Evolutionary Multi-Objective Cost and Privacy Driven Load Morphing in Smart Electricity Grid Partition

Abstract

Utilization of digital connectivity tools is the driving force behind the transformation of the power distribution system into a smart grid. This paper places itself in the smart grid domain where consumers exploit digital connectivity to form partitions within the grid. Every partition, which is independent but connected to the grid, has a set of goals associated with the consumption of electric energy. In this work, we consider that each partition aims at morphing the initial anticipated partition consumption in order to concurrently minimize the cost of consumption and ensure the privacy of its consumers. These goals are formulated as two objectives functions, i.e., a single objective for each goal, and subsequently determining a multi-objective problem. The solution to the problem is sought via an evolutionary algorithm, and more specifically, the non-dominated sorting genetic algorithm-II (NSGA-II). NSGA-II is able to locate an optimal solution by utilizing the Pareto optimality theory. The proposed load morphing methodology is tested on a set of real-world smart meter data put together to comprise partitions of various numbers of consumers. Results demonstrate the efficiency of the proposed morphing methodology as a mechanism to attain low cost and privacy for the overall grid partition.

Neuro-Kernel-Machine Network Utilizing Deep Learning and Its Application in Predictive Analytics in Smart City Energy Consumption

“…The IDs of the 10 smart meters selected The days selected for testing was the week including the days 200-207 (based on the documentation of the dataset). In addition, the datasets for the weight training of the NKMN have been morphed using the method proposed in [3] given that this is a method that introduces interactions among the citizens. The obtained results, which are recorded in terms of the Mean Average Percentage Error (MAPE), are depicted in Table 14.2.…”

“…Therefore, the proposed method is applicable to smart cities, and more specifically to partitions (or subgroups) within the smart city. The proposed method was tested on a set of real-world data that were morphed [3] obtained from a set of smart meters deployed in the state of Ireland. Results exhibited that the presented deep learning architecture has the potency to analyze the past behavior of the citizens and provide high accurate group demand predictions.…”

“…In this section the newly developed network for conducting predictive analytics is presented [30]. The developed network implements a deep learning approach [22,26] in order to learn the historic consumption patterns of city citizens and subsequently provide a prediction of energy over a predetermined time interval [3].…”

“…The role of weights is to express the degree of realization of the specific behavior of the citizen in the overall city demand [15]. The underlying idea is that in smart cities the overall demand is a result of the interactive demands of the various citizens since they do have the opportunity to exchange information and morph their final demand [3,8].…”

Synergism of Fuzzy Leaky Bucket with Virtual Buffer for Large Scale Social Driven Energy Allocation in Emergencies in Smart City Zones

“…The management of electricity at the zone level is still in its infancy, although there are ongoing efforts primarily leveraging artificial intelligence. In summary, the existing efforts [11][12][13][14][15][16] indicate a limited exploration of zone-based allocation in smart cities, particularly concerning emergency scenarios. Furthermore, none of the proposed methods thus far consider social factors as part of their decision-making process, thereby failing to provide a sense of "allocation justice" to the affected citizens.…”