Research on transmission line planning through massive data mining based on historical survey designs

Abstract

The growing demand for reliable and efficient power transmission has necessitated innovative solutions for transmission line planning. Despite advancements in energy systems, transmission line planning faces challenges related to optimizing routes and capacities while accommodating historical data variability and demand forecasts. The objective of the study is to utilize massive data mining techniques on historical survey designs to enhance transmission line planning, improving efficiency and reliability in the electrical grid while reducing costs and environmental impact. The study collects historical transmission data, including load forecasts, transmission line specifications, outage records, and demand patterns. The proposed study introduces an Intelligent Grasshopper Optimization Algorithm (IGOA) method for analyzing historical transmission data. This method identifies optimal transmission line placements and capacities, and enhancing decision-making by optimizing multiple objectives, including cost, reliability, and efficiency in power transmission planning. Simulations are conducted on the IEEE 118-bus system, testing various cases to ensure the robustness and efficiency of IGOA approach. The outcomes demonstrate the plans generated through the proposed IGOA strategy yield significantly lower expansion costs compared to traditional transmission line planning models, exhibiting minimal operational infeasibilities that can be easily addressed in short-term expansion planning. This research highlights a robust framework that can be adapted to various energy systems, ultimately supporting more sustainable and reliable power transmission infrastructure.

Keywords

historical survey designs transmission line planning Intelligent Grasshopper Optimization Algorithm (IGOA)IEEE 118-bus system

Introduction

In power systems, transmission line planning was necessary for effective activity and dependable transfer of energy from sources of generation to users. Transmission line planning becomes more difficult due to the upgrading of power networks that constitute the demand for electricity and the integration of renewable energy sources.¹ The traditional transmission line planning techniques possess deterministic models to handle the complexity of the modern grid. Transmission line design in digital transformation constitutes the use of sensors, smart grids, GIS, and other sources.² The economic, environmental, and social issues offer sophisticated data mining tools to improve transmission line development. The process of extracting valuable patterns and information from mines is known as data mining, and it has been widely used in different sectors. The prediction of future energy requirements and design intends the transmission line planning.³ Data mining’s capacity swiftly evaluates the vast volumes of data and uncovers insights. For instance, data mining assists the transmission line routes by environmental restrictions for electricity generation and consumption. Planning transmission lines becomes more complicated with renewable resources. The source of energy was frequently found in isolated locations, apart from the infrastructure of the main grid.⁴ Geographical difficulties, possible environmental effects, and power output unpredictability constitute new transmission lines to link various renewable energy sources. Finding trends in renewable energy generation ensures the best transmission line routes and grid integration locations. Additionally, data mining improves decision-making in transmission line development by offering comprehension trade-offs.⁵

Transmission line planning usually entails the striking balance between a number of competing, dependability, cost reduction, and environmental effect reduction. Data mining enhances the grid’s operational elements through physical layout and the positioning of transmission lines.⁶ Figure 1 represents the transmission infrastructure statistics. The transmission infrastructure contains load forecasts, operational performance, resilience, and transmission service.

Figure 1.

Transmission infrastructure statistics.

Predictive models offer information about future transmission capacity requirements for ensuring economic activity, population expansion, weather trends, and historical demand. It enables planners and grid operators to make better-informed choices on the location and timing of future transmission infrastructure investments.⁷ The potential of data mining integrates social and environmental factors into transmission line planning. Planners find routes and designs to reduce the consequences of data mining to examine social and environmental variables and financial factors.⁸ Transmission line design was improved by combining data mining methods with GIS. Planners determine the transmission line infrastructure by using data mining. The planners and grid operators intend better-informed choices on the location for enhancing future transmission infrastructure investments.⁹ The dependability and durability of transmission infrastructure are aided by GIS-based data mining. Several pieces of information, such as technical grid data, environmental data, economic predictions, and sociological data were integrated for transmission line planning.¹⁰ The interpretability of data mining models ensures transmission line planners. The sophisticated machine learning algorithms were capable of producing quite precise forecasts. The visual effects, land usage and possible harm to ecosystems, local communities, and environmental organizations frequently oppose transmission line projects.¹¹ Historical technologies used in transmission line planning might be difficult to combine with contemporary data mining methods. Conventional data mining techniques might struggle to handle real-time data integration such as changing demand, weather, and grid problems.

The study’s aim is to utilize massive data mining techniques on historical survey designs to enhance transmission line planning, improving efficiency and reliability in the electrical grid while reducing costs and environmental impact. The main contributions of this work are:

(1) The Intelligent Grasshopper Optimization Algorithm (IGOA) approach was proposed to analyze the historical transmission data, identify optimal transmission line placement capacities and enhance decision-making by optimizing multiple objectives, including cost, reliability and efficiency in power transmission planning.

(2) The objective of the study is to utilize massive data mining techniques on historical survey designs to enhance transmission line planning, improving efficiency and reliability in the electrical grid while reducing costs and environmental impact.

(3) This study offers a strong framework from different energy systems, facilitating more dependable, sustainable planning and infrastructure construction for power transmission.

Related works

To ensure viability, a planner must incorporate operating choices of plan schedules due to the unpredictability of renewable energy.¹² The operational choices over the planning horizon are computationally impossible to solve the GTEP problem. The GTEP was a layered technique with a problem’s structure. The experimental outcome demonstrated the GTEP solution tools. To anticipate and categorize transmission line issues in the power system, they suggested the TSVD-HUARPNN technique integrate the HUA and TSVD for RPNN.¹³ Transmission line faults were predicted and classified by the TSVD-HUARPNN technique. The experimental outcome demonstrated that the suggested approach has low detection complexity.

The electricity systems remain reliable, so the transmission line faults are detected quickly and accurately.¹⁴ The frequency-domain analysis of current and voltage possesses the TF to assess the impact of fault location. The transmission lines were identified and located by the DRL system. The experimental outcome demonstrated the faults of the short-circuit network. The microwave components were small and highly efficient by the quick growth of contemporary communication systems.¹⁵ The feed network consists of a significant amount of circuit space, power dividers, and filters at low frequencies. The result findings demonstrated the factor size reduction.

The mobile storage units intended to function in tandem with the transmission planning paradigm.¹⁶ To reduce the total cost of the model that includes expenditures on investment with transmission lines. The mobile storage systems maintain expenses like energy used by traditional elements, congestion taxes, and transport expenses. The experimental outcome showed substantial power networks. Power production methods, storage of energy, and electric energy infrastructure for transmission were intended for long-term growth.¹⁷ The demand for electric load toward planning, the suggested approach specifies the dimensions and locations of transmission storage systems. The LCP was used for the long-term growth of the transmission line. The experimental outcome demonstrated the planning expenses of the system.

The TNEP approach was used to determine the cost-effective method of grid expansion based on demand trends and long-term development in generation capacity.¹⁸ The TNEP incorporates flexible transmission systems for enhancing the power flows with the impedance of specific branches. The experimental findings indicated the use of renewable energy sources. The resilient transmission augmentation scheduling system possesses the contingency probability.¹⁹ The service interruption rate of specific equipment used to determine the range that characterizes the probability of risk. The experimental outcome demonstrated the triple layer optimal issue.

The TEP systems include more information about long-term system changes and power grid functions with intermittent renewable energy.²⁰ Planning and operating power systems required flexible assets with a higher degree of energy sectors. The experimental outcome demonstrated that the suggested strategy preserves solution quality. The supervised learning approach used popular classifiers to categorize power transmission line issues.²¹ The electrical grids’ reliable, stable, and secure defects were categorized and constitute how the electrical impulses correspond to them. Power system failure analysis comparisons were difficult and performance was unpredictable. The experimental outcome demonstrated the suggested approach to computing speed.

Data mining approaches constitute the trends and possibilities in power organizations. The artificial intelligence solutions were relied by expert systems.²² The development of BDA has constituted a profound impact on the distribution industry with the rapid expansion of interacting and sensing infrastructure impacted by renewable energy sources. The experimental outcome displayed the network’s electricity distribution. To ensure secure and reliable operations, transmission network controllers require a higher degree of actual time detection to increase awareness of situations and decision-making processes.²³ The virtualization of storage systems enables utilities to track the dynamic function of the system in actual time. The experimental outcome demonstrated the use of sophisticated analytical instruments.

The probabilistic modeling of electrical transmission networks during storms provides additional information about energy system operation and resilience assessment.²⁴ The transmission power system was modeled as a network for interconnected individual components susceptible to power flow and mechanical breakdown caused by wind. The experimental outcome demonstrated the transmission line upgrade. The transmission and distribution networks were segregated in conventional power system planning issues, which was inappropriate for power systems and developed quickly.²⁵ The hierarchical structure maximized the transmission networks simultaneously. The TSO constitutes leader to solve the TEP issues. The experimental outcome demonstrated that an integrated system significantly lowers the overall cost.

Coordination and communication across the transmission network possess dispersed generation. In transmission networks, integrated growth planning entails the investments of cost among networks.²⁶ The demand for power from renewable sources and the ideal expansion plan determine the optimum course of action assets. The experimental outcome demonstrated the stochastic technique of trade-off.

Recent methodologies in transmission line planning have focused on conventional optimization techniques, which often utilize linear models constrained by fixed parameters and do not adequately capture the dynamic nature of modern power grids. For instance, studies that employ deterministic models fail to accommodate uncertainties inherent in load forecasting and renewable generation. In contrast, our approach leverages a data mining framework in conjunction with IGOA to dynamically adjust routing and capacity decisions based on historical data patterns. This addresses the limitations inherent in prior studies by integrating real-time considerations, thereby enhancing both reliability and efficiency in planning outcomes.

Methodology

Transmission expansion planning (TEP) model

The planning phase was used to address the static TEP issues. The entire cost of the system was calculated by using the investment costs of the additional transmission lines that must be added during the planned period with LOL. Furthermore, security requirements constitute every scenario and the challenge was framed for power plants.

Loss function

TEP’s target function was stated to reduce the cost of additional transmission lines to the system to satisfy the demand for electrical energy during the planning periods, as expressed in equation (1).

Min D_{S} = \sum_{j i} D_{j i} m_{j i}

(1)

To ensure an efficient alignment of customer demand with the anticipated time horizon, it is essential to comply with all relevant constraints, including the requirements set forth by the power system.

Restrictions

Power balance, power flow, transmission line temperature limitations, plant restrictions, and system security requirements were represented as constraints while ensuring the TEP issue.

Equality restrictions

To ensure the demand of load from power losses, active power was frequently employed to describe TEP constraint problems. The mathematical model of power flow transmission lines among buses is expressed in equations (2) and (3).

e + h + q = c

(2)

e_{j i} - A_{j i} (m_{j i}^{0} + m_{j i}) θ_{j i} = 0

(3)

The LOL employed to ensure the power balance with following limits, while performing the generation and resizing intends to lower the cost of the expansion planning. LOL minimized by locating an appropriate way of expensive for the utility and societal welfare.

Inequality restrictions

The generation restriction of every bus (4), LOL for every customer (5), and right way extension of every branch (6) were the instances of inequality restrictions. Additionally, it contains the power flow thermal limit for every branch.

0 \leq h \leq \bar{h}

(4)

0 \leq q \leq \bar{c}

(5)

0 \leq m_{j i} \leq {\bar{m}}_{j i}, \forall (j, i) Є Ω

(6)

| e_{j i} | \leq (m_{j i}^{0} + m_{j i}) {\bar{e}}_{j i}

(7)

{| e_{j i} |}^{d} \leq (m_{j i}^{0} + m_{j i}) {\bar{e}}_{j i}, \forall (j, i) Є Ω, \forall (d) Є Ω_{c t l}

(8)

Feasibility management

The pertaining power system requirements were followed to determine a suitable solution for the TEP issues. The power balancing incorporates the LOL equality constraints, which implies raising utility costs and lowering social welfare. The transmission line temperature has contingency inequality restrictions. The constraint compliance issue was resolved by employing the aggregating strategy. Consequently, the related restrictions of function as penalty and the loss function of the TEP issues are recreated in equations (9)–(12).

O = D_{J} + D_{K} + π_{a} + π_{d}

(9)

D_{K} = \sum_{j} b_{j} q_{j}

(10)

π_{a} = ω_{1} \sum_{j = 1}^{Ω} \max (0, e_{j i} - {\bar{e}}_{j i})

(11)

π_{d} = ω_{2} \sum_{d = 1}^{Ω_{c t l}} \sqrt{\frac{\sum_{j = 1}^{Ω} {\max (0, e_{j i}^{d} - {\bar{e}}_{j i})}^{2}}{S_{d}}}

(12)

Here, $O$ represents the penalty function to be optimized, $D_{K}$ depicts the cost of load for $ω_{2}$ and $ω_{1}$ as penalty coefficients, and $d, π_{a}$ and $π_{d}$ represent the penalties associated with thermal overloading.

Intelligent Grasshopper Optimization Algorithm (IGOA)

The IGOA is used in transmission line planning to improve transmission line placement and design, guaranteeing efficient power distribution and lowering expenses. IGOA simulates possible transmission line topologies based on factors such as load demand, geographic restrictions, and environmental effects by modeling grasshopper motions. Effective routing and ideal design solutions are produced when the algorithm cleverly modifies its search parameters to strike a balance. It seeks to lower the operating costs and environmental consequences while improving electrical grid efficiency and dependability. The grasshopper optimization method mimics the behavior of grasshopper swarms. The grasshopper swarm travels great distances in search of a fresh food source. Within the swarm, grasshopper interactions have an impact on one another. The grasshoppers’ path is influenced by the force of the wind and gravity. The GOA was straightforward, and it was simple to use. However, it has several drawbacks that hinder the algorithm’s ability to provide superior results. The initial GOA was unable to use full iteration due to the exponentially shrinking comfort zone. The absence of random components in the original method results in low variability. Three enhancements were made to address the drawbacks of random leaping. Levy fly-enhance localization method and quadratic zone for comfort. These enhancements provide a comprehensive description of the upgrade specifics.

In our implementation of the IGOA, we made certain key assumptions. Firstly, we assumed that historical transmission data reflects consistent patterns in load forecasting and environmental factors, allowing for reliable predictions during the optimization process. Secondly, we set the parameters for the IGOA, such as the number of grasshopper agents and the maximum number of iterations, based on preliminary tests that indicated these values yielded optimal performance across multiple scenarios. These parameters can be adjusted for specific applications, contributing to the algorithm’s flexibility. Documenting these assumptions is crucial for reproducibility and understanding of the methodology.

Comfort levels

The global optimum solution is integrated by search engines throughout iterations if initial GOA modifies the safety zone. GOA limits the search space by using the safety zone option. The safety zone restriction was set as high during the assessment phase to provide the search agents adequate room to quickly locate the estimated optimum. The restricting factor must be minimal during the assessment phase to precisely search for the local optimum and prevent the search agents from moving quickly. Furthermore, search iterations constitute a linear declining factor that was unable to balance the search capability with the exploitation and exploration phases. The sigmoid function was added to align the search phases and improve the algorithm’s search capabilities. The sigmoid function improves the algorithm’s overall search capabilities by synchronizing the search phases. The sigmoid function is expressed in equation (13).

e (w) = \frac{1}{1 + f^{- w}}

(13)

The following regressive safety zone factor is based on the variation of the sigmoid function expressed in equation (14).

n = \frac{- 0.5}{1 + f^{(- 1.5 (c x - 5) + 2 \sin (c x))}} + v

(14)

Here, $v$ represents the adjustment variables and its ranges from [0, 1] expressed in equation (15).

d w = \frac{u (i t e r + 50)}{M a x I t e r a t i o n}

(15)

Here, $u$ depicts the accuracy correction factor, ranges from [1, 10].

Stochastic search with Levy flight

Every search agent explores the predetermined place and the absence of unpredictability might exceed the lack of originality during the search rounds. To enhance the performance of deterministic systems, include a random component. An effective mathematical technique for supplying a random component was Levy flight and the random search walk proposed by Paul Levy. Due to the complexity of implementing Levy flight, the following simulation approach is expressed in equation (16).

L e v y (c) = 0.01 \times \frac{q_{1} \times σ}{{| q_{2} |}^{\frac{1}{β}}}

(16)

Here, $c$ represents the size of the problem, $q_{1}$ and $q_{2}$ are two interval ranges from [0, 1], and $β$ represents constant values. $σ$ Calculations are expressed in equation (17).

σ = {(\frac{Γ (1 + β) \times \sin (\frac{π β}{2})}{Γ (\frac{1 + β}{2}) \times 2 (\frac{β - 1}{2})})}^{\frac{1}{β}}

(17)

where

Γ (w) = (w - 1)!

The search agents move toward the ideal place; Levy Flight might provide visibility to all of them. The search agents were able to observe the surrounding local regions. The Levy flight-based local search strategy was suggested to increase the search agents’ search range and improve their capacity to locate the optima. After a location update procedure was complete, every search agent’s position was modified by using Levy flight with a specific probability. The adjustment prescription is expressed in equation (18).

W_{j} = W_{j} + 10 d \times t_{t h r e s h o l d} \times L e v y (\dim) \times W_{j}

(18)

The direction and likelihood of the fluctuation were controlled by $t_{t h r e s h o l d}$ variable. The $t_{t h r e s h o l d}$ factor is expressed in equation (19).

t_{t h r e s h o l d} = s i g n (w_{t r a n s} - 1) + s i g n (w_{t r a n s} + 1)

(19)

Here, $w_{t r a n s}$ is a random integer that ranges from [−3, 3] and $s i g n (w)$ represents as a sign function.

Probabilistic jumping model

The GOA’s fundamental ideas were simple. The GOA search process became stuck in a local optimum was unable to continue. The potential drawback of GOA might constitute the implementation that does not translate into the elimination of the local optimum. The random jumping model intends to facilitate the capacity of local optimum. The previous target position might be replaced with the new one if a search agent discovers the ideal location. The random jumping equation begins to function as expressed in equation (20).

W_{j}^{n e w} = ((0.5 - r a n d) \times 2 + 1) W_{j}

(20)

The new position following the random jumping model is represented as $W_{j}^{n e w}$ . $W_{j}$ represents the location of the $j$ -th search agent more appropriately. The current iteration’s optimal location possesses the search movement was determined by the initial GOA, which disregards certain pertinent data. The location’s progression formula was changed to maintain the impact of the acquired knowledge about the leaping action expressed in equation (21).

W_{j}^{i t e r + 1} = n \times d \times T_{j} + (1 - o) {\hat{S}}_{c} + o \times W_{j}^{i t e r}

(21)

Here, $o$ represents the index variable to limit the effect of search ingredient location. To ensure that $T_{j}$ and $S_{c}$ can influence the evolution of the search agent that neither leaps nor hops towards the local optimal site. The effect of the leaping behavior is governed by the variable $o$ , which helps reduce the linear progression of iterations after a search agent exits the local optimum. The $o$ variable was computed as expressed in equation (22).

o = {\begin{cases} o - 0.3478, o > 0 \\ 0, o \leq 0 \\ 3 \times 0.3478, w h e n j u m p i n g o u t s u c c e s s f u l l y \end{cases}

(22)

Process of IGOA

The initiation, evolution, fitness update, and leaping stages were the four phases of the IGOA process. The settings were established for each search agent’s initial position and chosen at random by the startup phase. The search loop begins to function during the evolution phase. Equation (21) represents the search agent’s target place direction. A new location produced at every search agent performs as a Levy flight with a certain probability determined in equation (17). The suitability of the new location is determined by the updating phase. The new location integrates the previous global with new fitness that surpasses the global fitness. The leaping stage reached a new fitness level that was not better than global fitness. Using equation (19), the search agent attempts to exit the local optimum and new fitness was determined. The previous personal position might be replaced by the new one if the new fitness level surpasses the personal fitness level. Equation (22) updates the variable. The loop has completed the iteration so far. The loop terminates the maximum number of iterations achieved and the final outcome demonstrated the fitness and target location.

Implementation of IGOA for TEP

It describes how the TEP problem was solved by using IGOA. The potential transmission pathways were represented by each node and link. The basic network has three buses and three branches, possessing several line options and potential routes. By selecting the best line configurations for every branch, the IGOA model simulates the dynamic nature of transmission network architecture and how grasshoppers in the wild travel in coordinated swarms to search for food. The IGOA typically starts with a population of grasshopper agents that were randomly distributed around the network, representing the possible transmission routes. The search method was modeled after the swarm behavior of grasshoppers and investigated the distinct path. Grasshoppers use a balance of attraction and repulsion to adjust the postures to get the ideal solution. The exploitation and exploration phases were included in every iteration to guarantee that the grasshopper agents. The grasshopper’s fitness values were assessed to improve their locations in search of better answers. Parameters are adaptively adjusted to reflect the attraction and repulsion dynamics between the agents. The relative attraction and repulsion for each path are adaptively adjusted according to fitness update criteria that take into account cumulative desirability. The implementation of IGOA for TEP is divided into two main rules: the position update rule and the fitness evaluation rule.

Position update rule

Every iteration of the IGOA is governed by the position update rule, which controls how grasshopper agents modify the locations in the search space. It enables grasshoppers to focus on promising regions found in earlier rounds while simultaneously investigating new possible solutions. Mathematically, the position update rule is expressed in equation (23).

Z_{j} (S + 1) = Z_{j} (S) + B . r a n d () . (Z_{b e s t} (s) - Z_{j} (s)) + A . r a n d () . (Z_{m e a n} (s) - Z_{j} (s))

(23)

where

Z_{j} (S)

depicts the grasshopper iteration at

S

Z_{b e s t} (s)

represents the finest spot of the grasshopper,

Z_{m e a n} (s)

indicates the grasshopper’s average location, and

r a n d

represents the random value from 0 to 1.

Fitness evaluation rule

To determine the grasshopper’s position meets the requirements for the TEP issue requires the use of the fitness evaluation rule. It measures the quality of the solutions according to pertinent factors like load capacity, cost and dependability. Every grasshopper’s fitness level is determined by using the following equation (24).

E (Y_{j}) = \frac{1}{D (Y_{j})} + ⋋ . Q (Y_{j})

(24)

where

E (Y_{j})

represents the fitness value of the grasshopper,

D (Y_{j})

indicates the transmission lines selected by the grasshopper,

Q (Y_{j})

depicts the higher fitness value, and

⋋

represents the fitness weight factor.

Experimental results

The tasks were completed using MATLAB on a laptop equipped with an Intel Core i7-13650HX Duo 2.60 GHz processor, running Windows 10 and having 16 GB of RAM.

The IEEE 118-bus was utilized to evaluate the suggested TEP-IGOA technique. The 118-bus system has many possible branches for future transmission lines. The efficiency of the IGOA technique in maximizing transmission expansion plans was assessed by using the extensive network. It shows that the algorithm finds the best settings to save expenses while maintaining operational effectiveness and system dependability. Figure 2 depicts the IEEE 118-bus system.

Figure 2.

IEEE 118-bus system.

The IEEE 118-bus was utilized to ensure the performance of the power system. The system has 118 buses, 91 generators, 177 branches, and 54 loads, intended to replicate a real power grid. Its complexity offers a useful platform to test several approaches, such as load flow analysis and optimal power flow. The system’s transmission lines have certain impedance values that affect power flow and stability. Every bus is depicted as a node, and transmission lines indicate the lines link. At different places of the system, loads and generators were depicted as designated buses. Combinations of load and generator buses intend the IEEE 118-bus system. Power generation and distribution under different operating circumstances lead generators to constitute across the network. The IEEE 118-bus system serves as a valuable platform for developing and validating innovative methods for power system operation and control. To ensure secure transmission of electrical power, the IEEE 118-bus system is an essential instrument for improving knowledge and dependability of electrical grids.

Figure 3 shows the comparative features of without optimization and with optimization. It shows the distribution contours of each trial’s best solution. The optimization approach resulted in significantly lower investment expenses. It demonstrated with an optimization approach that produces higher quality solutions. Table 1 represents the result of IEEE 118-bus test system investment cost.

Figure 3.

Convergence features of without and with optimization.

Table 1.

Result of IEEE 118-bus test system investment cost.

Methods	N	$I n v e s t m e n t C o s t$ $(1 0^{3} $)$
Methods	N	Least favorable	Moderate	Most favorable
Without optimization	118	1900	1875	1825
With optimization (IGOA)	118	1300	1275	1240

Table 2 depicts the result of IEEE 118-bus test system cost efficiency. Figure 4 illustrates the investment cost of without and with optimization. The green line represents the investment cost of without optimization and the orange line depicts the investment cost of optimization (IGOA). The optimization approach utilizing the IGOA results in significantly lower investment costs compared to traditional methods.

Table 2.

Result of IEEE 118-bus test system cost efficiency.

Methods	SD	Compute cost efficiency ($)	Processing time (s)
Without optimization	8.2	1800.00	500.000
With optimization (IGOA)	4.8	1225.00	350.000

Figure 4.

Investment cost of without and with optimization.

Discussions

The automated transmission line design utilized ARG to minimize the construction length and expenses. It demonstrated the comparative algorithms in terms of speed and cost reductions of transmission line planning.²⁷ The UAV system is compared with conventional techniques to improve the efficiency and lower the costs for automatic inspection of electric transmission lines. It demonstrated the system’s efficiency in real-world settings by showing better performance than other techniques.²⁸ To identify the ideal transmission line were required to support renewable resources by utilizing a modified sequential evolution approach. The energy loss expenses during the line’s lifetime and optimize the capacity of power facilities. It shows the possible effects of transmission lines on the reliability of operation and efficiency of the system.²⁹ To overcome this, the proposed method, IGOA, analyzes historical transmission data, identifies optimal transmission line placements and capacities, and enhances decision-making by optimizing multiple objectives, including cost, reliability, and efficiency in power transmission planning.

In addition to the improvements in cost and efficiency, the adoption of IGOA for transmission line planning aligns with modern environmental objectives. The optimization process inherently considers geographical constraints, which allows for the identification of transmission routes that minimize disruption to ecosystems and reduce the carbon footprint of infrastructure development. The reduction in investment costs also suggests that resources can be allocated away from invasive projects to more sustainable alternatives. Quantitatively, preliminary assessments indicate potential reductions in land usage by up to 20% in comparison to conventional planning methods. This change directly correlates with decreased habitat disruption and lower emissions associated with construction activities. Future work will aim to incorporate more comprehensive ecological assessments to fully capture the environmental implications of enhanced transmission planning strategies.

Conclusions

The Intelligent Grasshopper Optimization Algorithm (IGOA) approach analyzes historical transmission data, identifies optimal transmission line placement capacities, and enhances decision-making by optimizing multiple objectives, including cost, reliability, and efficiency in power transmission planning. This research intends to utilize massive data mining techniques on historical survey designs to enhance transmission line planning, improving efficiency and reliability in the electrical grid while reducing costs and environmental impact. To address the TEP issue while integrating the power flow model, this study proposes a unique approach utilizing the Intelligent Grasshopper Optimization Algorithm (IGOA). When compared to the traditional approaches, like without optimization, the suggested approach IGOA with optimization using the IEEE 118-bus system performs well in terms of reduced computation time, improved solution quality, and more steady convergence characteristics. The results demonstrate that the plans generated through the proposed IGOA strategy yield significantly lower expansion costs compared to traditional transmission line planning models, exhibiting minimal operational infeasibilities that can be easily addressed in short-term expansion planning. This research highlights a robust framework that can be adapted to various energy systems, ultimately supporting more sustainable and reliable power transmission infrastructure.

Limitations and future scope

Historical technologies used in transmission line planning might be difficult to combine with contemporary data mining methods. Public opposition, environmental evaluations, and regulatory permits were frequently required for transmission line planning. Conventional data mining techniques might struggle to handle real-time data integration such as changing demand, weather, and grid problems. In future research, data mining should include the tools to impact transmission lines’ negative environmental effects and integrate ecological biodiversity data to design routes for systems.

Statements and declarations

Footnotes

Conflicting interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: The study was supported by the State Grid Shandong Electric Power Company Proposition Guide Project “Deepening Application Research on the Whole Process of Planning and Construction Based on 3D Design Results” (No. 2022A-029).

ORCID iD

Chunhui He

Appendix

References

Mallapragada

Bose

, et al. Hydrogen supply chain planning with flexible transmission and storage scheduling. IEEE Trans Sustain Energy 2021; 12(3): 1730–1740. DOI: 10.1109/TSTE.2021.3064015.

Seyyedi

Armand

Shahmoradi

, et al. Iterative optimization of a bi-level formulation to identify severe contingencies in power transmission systems. Int J Electr Power Energy Syst 2023; 145: 108670. DOI: 10.1016/j.ijepes.2022.108670.

Baloch

Muhammad

. An intelligent data mining-based fault detection and classification strategy for microgrid. IEEE Access 2021; 9: 22470–22479. DOI: 10.1109/ACCESS.2021.3056534.

Luo

Yang

, et al. A survey of intelligent transmission line inspection based on unmanned aerial vehicle. Artif Intell Rev 2023; 56(1): 173–201. DOI: 10.1007/s10462-022-10189-2.

González

Sauma

van der Weijde

. Community energy projects in the context of generation and transmission expansion planning. Energy Econ 2022; 108: 105859. DOI: 10.1016/j.eneco.2022.105859.

Souza

Stefenon

Singh

, et al. Hybrid-YOLO for classification of insulators defects in transmission lines based on UAV. Int J Electr Power Energy Syst 2023; 148: 108982. DOI: 10.1016/j.ijepes.2023.108982.

Yuan

Liang

Zhang

, et al. UHVDC transmission line diagnosis method for integrated community energy system based on wavelet analysis. Front Energy Res 2024; 12: 1401285. DOI: 10.3389/fenrg.2024.1401285.

Zheng

Liu

, et al. GEB-YOLO: a novel algorithm for enhanced and efficient detection of foreign objects in power transmission lines. Sci Rep 2024; 14(1): 15769. DOI: 10.1038/s41598-024-64991-9.

Prado

Costa

Silva

, et al. High-frequency-based transmission line percentage differential protection with traveling wave alignment. IEEE Access 2024; 9: 129404–129416. DOI: 10.1109/ACCESS.2024.3456040.

10.

Rajoria

Sharma

. Nature inspired algorithms for transmission network expansion planning problems: a review. Int J Intell Eng Inf 2022; 10(6): 435–463. DOI: 10.1504/IJIEI.2022.129684.

11.

Moradzadeh

Teimourzadeh

Mohammadi-Ivatloo

, et al. Hybrid CNN-LSTM approaches for identification of type and locations of transmission line faults. Int J Electr Power Energy Syst 2022; 135: 107563. DOI: 10.1016/j.ijepes.2021.107563.

12.

Conejo

Liu

, et al. Mixed-integer linear programming models and algorithms for generation and transmission expansion planning of power systems. Eur J Oper Res 2022; 297(3): 1071–1082. DOI: 10.1016/j.ejor.2021.06.024.

13.

Rajesh

Kannan

Vishnupriyan

, et al. Optimally detecting and classifying the transmission line fault in power system using hybrid technique. ISA Trans 2022; 130: 253–264. DOI: 10.1016/j.isatra.2022.03.017.

14.

Teimourzadeh

Moradzadeh

Shoaran

, et al. High impedance single-phase faults diagnosis in transmission lines via deep reinforcement learning of transfer functions. IEEE Access 2021; 9(9): 15796–15809. DOI: 10.1109/ACCESS.2021.3051411.

15.

Chung

Tian

Wang

, et al. Miniaturization of microwave planar circuits using composite microstrip/coplanar-waveguide transmission lines. Alex Eng J 2022; 61(11): 8933–8942. DOI: 10.1016/j.aej.2022.02.027.

16.

Pulazza

Zhang

Kang

, et al. Transmission planning with battery-based energy storage transportation for power systems with high penetration of renewable energy. IEEE Trans Power Syst 2021; 36(6): 4928–4940. DOI: 10.1109/TPWRS.2021.3069649.

17.

Moradi-Sepahvand

Amraee

. Integrated expansion planning of electric energy generation, transmission, and storage for handling high shares of wind and solar power generation. Appl Energy 2021; 298: 117137. DOI: 10.1016/j.apenergy.2021.117137.

18.

Tanneau

Van Hentenryck

. Strong mixed-integer formulations for transmission expansion planning with FACTS devices. Elec Power Syst Res 2024; 235: 110695. DOI: 10.1016/j.epsr.2024.110695.

19.

Wang

Han

, et al. Distributionally robust transmission expansion planning considering uncertainty of contingency probability. J Modern Power Sys Clean Energy 2021; 10(4): 894–901. DOI: 10.35833/MPCE.2020.000768.

20.

Borozan

Giannelos

Falugi

, et al. Machine learning-enhanced benders decomposition approach for the multi-stage stochastic transmission expansion planning problem. Elec Power Syst Res 2024; 237: 110985. DOI: 10.1016/j.epsr.2024.110985.

21.

Nawaz

Albalawi

Bukhari

, et al. Timeseries Fault classification in power transmission lines by non-intrusive feature extraction and selection using supervisare machine learning. IEEE Access 2024; 12: 93426–93449. DOI: 10.1109/ACCESS.2024.3423828.

22.

Dominguez

Prado

Arboleya

, et al. Evolution of knowledge mining from data in power systems: the big data analytics breakthrough. Elec Power Syst Res 2023; 218: 109193. DOI: 10.1016/j.epsr.2023.109193.

23.

Sevilla

Liu

Barocio

, et al. State-of-the-art of data collection, analytics, and future needs of transmission utilities worldwide to account for the continuous growth of sensing data. Int J Electr Power Energy Syst 2022; 137: 107772. DOI: 10.1016/j.ijepes.2021.107772.

24.

Christou

Bocchini

. Framework for probabilistic simulation of power transmission network performance under hurricanes. Reliab Eng Syst Saf 2022; 217: 108072. DOI: 10.1016/j.ress.2021.108072.

25.

El-Meligy

Sharaf

Soliman

. A coordinated scheme for transmission and distribution expansion planning: a tri-level approach. Elec Power Syst Res 2021; 196: 107274. DOI: 10.1016/j.epsr.2021.107274.

26.

Muñoz-Delgado

Contreras

Arroyo

, et al. Integrated transmission and distribution system expansion planning under uncertainty. IEEE Trans Smart Grid 2021; 12(5): 4113–4125. DOI: 10.1109/TSG.2021.3071385.

27.

Nan

Liu

, et al. Transmission line-planning method based on adaptive resolution grid and improved Dijkstra algorithm. Sensors 2023; 23(13): 6214. DOI: 10.3390/s23136214.

28.

Zhou

, et al. Power line-guided automatic electric transmission line inspection system. IEEE Trans Instrum Meas 2022; 71: 1–8. DOI: 10.1109/TIM.2022.3169555.

29.

Ristic

Sosic

. Multicriteria transmission expansion planning based on differential evolution and georeferencing–case study Serbia. Int J Electr Power Energy Syst 2022; 135: 107593. DOI: 10.1016/j.ijepes.2021.107593.