Natural Aggregation Algorithm Research Articles

An empirical hybridized Siamese network using hypercube natural aggregation algorithm for handling imbalance data learning

AbstractDealing with imbalanced data is a common challenge in machine learning, where one class has significantly fewer examples than another. Successfully addressing this challenge requires careful consideration of the data, algorithm, and evaluation metrics to ensure that the model accurately predicts the minority class. In this study, we present a hybrid approach called Siamese‐HYNAA, which combines a Siamese network and a population‐based optimizer hypercube natural aggregation algorithm (HYNAA) to generate candidate solutions for augmenting the minority class. We collected 10 imbalanced datasets ranging from 1.81 to 8.78 imbalanced ratios and built solution pairs based on correctly predicted candidate solutions using support vector machine (SVM). We then fed these solutions to the Siamese network, which employs a one‐shot learning approach to improve predictions with fewer candidate solutions. However, we found that SVM predicted only a small number of minority class samples accurately, prompting us to optimize the number of candidate solution pairs using HYNAA to generate more synthetic samples for the Siamese network. We evaluated our proposed strategy against basic SMOTE and our previous work, SMOTE‐PSOEV, using various performance measures, including ROC‐AUC learning curves, sensitivity, specificity, accuracy, Characteristic stability index, balanced accuracy, F1‐score, informedness, markedness, and execution time. Our results indicate that Siamese‐HYNAA generates promising results for imbalanced data.

A multi-objective natural aggregation algorithm for optimizing user allocation matrix in visible light communication

Allocating users to LED panels in a visible light communication (VLC) environment is a non-convex multi-objective constrained optimization problem. The computational complexity and accuracy of the optimization are the key factors to deal with in a VLC environment. In this manuscript, initially the user allocation problem is formulated as a single objective optimization problem by using sum-utility function of data rate and blockage probability. Then these two contradictory objective functions are simultaneously optimized by a new multi-objective natural aggregation algorithm (MONAA). This proposed algorithm is inspired by the aggregation behavior of cockroaches which help them to determine the darkest spot in a search space. The performance of this multi-objective algorithm is compared with NSGA-II, MOPSO, MOEA/D and MOSOS on eight unconstrained and six constrained mathematical function optimizations. In single objective and multi-objective cases, superior performance is demonstrated by the natural aggregation algorithm for solving the user allocation matrix optimization.

Hierarchical Operation Management of Electric Vehicles for Depots With PV On-Site Generation

Solar photovoltaic (PV) generation is a promising energy cost-saving selection for depots that use electric vehicles (EVs) to deliver goods; however, the intermittency of power output renders it challenging to realize reliable and economical operations. This paper proposes a two-stage hierarchical operation management method of EVs for depots with on-site PV generation. In the day-ahead stage, considering real road networks and battery swapping mode, a coordinated scheduling model of delivery service and charging/discharging for EVs is constructed to minimize the overall energy cost and logistics delivery cost by using the forecasted PV power output. Moreover, an effective solution approach based on the natural aggregation algorithm and Floyd algorithm is developed for the model. In the actual operation stage, a model prediction control (MPC)-based rolling horizon operation strategy is proposed to correct EVs’ charging/discharging decisions with the realization of real-time PV power output, aiming at to minimize the deviation in the actual and day-ahead scheduled interactive power between the depot and upper grid. Finally, simulations are conducted to validate the proposed methods.

Planning of electric vehicle charging stations and distribution system with highly renewable penetrations

With the increasing prevalence of electric vehicles (EVs), the EV charging station (EVCS) and power distribution have become a coupled physical system. A multi-objective planning model is developed herein for the sizing and siting of EVCSs and the expansion of a power distribution network with high wind power penetration. The objectives of the planning model are to minimise the total cost of investment and energy losses of the distribution system while maximising the total captured traffic flow. The uncertainties associated with wind power sources are considered. Additionally, the uncertainties in EV daily charging loads are also important concerns in the optimisation of the planning model. To model the EV load uncertainties, a recent scenario generation (SG) method is adopted. Further, a multi-objective optimisation tool, Multi-Objective Natural Aggregation Algorithm (MONAA), is introduced to obtain the final solutions of the planning model. The simulations based on coupled 54-node distribution network and 25-node traffic network systems are conducted to verify the efficiency of the proposed model and the effectiveness of SG-based MONAA.

Integrated planning of internet data centers and battery energy storage systems in smart grids

Modern power grids have been becoming complex cyber-physical systems integrated with distributed energy sources and information and communication facilities. With prevalence of cloud computing, geo-distributed, networked data centers have become an integrated part of modern grids. The coupling impact between data centers and smart grids thus becomes an important consideration. This paper proposes an integrated planning scheme that optimally determines the locations and capacities of interconnected Internet data centers and battery energy storage systems in a smart grid. The model is formulated as a multi-objective optimization problem, in which both computational performance metrics of Internet data centers and operational criteria of the grid are coordinately considered as three inter-related but conflict objectives; the coupling impact between the cyber and energy resources are modelled. An advanced evolutionary algorithm – Multi-Objective Natural Aggregation Algorithm is used to solve the model. Extensive case studies are conducted to demonstrate the reasonability and effectiveness of the proposed integrated planning method.

Operational Planning of Centralized Charging Stations Utilizing Second-Life Battery Energy Storage Systems

Centralized Charging Station (CCS) provides a convenient charging and maintenance platform for providing battery charging and delivery services to serve Electric Vehicles (EVs)’ battery swapping demands at battery swapping points. This article proposes an operational planning framework for a CCS with integration of photovoltaic solar power sources and an Echelon Battery System (EBS) comprising batteries retired from EVs (known as CCS-PV-EBS). The system is characterized by secondary using retired batteries to support the centrally charging services to the serving batteries. A rolling horizon-based operation strategy is proposed for the CCS-PV-EBS, which consists of a battery charging demand determination process and a multi-objective optimization process. An effective solving approach based on Multi-Objective Natural Aggregation Algorithm (MONAA) is developed for the proposed model. Extensive numerical simulations are conducted to validate the proposed method.

Low-Carbon Electricity Network Transition Considering Retirement of Aging Coal Generators

In order to achieve sustainable development goals, modern power systems need to achieve a low-carbon transition. Retirement and replacement of aging coal-fired power plants (CFPP) is the major part of electricity network transition. However, the sudden retirement of large aging CFPP could lead to power supply or reserve shortages and generally, it takes several years to complete the replacement process. This paper proposes a low-carbon electricity network transition model, helping to plan aging CFPP retirement and renewable power plants installation as well as network augmentation. The trade-off decisions are found among three conflicting objectives including cost, risk and carbon emission. Moreover, the carbon emission flow (CEF) model is applied in the planning process to calculate carbon emissions from the demand side, in order to assess the efficacy of the low-carbon transition. A relatively new multi-objective natural aggregation algorithm (MONAA) is introduced and applied to find the optimal solution. The proposed model is verified on a modified IEEE 24-bus RTS system and a modified IEEE 118-bus system. According to the numerical results, the proposed model can achieve carbon mitigation, cost and risk benefits and provide a roadmap to guide the energy network transformation towards a low-carbon economy.

A novel hybrid metaheuristic optimization method: hypercube natural aggregation algorithm

The natural aggregation algorithm (NAA) is a new efficient population-based optimizer. The NAA has a competent performance when compared to other well-established optimizers. However, a problem of concern is NAA lack of exploitation in its local search. In this article, we propose an improved version of NAA. The modifications made are: hypercubes with displacement and shrink mechanism applied in each shelter, we designed a new movement operator to search inside the hypercubes, an improved readjustment of the algorithm’s parameters and “leave shelter” formula of NAA, to better mimic the aggregation behavior. To prove the effectiveness of the modified hypercube natural aggregation algorithm (HYNAA), we compared with classics optimizers, such as PSO, DE and ABC, state of the art, such as CMA-ES, MSA and NAA himself with a benchmark of 28 functions. The said functions consist of five unimodal, 19 multimodal and four hybrids, and we compared them on 30, 50 and 100 dimensions. We also made extra comparisons against NAA in 500 and 1000 dimensions to contrast the ability of the hypercubes to reduce the dimensional complexity. Finally, we tested two trajectory optimization problems. Experimental results and statistical tests demonstrate that the performance of HYNAA is significantly better than that of other optimizers.

Coordinated residential energy resource scheduling with human thermal comfort modelling and renewable uncertainties

With development of two-way communication technology, residential users are able to reshape their energy consumption patterns based on demand response signals. This study proposes an optimal residential energy resource scheduling model to minimise the home electricity cost while fully considering the user's life convenience, the user's thermal comfort, and renewable uncertainties. The proposed model accounts for the characteristics of shiftable appliance, air-conditioning system, electric vehicle's charging pattern, and renewable generation of both wind and solar power. Wasserstein distance metric and K-medoids-based scenario generation and reduction techniques are used to address the renewable uncertainty. An adaptive thermal comfort model is employed to estimate the user's indoor thermal comfort degree. A waiting cost model is applied to measure the user's preference on the household appliance's operation. In addition, a recently proposed metaheuristic optimisation algorithm (the natural aggregation algorithm) is used to solve the proposed model. The simulation results show the proposed model is effective in minimising the household's daily electricity bill while preserving the user's comfort level.

Joint planning of active distribution networks considering renewable power uncertainty

This paper proposes a multi-objective joint planning model for Active Distribution Networks (ADNs). The model determines the location and size of Electric Vehicle Charging Stations (EVCSs), Renewable Energy Sources (RESs), Battery Energy Storage System (BESSs), and distribution network expansion schemes, with the objectives of minimizing the total investment and reliability cost of the distribution network and maximizing the EVCSs’ charging service capability. A scenario-based stochastic modelling approach based on Wasserstein distance metric and K-medoids scenario analysis is developed to model the stochastic nature of renewable generation. A multi-objective optimization algorithm, Multi-Objective Natural Aggregation Algorithm (MONAA), is applied to solve the proposed model. Case studies are conducted on a coupled 54-node distribution system and 25-node traffic system to validate the effectiveness of the proposed method.

A Framework for Cyber-Topology Attacks: Line-Switching and New Attack Scenarios

Cyber security of modern power systems has drawn increasing attention in recent years. This paper proposes a class of cyber-topology attacks derived from false data injection attacks, with the aim of disturbing the operation of power systems. Three kinds of cyber-topology attack are proposed: 1) line-addition attack; 2) line-removal attack; and 3) line-switching attack. By directly misleading the decision-making process of the independent system operator, the proposed cyber-topology attack consequently affects the economic operation and security of the system. We establish optimal attack models for different cyber-topology attack scenarios, and use a recently proposed metaheuristic optimization algorithm the natural aggregation algorithm to solve the resulting attack models. Experiments based on the IEEE 39-node benchmark system show that the proposed class of attacks poses a significant threat to modern power systems.

Power Supply Mode Planning of Electric Vehicle Participating in Logistics Distribution Based on Battery Charging and Swapping Station

Abstract Considering the operating pattern of battery charging and swapping station (BCSS) providing two power supply modes referring to battery charging mode and battery swapping mode at the same time, the power supply mode planning of electric vehicle (EV) participating in logistics distribution is conducive to decrease the operation costs. The primary contribution of this paper is to construct an optimization model with the objective of minimizing the overall cost of transportation cost and slow charging cost by considering the optimal driving route of EV, the selection of power supply mode and the slow discharging or charging management in the depot. The transportation cost is consisted of fast charging cost, battery swapping cost, battery life loss cost and vehicle loss cost. The secondary contribution of this paper is to improve a novel optimization algorithm called natural aggregation algorithm (NAA) as integer version to solve effectively the proposed model. Taking 33-node logistics distribution system as an example to carry out numerical simulation, the impacts of power supply mode planning on transportation cost and slow dis/charging cost are analyzed, the impacts of slow dis/charging strategy on the total cost are analyzed, and the effectiveness of proposed model in 13-node, 64-node, 112-node logistics distribution system are comparatively analyzed. The simulation results have demonstrated the feasibility and effectiveness of the proposed model and approach.

Generalized FDIA-Based Cyber Topology Attack With Application to the Australian Electricity Market Trading Mechanism

This paper proposes a generalized false data injection attack-based cyber topology attack capable of disturbing conventional transactions in the electricity market. The proposed attack aims to mislead customers pay higher electricity bills in the wholesale market by making small, undetected price deviations during each attack interval over an extended period. In this paper, the Australian electricity market trading mechanism is considered, in which an extended attack over a single day is proposed, spanning totally 288 5-minute dispatch (attack) intervals. The proposed attack poses no security threat to the power system, affecting only the economic costs borne by customers. A defining feature of the proposed model is the joint consideration of both topology error processing and bad data detection constraints in order to ensure validity of the proposed attack. The rolling horizon optimization technique is used to make appropriate adjustment to the attacker’s strategy considering the practical operating condition. A new metaheuristic optimization algorithm previously proposed by the authors, Natural aggregation algorithm, is used to find the corresponding attack strategies in this paper. Case studies on the IEEE-118 benchmark system are conducted to validate the proposed attack methodology.

Distributed residential energy resource scheduling with renewable uncertainties

Advances in metering and two-way communication technologies foster the studies of Home Energy Management System (HEMS). This study proposes a new HEMS, which optimally schedules the distributed residential energy resources (DRERs) in a smart home environment with varying electricity tariff and high solar penetrations. The uncertainties of solar power output are captured by using Monte Carlo sampling technique to generate multiple solar output scenarios based on the probabilistic solar radiation model. The homeowner's rigid and elastic restrictions on the operations of the automatically controlled household appliances are modelled. Based on this, an optimal DRER scheduling model is proposed to minimise the home operation cost while taking into account the homeowner's requirements. A new heuristic optimisation algorithm recently proposed by the authors, i.e. natural aggregation algorithm, is used to solve the proposed model. Simulations based on real Australian solar data are conducted to validate the proposed method.

Coordinated residential energy resource scheduling with vehicle‐to‐home and high photovoltaic penetrations

Home energy management system (HEMS) provides an effective solution to assist residential users in dealing with the complexity of dynamic electricity prices. This study proposes a new HEMS in contexts of real-time electricity tariff and high residential photovoltaic penetrations. First, the HEMS accepts user-specified residential energy resource operation restrictions as inputs. Then, based on the forecasted solar power outputs and electricity prices, an optimal scheduling model is proposed to support the decision making of the residential energy resource (RES) operations. For the scheduling of heating, ventilating, and air conditioning system, an advanced adaptive thermal comfort model is employed to estimate the user's indoor thermal comfort degree. For the controllable appliances, the `user disturbance value' metric is proposed to estimate the psychological disturbances of an appliance schedule on the user's preference. The proposed scheduling model aims to minimise the future 1 day energy costs and disturbances to the user. A new biological self-aggregation intelligence inspired metaheuristic algorithm recently proposed by the authors (a natural aggregation algorithm) is applied to solve the model. Extensive simulations are conducted to validate the proposed method.

Rolling horizon optimization for real-time operation of thermostatically controlled load aggregator

Thermostatically controlled loads (TCLs) have great potentials to participate in the demand response programs due to their flexibility in storing thermal energy. The two-way communication infrastructure of smart grids provides opportunities for the smart buildings/houses equipped with TCLs to be aggregated in their participation in the electricity markets. This paper focuses on the real-time scheduling of TCL aggregators in the power market using the structure of the Nordic electricity markets a case study. An International Organization of Standardization (ISO) thermal comfort model is employed to well control the occupants’ thermal comfort, while a rolling horizon optimization (RHO) strategy is proposed for the TCL aggregator to maximize its profit in the regulation market and to mitigate the impacts of system uncertainties. The simulations are performed by means of a metaheuristic optimization algorithm, i.e., natural aggregation algorithm (NAA). A series of simulations are conducted to validate the effectiveness of proposed method.

Natural Aggregation Approach based Home Energy Manage System with User Satisfaction Modelling

With the prevalence of advanced sensing and two-way communication technologies, Home Energy Management System (HEMS) has attracted lots of attentions in recent years. This paper proposes a HEMS that optimally schedules the controllable Residential Energy Resources (RERs) in a Time-of-Use (TOU) pricing and high solar power penetrated environment. The HEMS aims to minimize the overall operational cost of the home, and the user’s satisfactions and requirements on the operation of different household appliances are modelled and considered in the HEMS. Further, a new biological self-aggregation intelligence based optimization technique previously proposed by the authors, i.e., Natural Aggregation Algorithm (NAA), is applied to solve the proposed HEMS optimization model. Simulations are conducted to validate the proposed method.