The advanced metering infrastructure (AMI) of the smart grid plays a critical role in energy management and billing by enabling the periodic transmission of consumers’ power consumption readings. To optimize data collection efficiency, AMI employs a “change and transmit” (CAT) approach. This approach ensures that readings are only transmitted when there is enough change in consumption, thereby reducing data traffic. Despite the benefits of this approach, it faces security challenges where malicious consumers can manipulate their readings to launch cyberattacks for electricity theft, allowing them to illegally reduce their bills. While this challenge has been addressed for supervised learning CAT settings, it remains insufficiently addressed in unsupervised learning settings. Moreover, due to the distortion introduced in the power consumption readings due to using the CAT approach, the accurate prediction of future consumption for energy management is a challenge. In this paper, we propose a two-stage approach to predict future readings and detect electricity theft in the smart grid while optimizing data collection using the CAT approach. For the first stage, we developed a predictor that is trained exclusively on benign CAT power consumption readings, and the output of the predictor is the actual readings. To enhance the prediction accuracy, we propose a cluster-based predictor that groups consumers into clusters with similar consumption patterns, and a dedicated predictor is trained for each cluster. For the second stage, we trained an autoencoder and a one-class support vector machine (SVM) on the benign reconstruction errors of the predictor to classify instances of electricity theft. We conducted comprehensive experiments to assess the effectiveness of our proposed approach. The experimental results indicate that the prediction error is very small and the accuracy of detection of the electricity theft attacks is high.

The Hydromagnetic desalination (HMD) system is a continuous process with several advantages, including a high water recovery ratio, and can be favored economically by producing several industrial byproducts instead of discharging the highly concentrated brine to the environment. In the current work, the ions concentration in the Electrodialysis (ED) technique is simulated using COMSOL Multiphysics V.5.2 software. The ED cell simulated in this paper contains two selective membranes (anion and cation) with a width of 0.25 mm each. The salt is to be taken away in the middle domain. The cell operation has been simulated to separate the sodium and chlorine ions from the HMD brine waste solution at 40 or 55^ºC temperatures at different voltages and concentrations. In this two-dimensional model, the Nernst-Plank equation has been used to describe ion flux and charge transport in the electrolyte solution. Secondary current distribution theory and the electroneutrality condition have been used in the mathematical model. Finally, Donnan equations have been used to provide the exact fulfillment of boundary conditions for constant voltage mode. The simulation shows that the highest efficiency is obtained at high temperatures and voltage with the lowest feed concentration. Finally, the results have been validated using experimental data from the literature, and a satisfying agreement has been found.

Many industries produce and discharge large quantities of dilute metal ion solutions from the acid treatment of alloys, electroplating rinses, and leaches and effluents from the manufacture of chemicals. This discharge is considered to be a serious environmental threat. Electrochemical treatment is used as a sustainable effective technology for removal of heavy metals. In this study, experiments were carried out using a bench-scale electrochemical cell incorporating flow-by porous graphite electrodes for deposition of iron. The effect of current density, feed flow rate, and initial iron concentration on removal efficiency and current efficiency were studied. Experimental results showed that the maximum removal efficiencies(99.7%) and (99.9%) were obtained at flow rate of 0.278 ml/s, for initial iron concentration of 100 ppm and 200 ppm respectively. For concentration of 50 ppm it was 99.48% at flow rate of 1.11 ml/s, current density of 0.98 mA/cm2 and pH of 4. and maximum current efficiencies were 53% at 100 ppm , 99.9% at 200 ppm ,at flow rate of 0.833 ml/s, and 38.05% at 50 ppm at flow rate of 1.11 ml/s all obtained at current density of 0.98 mA/cm2. Solution pH in the range of 3 to 5 has a little effect on the deposition of iron.