Table 1 Comprehensive summary of literature studies related to the problem of multi-objective IoT service placement in fog computing.

Nashaat et al.¹⁶

Multi-Dimensional Quality of Experience (QoE) Model

This QoE model comprises two phases, which the first phase is responsible for determining the priority of different application placements depending on the impactful factors that include user expectations, application utilization and context of environment runtime.

It considerably minimized application placement time, application delay, network usage, and power consumption.

It improved the overall system performance by compromising a slight increase in the energy consumption related to fog control nodes.

Salimian et al.¹⁷

Grey Wolf Optimization Algorithm-Based IoT Application Placement (GWOAAP) scheme

This approach was identified to attain better convergence to the solution in the process of near-optimal application deployment which is introduced over the fog nodes.

The results confirmed better performance rate, mean waiting time, remaining services sent, and response time achieved with different tasks derived from applications.

It completely depended only on a single objective function which may not be realistic in some fog computing scenarios.

Wu et al.¹⁸

Evolutionary Algorithm-Based Fuzzy Scheduler (EABFS)

This evolutionary algorithm-inspired model considered the objectives of schedule robustness and customers’ agreement index into account for application placement in fog computing environment.

The results confirmed better execution time, makespan and failure rate independent to the number of tasks derived from applications.

The adopted evolutionary algorithm suffered from the problem of premature convergence and poor solution diversity.

Goudarzi et al.¹⁹

IMPortance weighted Actor-Learner Architectures (IMPALA)-based IoT application deployment mechanism (IWALASADM

This IWALASADM approach minimized the agents’ exploration costs obtained from the Directed Acyclic Graphs (DAGs)-modelled IoT applications that support diversified topologies and reduced the placement problem complexity with minimized constraints during the process of satisfying the dependencies with the applications of DAG-based IoT.

It concentrated on improving the sample efficiency and improved execution cost of IoT applications

It still possesses room for improvement in terms of exploration cost inherent with the searching agents during the process of task deployment during the execution.

Tavousi et al.²⁰

Fuzzy Approach-based Heuristic Algorithm (FAHAOP)

This FAHAOP approach classified the IoT applications depending on the properties of applications which need to be deployed over the virtualized computing resources.

It targeted on improving the average response time, percentage of deadline satisfied requests and resource wastage

The properties of the applications considered for deployment need improvement and need to be comprehensive such that it highlights all possibilities in the implementation scenario.

Sriraghavendra et al.²¹

Genetic Algorithm (GA)-based QoS-aware service placement mechanism (GASDM)

This GASDM handled the challenging tasks that are related to the orchestrating of the time sensitive IoT applications and incorporated a reliable multi-tier fog computing architecture which prevents the generic problem of deadlines which are inherent with the nodes of the cloud and fog.

It focussed on reducing the service execution delay and overall response time

The deadline considered for application deployment needs to be more dynamic in nature and on par with static properties.

Taghizadeh et al.²²

Non-Dominated Sorting Genetic Algorithm-based metaheuristic-based IoT application placement approach (NSGAMAP)

This NSGAMAP approach handles the node with different hardware potentialities which impose the challenges that arise during traffic reduction and latency in fog computing paradigms.

The results confirmed a decrease in latency, data access cost and increased data availability.

The latency and traffic reduction issue considered during the process of deployment needs improvement.

Ghobaei-Arani and Shahidinejad²³

Evolutionary Whale Optimization Algorithm-based Meta-Heuristic Mechanism (EWOAMHM)

It determined potential service placement using WOA for improving the throughput and energy consumption with the process of formulating the fitness function that helped in determining the optimal IoT service placement plan.

It concentrates in increasing the rate of the resource usage and service acceptance ratio with reduced service delay and energy consumption

The rate of exploration and exploitation during the process of application deployment needs improvement

Subbaraj et al.²⁴

Crow Search Algorithm-based Multi-Objective Metaheuristic Application Placement Algorithm (CSAMMAPA)

This CSAMMAPA approach considered the factors of security hit ratio and success ratio during the formulation and utilization of fitness function that helps in attaining IoT application placement.

It mainly focussed on the factors of success ratio and the security hit ratio.

The factors considered for formulating the fitness function are not comprehensive and thereby need improvement.

Sabireen and Venkataraman²⁵

Fog Picker and Multi-objective Particle Swarm Optimization-based clustering approach (FP-MPSOCA)

This FP-MPSOCA approach was proposed as a lightweight algorithm which helped in the dynamic scheduling of the fog nodes depending on the problem of multi-objective optimization.

It focussed on the process of improving the convergence and divergence compared to the baseline approaches, and task scheduling efficiency with respect to fog nodes and IoT application components.

This multi-objective optimization problem needs improvement in terms of proper balance exploration and exploitation during the process of application deployment.

Sun et al.³⁹

Proximal Policy Optimization Algorithm-based Proportional Fairness-Aware Auction method (PPOAPFAAM)

This PPOAPFAAM approach decoupled the process of task scheduling for implementing decision making associated with task allocation and resource allocation under different competitive scenarios.

It allocated different computing resources to each individual node using an auction algorithm after the process of completing the resource allocation.

This task allocation need to improve the response time and system throughput to the necessitated level.

Xia et al.⁴⁰

Metalearning-Based Alternating Minimization Algorithm-based Nonconvex Optimization

This MAMANCO approach incorporated the principle of non-convex optimization for improving the degree of interpretability in an optimal manner.

It included the merits of non-convex problem solutions for addressing the problem of non-linearity, matrix completion and bilinear inverse problem.

The inclusion of non-convex problem solutions still need to improved the quality of the solutions to the expected level.

Zhang et al.⁴¹

Multiple time-scale dispatch model which used the merits of frequency dynamics of islanding awareness

This multiple time-scale dispatch model proposed for micro-grid power dispatch transformed the problem of micro-grid into a multi-objective optimization problem by considering the factors of frequency stability, voltage deviation and economic cost.

It integrated the significance of an elite learning technique into the penalty-based boundary intersection (PBI) based multi-objective optimization approach for addressing the problem of micro-grid.

The inclusion of the elite learning technique has the probability of maximizing the degree of frequency dynamics of islanding awareness in the process of dispatch process.

Lin et al.⁴²

An entropy features-based optimized CatBoost model (EFOCBM) for attaining for an imbalanced industrial load identification process

This EFOCBM model selected the states of the switches with multiple number of original samples related to the load data from the dataset considered for evaluation.

This samples are segmented into time domain by partitioning each sample data into intervals associated to three time-domains.

The load identification model minimized the features of entropy which may not be realistic in most of the models of implementation in the prediction process.

Ding et al.⁴³

An intelligent traffic flow control system framework for achieving traffic flow management and attaining real-time prediction

This framework improved urban safety and traffic efficiency for the purpose of reducing the accident rates and optimizing the signal control such that application layers, perception and network platform.

It used the technology of vehicle networking for collecting the data traffic and at the same time, guaranteeing real-time transmission through 6G communication.

It used the technology of vehicle networking for collecting the data traffic which improved the rate of data response during the process of vehicular privacy and protection.

Peng et al.⁴⁴

Dynamic pricing driven double broad reinforcement learning model

This DPDDRL model guaranteed the safe vehicular operation for the objective of mitigating the degree of risks such that performance of the network can be improved with the required level of satisfaction.

This offloading model used the characteristics of long decision time for deriving the large number of parameters in the results of the deep network with large utilization of computational resources.

This offloading model used the characteristics of long decision time which increased the degree of response time

Xu et al.⁴⁵

Value Transfer Incentive Model

This Value Transfer Incentive Model addressed the problem of restricted data owner engagement with personalized model construction.

It ensured a fair benefit redistribution using the mechanism of bail and contribution assessment using the merits of InterPlanetary File System (IPFS) and Smart Contracts (SC) such that high reliability and security is improved in the implementation process.

The degree of reliability and security enforced by the implementation model was also identified to be comparatively lower than the baseline approaches.

Sun at al.⁴⁶

A breadth-first search (BFS)-based SFC deployment optimization (SFCDO) algorithm

It specifically used a BFS-based algorithm for identifying the shortest oath between the source and the destination nodes.

It also used the method of shortest path for selecting the process of SFC deployment with minimized number of hops on par with the simulated annealing and greedy algorithm.

The adopted BFS-approach determined the shortest path with marginal value during the process of identifying the path between the source and destination nodes.

Sun at al.⁴⁷

An online service function chain deployment (OSFCD) algorithm

This OSFCD method potentially handled the requests of SFC in the perspective of NFC in terms of 6G communication technology.

This method selected the path for the objective of determining the length of SFC from the deployment perspective.

It is identified to be marginal in process of attaining SFC achievement using the function of NFC during the process of optimization.