovoltaic (PV) production, coupled with the widespread use of enabling technologies such as artificial intelligence, have led to the emergence of new tools, market models, and business opportunities. The accurate forecasting of these resources has become crucial to decision making, despite data availability and reliability issues in some parts of the world. To address these challenges, this paper proposes a deep and machine learning-based methodology for PV power forecasting, which includes XGBoost, random forest, support vector regressor, multi-layer perceptron, and LSTM-based tuned models, and introduces the ConvLSTM1D approach for this task. These models were evaluated on the univariate time-series prediction of low-volume residential PV production data across various forecast horizons. The proposed benchmarking and analysis approach considers technical and economic impacts, which can provide valuable insights for decision-making tools with these resources. The results indicate that the random forest and ConvLSTM1D model approaches yielded the most accurate forecasting performance, as demonstrated by the lowest RMSE, MAPE, and MAE across the different scenarios proposed.

This paper describes the development of a deep neural network architecture based on transformer encoder blocks and Time2Vec layers for the prediction of electricity prices several steps ahead (8 h), from a probabilistic approach, to feed future decision-making tools in the context of the widespread use of intra-day DERs and new market perspectives. The proposed model was tested with hourly wholesale electricity price data from Colombia, and the results were compared with different state-of-the-art forecasting baseline-tuned models such as Holt–Winters, XGBoost, Stacked LSTM, and Attention-LSTM. The findings show that the proposed model outperforms these baselines by effectively incorporating nonlinearity and explicitly modeling the underlying data’s behavior, all of this under four operating scenarios and different performance metrics. This allows it to handle high-, medium-, and low-variability scenarios while maintaining the accuracy and reliability of its predictions. The proposed framework shows potential for significantly improving the accuracy of electricity price forecasts, which can have significant benefits for making informed decisions in the energy sector.

Electricity markets provide valuable data for regulators, operators, and investors. The use of machine learning methods for electricity market data could provide new insights about the market, and this information could be used for decision-making. This paper proposes a tool based on multi-output regression method using support vector machines (SVR) for LMP forecasting. The input corresponds to the active power load of each bus, in this case obtained through Monte Carlo simulations, in order to forecast LMPs. The LMPs provide market signals for investors and regulators. The results showed the high performance of the proposed model, since the average prediction error for fitting and testing datasets of the proposed method on the dataset was less than 1%. This provides insights into the application of machine learning method for electricity markets given the context of uncertainty and volatility for either real-time and ahead markets.

This paper develops and analyzes four energy scenarios for Colombia that consider the El Niño phenomenon and the inclusion of renewable energies in the energy generation matrix for the period 2020–2035. A comparative analysis is presented between the results of the different scenarios proposed. The most relevant finding is the use of the reserve margin as an indicator of system reliability. A scenario which included 7214 MW of large-scale non-conventional renewable energy, 10,000 MW of distributed generation, and 12,240 MW of hydroelectric power was assumed, with a reserve margin of over 50%. Additionally, it was found that for the scenarios in which a generation capacity with non-conventional renewable energies of less than 10,000 MW in 2034 was assumed, the reserve margin of the system in the seasons of the El Niño phenomenon will be less than historical records of the system. Alternatively, it was found that the scenarios in which the inclusion of at least 9600 MW of the electric power generation capacity of non-conventional renewable energies proposed by 2034 offer benefits in the reduction in greenhouse gas (GHG) emissions, which contributes to the achievement of the emission reduction objectives of the Paris Agreement.

In the day-ahead dispatching of network-constrained electricity markets, renewable energy and distributed resources are dispatched together with conventional generation. The uncertainty and volatility associated to renewable resources represents a new paradigm to be faced for power system operation. Moreover, in various electricity markets there are mechanisms to allow the demand participation through demand response (DR) strategies. Under operational and economic restrictions, the operator each day, or even in intra-day markets, dispatchs an optimal power flow to find a feasible state of operation. The operation decisions in power markets use an optimal power flow considering unit commitment to dispatch economically generation and DR resources under security restrictions. This paper constructs a model to include demand response in the optimal power flow under wind power uncertainty. The model is formulated as a mixed-integer linear quadratic problem and evaluated through Monte-Carlo simulations. A large number of scenarios around a trajectory bid captures the uncertainty in wind power forecasting. The proposed integrated OPF model is tested on the standard IEEE 39-bus system.

The rapid increase in the integration of distributed resources such as distributed generation (DG), demand response (DR) and electricity storage (ES) requires management schemes to integrate distributed resources into low and medium electricity networks. Energy management represents a challenge for operation of electric grids when distributed resources are merged into the network. This paper address the energy management of distributes resources considering a complete characterization of them. The feasibility of those resources is considered into a microgrid model, so, the distributed resources are integrated through of a microgrid. This paper proposes the integration of distributed resources using a microgrid concept because there are relevant advantages of this model. The operational advantages are evident from the results. The results show how effectively different energy resources can be managed into the grid in the most efficient way.