In smart grids (SGs), the systematic utilization of consumer energy data while maintaining its privacy is of paramount importance. This research addresses this problem by energy theft detection while preserving the privacy of client data. In particular, this research identifies centralized models as more accurate in predicting energy theft in SGs but with no or significantly less data protection. Current research proposes a novel federated learning (FL) framework, namely FedDP, to tackle this issue. The proposed framework enables various clients to benefit from on-device prediction with very little communication overhead and to learn from the experience of other clients with the help of a central server (CS). Furthermore, for the accurate identification of energy theft, the use of a novel federated voting classifier (FVC) is proposed. FVC uses the majority voting-based consensus of traditional machine learning (ML) classifiers namely, random forests (RF), k-nearest neighbors (KNN), and bagging classifiers (BG). To the best of our knowledge, conventional ML classifiers have never been used in a federated manner for energy theft detection in SGs. Finally, substantial experiments are performed on the real-world energy consumption dataset. Results illustrate that the proposed model can accurately and efficiently detect energy theft in SGs while guaranteeing the security of client data.

Summary Ever‐increasing energy demand and technology development are continuously pursuing the attention of power system planners to design an optimum strategy for supplying future electrical demand. Generation expansion planning turns out to be a crucial step for an efficient energy management system in a modern power grid. In this paper, a novel whale optimization algorithm with penalty factor approach (WOA‐PFA) framework has been developed to solve a nonlinear, discrete, dynamic, highly complex, heavily constrained GEP problem. Reliability evaluation is accomplished using equivalent energy function approach. A virtual mapping procedure is utilized to add computational strength to the WOA‐PFA framework. Emission reduction is performed by utilizing total emission reduction constraint. The results are organized in four case studies starting with base power plants and adding wind, solar, and solar with storage facility in succession for the rest of case studies. Simulation results prove that the proposed WOA‐PFA shows promising results in terms of the least cost and computational time as compared with the techniques presented in the literature.

ED (Economic Dispatch) problem is one of the vital step in operational planning. It is a nonconvex constrained optimization problem. However, it is solved as convex problem by approximation of machine input/output characteristics, thus resulting in an inaccurate result. Reliable, secure and cheapest supply of electrical energy to the consumers is the prime objective in power system operational planning. Increase in fuel cost, reduction in fossil-fuel assets and ecological concerns have forced to integrate renewable energy resources in the generation mix. However, the instability of wind and solar power output affects the power network. For solution of such solar and wind integrated economic dispatch problems, evolutionary approaches are considered potential solution methodologies. These approaches are considered as potential solution methodologies for nonconvex ED problem. This paper presents CEED (Combined Emission Economic Dispatch) of a power system comprising of multiple solar, wind and thermal units using continuous and binary FPA (Flower Pollination Algorithm). Proposed algorithm is applied on 5, 6, 15, 26 and 40 thermal generators by integrating several solar and wind plants, for both convex and non-convex ED problems. Proposed algorithm is simulated in MATLAB 2014b. Results of simulations, when compared with other approaches, show promise of the approach.

Generation expansion planning (GEP) is a vital step in power system planning after load forecast. It is a highly constrained, dynamic, combinatorial, and discrete optimization problem. Mathematically, it is modeled as a mixed-integer nonlinear programming problem with high dimensionality and stochastic characteristics. The integration of renewable energy sources makes the GEP problem a complicated task and less reliable due to its intermittent nature. Meta-heuristic approaches are considered as potential solution methodologies to optimize the least cost GEP problem. This paper presents a novel GEP optimization framework to pursue the least cost GEP achieving a certain reliability level according to the forecasted demand for a planning horizon. The proposed GEP optimization framework is a correction matrix method with an indicator-based discrete water cycle algorithm (DWCA-CMMI). In DWCA-CMMI, a new parallel constraint handling approach, called a correction matrix method with indicators (CMMI), has been developed. DWCA-CMMI requires a smaller number of iterations and search agents to minimize the total GEP cost as compared to penalty factor-based metaheuristic approaches. Hence, CMMI enhances the convergence speed of the algorithm, avoids trapping in local optima, and improves both exploration and particularly exploitation. The proposed optimization framework is applied to reliability constrained and emission constrained GEP problems (test systems) from the literature. The proposed framework shows the promising results in terms of least cost and runtime as compared to results given by recent approaches presented in the literature. The applicability of the proposed approach has also been evaluated by applying to a real case study of Pakistan's power system to devise the feasible generation expansion plan.

Presently, axial flux permanent magnet machines are becoming popular and are being deployed actively for low speed applications. This paper presents an improved model of a multistage axial flux permanent magnet generator (AFPMG). The multistage AFPMG consists of multiple stator and rotor discs. There are three identical 1-phase stator discs and four in-phase rotor discs in the proposed multistage AFPMG. In this research, 4 case studies were analyzed on the design of the multistage AFPMG. First, a phase shift model (PSM) positions the three 1-phase stator discs to behave as a 3-phase generator. Actually, the PSM computes phases for three stator discs in order to establish phase shift of 120• between each two phases. The implementation of the presented model in the multistage AFPMG reduces the diameter of the stator disc three times as compared to the conventional 3-phase AFPMG with identical rated specifications. Second, the voltage waveform of the AFPMG was analyzed for harmonic contents and the percentages of 3rd and 5th harmonics were computed. The test results show that 3rd and 5th harmonics were reduced to 10.7% and 0.54%, respectively, in voltage waveform. Third, the proposed multistage AFPMG was designed considering begin-to-end winding connections of the stator disc. While adopting begin-to-end connection, the number of poles of the AFPMG are doubled, which ultimately increases air-gap flux density and thus the terminal voltage of the stator disc and operating shaft speed is halved. The test results show that the torque-to-weight ratio parameter of the designed AFPMG was improved by using a begin-to-end connection for the stator disc. Fourth, the increased air-gap flux density also improves the power density parameter of the AFPMG with a begin-to-end winding connection.Moreover, a prototype model of a 1200-W multistage AFPMG was designed and fabricated while following PSM and begin-to-end winding connection and tested. Thus the test results verify the proposed model of the multistage AFPMG for wind turbine applications.