<p>There are a lot of chances to improve home energy efficiency with the growing use of solar photovoltaic (PV) systems with battery storage. The proposed multiplayer battle game-inspired optimizer-synaptic intelligence convolutional neural network (MBGO-SICNN) approach is aimed at maximizing self-consumption rates and reducing reliance on grid energy. Additionally, it reduces the household electricity cost (COE) while simultaneously increasing energy efficiency. Solar photovoltaic system and grid and SICNN are used to forecast the energy demand within the house. The proposed strategy is analyzed under fixed and a time-of-use (TOU) tariffs. The proposed strategy attains the lowest cost of electricity (COE) at 21.17 <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$\text{c}\!\!/$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mtext>c</mtext> <mspace width="-0.166667em" /> <mspace width="-0.166667em" /> <mo stretchy="false">/</mo> </mrow> </math></EquationSource> </InlineEquation>/kWh, significantly reducing electricity costs compared to existing methods such as GOA (22.79 <InlineEquation ID="IEq2"> <EquationSource Format="TEX">$\text{c}\!\!/$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mtext>c</mtext> <mspace width="-0.166667em" /> <mspace width="-0.166667em" /> <mo stretchy="false">/</mo> </mrow> </math></EquationSource> </InlineEquation>/kWh), DGCNN (23.53 <InlineEquation ID="IEq3"> <EquationSource Format="TEX">$\text{c}\!\!/$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mtext>c</mtext> <mspace width="-0.166667em" /> <mspace width="-0.166667em" /> <mo stretchy="false">/</mo> </mrow> </math></EquationSource> </InlineEquation>/kWh), and GA. It indicates the possibility of the proposed MBGO-SICNN strategy to notably improve the efficiency and performance of energy management (EM) in residential photovoltaic-battery systems and initiate for more cost-effective and sustainable energy practices in home settings.</p>

Optimizing residential energy management through an integrated techno-economic evaluation of PV-battery systems

期刊论文
发表日期：

2026年7月23日

查看全文

P. Marish Kumar,
Raghavendran Coona Raja,
Santhana Krishnan Thirumalai,
I. Arul Doss Adaikalam

摘要

There are a lot of chances to improve home energy efficiency with the growing use of solar photovoltaic (PV) systems with battery storage. The proposed multiplayer battle game-inspired optimizer-synaptic intelligence convolutional neural network (MBGO-SICNN) approach is aimed at maximizing self-consumption rates and reducing reliance on grid energy. Additionally, it reduces the household electricity cost (COE) while simultaneously increasing energy efficiency. Solar photovoltaic system and grid and SICNN are used to forecast the energy demand within the house. The proposed strategy is analyzed under fixed and a time-of-use (TOU) tariffs. The proposed strategy attains the lowest cost of electricity (COE) at 21.17 $\text{c}\!\!/$ $c /$ /kWh, significantly reducing electricity costs compared to existing methods such as GOA (22.79 $\text{c}\!\!/$ $c /$ /kWh), DGCNN (23.53 $\text{c}\!\!/$ $c /$ /kWh), and GA. It indicates the possibility of the proposed MBGO-SICNN strategy to notably improve the efficiency and performance of energy management (EM) in residential photovoltaic-battery systems and initiate for more cost-effective and sustainable energy practices in home settings.