Uncertainty modeling of renewable energy sources, load demand, electricity price, etc. create a high volume of data in smart grids. Accordingly, in this article, a precise forecasting method based on a deep learning concept with microclustering (MC) task is presented. The MC method is structured based on hybrid unsupervised and supervised clustering tasks by $K$ -means and Gaussian support vector machine, respectively. In the proposed method, the input data sequence is clustered by the MC task, and then the forecasting process is employed. By applying the MC, input data in each hour are categorized into different groups, and a distinctive forecasting unit is allocated to each one. In this way, more clusters and forecasting networks are earmarked for the hours with higher fluctuation rates. The bi-directional long short-term memory (B-LSTM), which is one of the newest recurrent artificial neural networks, is proposed as the forecasting unit. The B-LSTM has bidirectional memory—feedforward and feedback loops—that helps us to investigate both previous and future hidden layers data. The optimal number of clusters in each hour is determined based on the Davies–Bouldin index. To evaluate the performance of the proposed method, in this study, three forecasting tasks including the wind speed, load demand, and electricity price are studied in different periods using the Ontario province, Canada, data set. The results are compared with other benchmarking methods to verify the robustness and effectiveness of the proposed method. In fact, the proposed method, which is equipped with the MC technique and B-LSTM networks, significantly promotes the forecasting results, especially in spike points.

An accurate Electricity Price Forecasting (EPF) plays a vital role in the deregulated energy markets and has a specific effect on optimal management of the power system. Considering all the potent factors in determining the electricity prices - some of which have stochastic nature - makes this a cumbersome task. In this paper, first, Grey Correlation Analysis (GCA) is applied to select the effective parameters in EPF problem and eliminate redundant factors based on low correlation grades. Then, a deep neural network with Stacked Denoising Auto-Encoders (SDAEs) has been utilized to denoise data sets from different sources individually. After that, to detect the main features of the input data and putting aside the unnecessary features, Dimension Reduction (DR) process is implemented. Finally, the rough structure Artificial Neural Network (ANN) has been executed to forecast the day-ahead electricity price. The proposed method is implemented on the data of Ontario, Canada, and the forecasted results are compared with different structures of ANN, Support Vector Machine (SVM), Long Short-Term Memory (LSTM) - benchmarking methods in this field- and forecasting data reported by Independent Electricity System Operator (IESO) to evaluate the efficiency of the proposed approach. Furthermore, the results of this study indicate that the proposed method is efficient in terms of reducing error criterion and improves the forecasting error about 5 to 10 percent in comparison with IESO. This is a remarkable achievement in EPF field.

Growing penetration of Plug-in Electric Vehicles (PEVs) in the transportation fleet and their subsequent charging demands introduce substantial intermittency to the electric load profile which imposes techno-economic challenges on power distribution networks. To address the uncertainty in demand, a novel deep learning-based approach equipped with a hybrid classification task is developed which can take into account the travel characteristics of the PEV owners. The classification structure helps us scrutinize the PEVs demand by allocating a specific forecasting network to each cluster of travel behavior patterns. In our hybrid classification task, first, an unsupervised classifier discerns hidden travel-behavior patterns between the historical PEVs data by clustering them; then, a supervised classifier directs each new PEV data to its appropriate clusterspecific forecasting network. The deep learning-based forecasting and classification networks are constructed based on the Long Short-Term Memory networks to investigate long-and short term features in PEV behaviors. The data-driven structure of our proposed method enables us to observe and preserve the correlation between PEV travel data parameters (departure time, arrival time and traveled distance) and avoid the generation of unrealistic travel samples found in scenario-based approaches. To verify the effectiveness of the proposed method in practical environments, we have studied the impact of the precise forecasting of the PEVs demand in an aggregator’s financial profit in the energy market of the California Independent System Operator market. The numerical results confirm the outstanding performance of our proposed deep learning-based method in forecasting PEVs demand against benchmark approaches in this field such as Monte Carlo, Quasi-Monte Carlo, and Copula with only a 6.77% error in comparison with real data.

The growing integration of high-wattage Internet of Things (IoT)-enabled electrical appliances at the consumer end has created a new attack surface that an adversary can exploit to disrupt power grid operations. Specifically, dynamic load-altering attacks (D-LAAs), accomplished by an abrupt or strategic manipulation of a large number of consumer appliances in a botnet-type attack, have been recognized as major threats that can potentially destabilize power grid control loops. This article introduces a novel approach-based a multioutput network (2-D convolutional neural networks classifier and reconstruction decoder)—called “2DR-CNN”—to detect and localize D-LAAs with high resolution. To achieve this, we leverage the frequency and phase angle data of the generator buses monitored by phasor measurement units (PMUs) installed in the power grid. To verify the effectiveness of the proposed method, simulations are conducted on IEEE 14- and 39-bus systems. The performance of the 2DR-CNN method is compared against several benchmark machine-learning-based approaches. The results confirm that the proposed method outperforms other techniques in detection and localizing D-LAAs with high resolution in a number of practical scenarios, including PMU measurement noises and missing measurements.

The widespread deployment of “smart” electric vehicle charging stations (EVCSs) will be a key step toward achieving green transportation. The connectivity features of smart EVCSs can be utilized to schedule EV charging operations while respecting user preferences, thus avoiding synchronous charging from a large number of customers and relieving grid congestion. However, the communication and connectivity requirements involved in smart charging raise cybersecurity concerns. In this work, we investigate charge manipulation attacks (CMAs) against EV charging, in which an attacker manipulates the information exchanged during smart charging operations. The objective of CMAs is to shift the EV aggregator’s demand across different times of the day. The proposed CMAs can bypass existing protection mechanisms in EV communication protocols. We quantify the impact of CMAs on the EV aggregator’s economic profit by modeling their participation in the day-ahead (DA) and real-time (RT) electricity markets. Finally, we propose an unsupervised deep learning-based mechanism to detect CMAs by monitoring the parameters involved in EV charging. We extensively analyze the CMAs impact and the efficiency of the proposed detection on real-world EV charging datasets. The results highlight the vulnerabilities of smart charging operations and the need for a monitoring mechanism to detect malicious CMAs.